{
"method": "safetensors header only; tensor payloads are not loaded",
"schema_version": 1,
"source_pin": "Qwen/Qwen3-TTS-12Hz-0.6B-Base@5d83992436eae1d760afd27aff78a71d676296fc",
"summary": {
"by_dtype": {
"BF16": 478,
"F32": 496
},
"by_source": {
"model.safetensors": 478,
"speech_tokenizer/model.safetensors": 496
},
"payload_bytes": 2511515780,
"tensor_count": 974
},
"tensors": [
{
"bytes": 3072,
"dtype": "BF16",
"elements": 1536,
"name": "speaker_encoder.asp.conv.bias",
"shape": [
1536
],
"source": "model.safetensors"
},
{
"bytes": 393216,
"dtype": "BF16",
"elements": 196608,
"name": "speaker_encoder.asp.conv.weight",
"shape": [
1536,
128,
1
],
"source": "model.safetensors"
},
{
"bytes": 256,
"dtype": "BF16",
"elements": 128,
"name": "speaker_encoder.asp.tdnn.conv.bias",
"shape": [
128
],
"source": "model.safetensors"
},
{
"bytes": 1179648,
"dtype": "BF16",
"elements": 589824,
"name": "speaker_encoder.asp.tdnn.conv.weight",
"shape": [
128,
4608,
1
],
"source": "model.safetensors"
},
{
"bytes": 1024,
"dtype": "BF16",
"elements": 512,
"name": "speaker_encoder.blocks.0.conv.bias",
"shape": [
512
],
"source": "model.safetensors"
},
{
"bytes": 655360,
"dtype": "BF16",
"elements": 327680,
"name": "speaker_encoder.blocks.0.conv.weight",
"shape": [
512,
128,
5
],
"source": "model.safetensors"
},
{
"bytes": 128,
"dtype": "BF16",
"elements": 64,
"name": "speaker_encoder.blocks.1.res2net_block.blocks.0.conv.bias",
"shape": [
64
],
"source": "model.safetensors"
},
{
"bytes": 24576,
"dtype": "BF16",
"elements": 12288,
"name": "speaker_encoder.blocks.1.res2net_block.blocks.0.conv.weight",
"shape": [
64,
64,
3
],
"source": "model.safetensors"
},
{
"bytes": 128,
"dtype": "BF16",
"elements": 64,
"name": "speaker_encoder.blocks.1.res2net_block.blocks.1.conv.bias",
"shape": [
64
],
"source": "model.safetensors"
},
{
"bytes": 24576,
"dtype": "BF16",
"elements": 12288,
"name": "speaker_encoder.blocks.1.res2net_block.blocks.1.conv.weight",
"shape": [
64,
64,
3
],
"source": "model.safetensors"
},
{
"bytes": 128,
"dtype": "BF16",
"elements": 64,
"name": "speaker_encoder.blocks.1.res2net_block.blocks.2.conv.bias",
"shape": [
64
],
"source": "model.safetensors"
},
{
"bytes": 24576,
"dtype": "BF16",
"elements": 12288,
"name": "speaker_encoder.blocks.1.res2net_block.blocks.2.conv.weight",
"shape": [
64,
64,
3
],
"source": "model.safetensors"
},
{
"bytes": 128,
"dtype": "BF16",
"elements": 64,
"name": "speaker_encoder.blocks.1.res2net_block.blocks.3.conv.bias",
"shape": [
64
],
"source": "model.safetensors"
},
{
"bytes": 24576,
"dtype": "BF16",
"elements": 12288,
"name": "speaker_encoder.blocks.1.res2net_block.blocks.3.conv.weight",
"shape": [
64,
64,
3
],
"source": "model.safetensors"
},
{
"bytes": 128,
"dtype": "BF16",
"elements": 64,
"name": "speaker_encoder.blocks.1.res2net_block.blocks.4.conv.bias",
"shape": [
64
],
"source": "model.safetensors"
},
{
"bytes": 24576,
"dtype": "BF16",
"elements": 12288,
"name": "speaker_encoder.blocks.1.res2net_block.blocks.4.conv.weight",
"shape": [
64,
64,
3
],
"source": "model.safetensors"
},
{
"bytes": 128,
"dtype": "BF16",
"elements": 64,
"name": "speaker_encoder.blocks.1.res2net_block.blocks.5.conv.bias",
"shape": [
64
],
"source": "model.safetensors"
},
{
"bytes": 24576,
"dtype": "BF16",
"elements": 12288,
"name": "speaker_encoder.blocks.1.res2net_block.blocks.5.conv.weight",
"shape": [
64,
64,
3
],
"source": "model.safetensors"
},
{
"bytes": 128,
"dtype": "BF16",
"elements": 64,
"name": "speaker_encoder.blocks.1.res2net_block.blocks.6.conv.bias",
"shape": [
64
],
"source": "model.safetensors"
},
{
"bytes": 24576,
"dtype": "BF16",
"elements": 12288,
"name": "speaker_encoder.blocks.1.res2net_block.blocks.6.conv.weight",
"shape": [
64,
64,
3
],
"source": "model.safetensors"
},
{
"bytes": 256,
"dtype": "BF16",
"elements": 128,
"name": "speaker_encoder.blocks.1.se_block.conv1.bias",
"shape": [
128
],
"source": "model.safetensors"
},
{
"bytes": 131072,
"dtype": "BF16",
"elements": 65536,
"name": "speaker_encoder.blocks.1.se_block.conv1.weight",
"shape": [
128,
512,
1
],
"source": "model.safetensors"
},
{
"bytes": 1024,
"dtype": "BF16",
"elements": 512,
"name": "speaker_encoder.blocks.1.se_block.conv2.bias",
"shape": [
512
],
"source": "model.safetensors"
},
{
"bytes": 131072,
"dtype": "BF16",
"elements": 65536,
"name": "speaker_encoder.blocks.1.se_block.conv2.weight",
"shape": [
512,
128,
1
],
"source": "model.safetensors"
},
{
"bytes": 1024,
"dtype": "BF16",
"elements": 512,
"name": "speaker_encoder.blocks.1.tdnn1.conv.bias",
"shape": [
512
],
"source": "model.safetensors"
},
{
"bytes": 524288,
"dtype": "BF16",
"elements": 262144,
"name": "speaker_encoder.blocks.1.tdnn1.conv.weight",
"shape": [
512,
512,
1
],
"source": "model.safetensors"
},
{
"bytes": 1024,
"dtype": "BF16",
"elements": 512,
"name": "speaker_encoder.blocks.1.tdnn2.conv.bias",
"shape": [
512
],
"source": "model.safetensors"
},
{
"bytes": 524288,
"dtype": "BF16",
"elements": 262144,
"name": "speaker_encoder.blocks.1.tdnn2.conv.weight",
"shape": [
512,
512,
1
],
"source": "model.safetensors"
},
{
"bytes": 128,
"dtype": "BF16",
"elements": 64,
"name": "speaker_encoder.blocks.2.res2net_block.blocks.0.conv.bias",
"shape": [
64
],
"source": "model.safetensors"
},
{
"bytes": 24576,
"dtype": "BF16",
"elements": 12288,
"name": "speaker_encoder.blocks.2.res2net_block.blocks.0.conv.weight",
"shape": [
64,
64,
3
],
"source": "model.safetensors"
},
{
"bytes": 128,
"dtype": "BF16",
"elements": 64,
"name": "speaker_encoder.blocks.2.res2net_block.blocks.1.conv.bias",
"shape": [
64
],
"source": "model.safetensors"
},
{
"bytes": 24576,
"dtype": "BF16",
"elements": 12288,
"name": "speaker_encoder.blocks.2.res2net_block.blocks.1.conv.weight",
"shape": [
64,
64,
3
],
"source": "model.safetensors"
},
{
"bytes": 128,
"dtype": "BF16",
"elements": 64,
"name": "speaker_encoder.blocks.2.res2net_block.blocks.2.conv.bias",
"shape": [
64
],
"source": "model.safetensors"
},
{
"bytes": 24576,
"dtype": "BF16",
"elements": 12288,
"name": "speaker_encoder.blocks.2.res2net_block.blocks.2.conv.weight",
"shape": [
64,
64,
3
],
"source": "model.safetensors"
},
{
"bytes": 128,
"dtype": "BF16",
"elements": 64,
"name": "speaker_encoder.blocks.2.res2net_block.blocks.3.conv.bias",
"shape": [
64
],
"source": "model.safetensors"
},
{
"bytes": 24576,
"dtype": "BF16",
"elements": 12288,
"name": "speaker_encoder.blocks.2.res2net_block.blocks.3.conv.weight",
"shape": [
64,
64,
3
],
"source": "model.safetensors"
},
{
"bytes": 128,
"dtype": "BF16",
"elements": 64,
"name": "speaker_encoder.blocks.2.res2net_block.blocks.4.conv.bias",
"shape": [
64
],
"source": "model.safetensors"
},
{
"bytes": 24576,
"dtype": "BF16",
"elements": 12288,
"name": "speaker_encoder.blocks.2.res2net_block.blocks.4.conv.weight",
"shape": [
64,
64,
3
],
"source": "model.safetensors"
},
{
"bytes": 128,
"dtype": "BF16",
"elements": 64,
"name": "speaker_encoder.blocks.2.res2net_block.blocks.5.conv.bias",
"shape": [
64
],
"source": "model.safetensors"
},
{
"bytes": 24576,
"dtype": "BF16",
"elements": 12288,
"name": "speaker_encoder.blocks.2.res2net_block.blocks.5.conv.weight",
"shape": [
64,
64,
3
],
"source": "model.safetensors"
},
{
"bytes": 128,
"dtype": "BF16",
"elements": 64,
"name": "speaker_encoder.blocks.2.res2net_block.blocks.6.conv.bias",
"shape": [
64
],
"source": "model.safetensors"
},
{
"bytes": 24576,
"dtype": "BF16",
"elements": 12288,
"name": "speaker_encoder.blocks.2.res2net_block.blocks.6.conv.weight",
"shape": [
64,
64,
3
],
"source": "model.safetensors"
},
{
"bytes": 256,
"dtype": "BF16",
"elements": 128,
"name": "speaker_encoder.blocks.2.se_block.conv1.bias",
"shape": [
128
],
"source": "model.safetensors"
},
{
"bytes": 131072,
"dtype": "BF16",
"elements": 65536,
"name": "speaker_encoder.blocks.2.se_block.conv1.weight",
"shape": [
128,
512,
1
],
"source": "model.safetensors"
},
{
"bytes": 1024,
"dtype": "BF16",
"elements": 512,
"name": "speaker_encoder.blocks.2.se_block.conv2.bias",
"shape": [
512
],
"source": "model.safetensors"
},
{
"bytes": 131072,
"dtype": "BF16",
"elements": 65536,
"name": "speaker_encoder.blocks.2.se_block.conv2.weight",
"shape": [
512,
128,
1
],
"source": "model.safetensors"
},
{
"bytes": 1024,
"dtype": "BF16",
"elements": 512,
"name": "speaker_encoder.blocks.2.tdnn1.conv.bias",
"shape": [
512
],
"source": "model.safetensors"
},
{
"bytes": 524288,
"dtype": "BF16",
"elements": 262144,
"name": "speaker_encoder.blocks.2.tdnn1.conv.weight",
"shape": [
512,
512,
1
],
"source": "model.safetensors"
},
{
"bytes": 1024,
"dtype": "BF16",
"elements": 512,
"name": "speaker_encoder.blocks.2.tdnn2.conv.bias",
"shape": [
512
],
"source": "model.safetensors"
},
{
"bytes": 524288,
"dtype": "BF16",
"elements": 262144,
"name": "speaker_encoder.blocks.2.tdnn2.conv.weight",
"shape": [
512,
512,
1
],
"source": "model.safetensors"
},
{
"bytes": 128,
"dtype": "BF16",
"elements": 64,
"name": "speaker_encoder.blocks.3.res2net_block.blocks.0.conv.bias",
"shape": [
64
],
"source": "model.safetensors"
},
{
"bytes": 24576,
"dtype": "BF16",
"elements": 12288,
"name": "speaker_encoder.blocks.3.res2net_block.blocks.0.conv.weight",
"shape": [
64,
64,
3
],
"source": "model.safetensors"
},
{
"bytes": 128,
"dtype": "BF16",
"elements": 64,
"name": "speaker_encoder.blocks.3.res2net_block.blocks.1.conv.bias",
"shape": [
64
],
"source": "model.safetensors"
},
{
"bytes": 24576,
"dtype": "BF16",
"elements": 12288,
"name": "speaker_encoder.blocks.3.res2net_block.blocks.1.conv.weight",
"shape": [
64,
64,
3
],
"source": "model.safetensors"
},
{
"bytes": 128,
"dtype": "BF16",
"elements": 64,
"name": "speaker_encoder.blocks.3.res2net_block.blocks.2.conv.bias",
"shape": [
64
],
"source": "model.safetensors"
},
{
"bytes": 24576,
"dtype": "BF16",
"elements": 12288,
"name": "speaker_encoder.blocks.3.res2net_block.blocks.2.conv.weight",
"shape": [
64,
64,
3
],
"source": "model.safetensors"
},
{
"bytes": 128,
"dtype": "BF16",
"elements": 64,
"name": "speaker_encoder.blocks.3.res2net_block.blocks.3.conv.bias",
"shape": [
64
],
"source": "model.safetensors"
},
{
"bytes": 24576,
"dtype": "BF16",
"elements": 12288,
"name": "speaker_encoder.blocks.3.res2net_block.blocks.3.conv.weight",
"shape": [
64,
64,
3
],
"source": "model.safetensors"
},
{
"bytes": 128,
"dtype": "BF16",
"elements": 64,
"name": "speaker_encoder.blocks.3.res2net_block.blocks.4.conv.bias",
"shape": [
64
],
"source": "model.safetensors"
},
{
"bytes": 24576,
"dtype": "BF16",
"elements": 12288,
"name": "speaker_encoder.blocks.3.res2net_block.blocks.4.conv.weight",
"shape": [
64,
64,
3
],
"source": "model.safetensors"
},
{
"bytes": 128,
"dtype": "BF16",
"elements": 64,
"name": "speaker_encoder.blocks.3.res2net_block.blocks.5.conv.bias",
"shape": [
64
],
"source": "model.safetensors"
},
{
"bytes": 24576,
"dtype": "BF16",
"elements": 12288,
"name": "speaker_encoder.blocks.3.res2net_block.blocks.5.conv.weight",
"shape": [
64,
64,
3
],
"source": "model.safetensors"
},
{
"bytes": 128,
"dtype": "BF16",
"elements": 64,
"name": "speaker_encoder.blocks.3.res2net_block.blocks.6.conv.bias",
"shape": [
64
],
"source": "model.safetensors"
},
{
"bytes": 24576,
"dtype": "BF16",
"elements": 12288,
"name": "speaker_encoder.blocks.3.res2net_block.blocks.6.conv.weight",
"shape": [
64,
64,
3
],
"source": "model.safetensors"
},
{
"bytes": 256,
"dtype": "BF16",
"elements": 128,
"name": "speaker_encoder.blocks.3.se_block.conv1.bias",
"shape": [
128
],
"source": "model.safetensors"
},
{
"bytes": 131072,
"dtype": "BF16",
"elements": 65536,
"name": "speaker_encoder.blocks.3.se_block.conv1.weight",
"shape": [
128,
512,
1
],
"source": "model.safetensors"
},
{
"bytes": 1024,
"dtype": "BF16",
"elements": 512,
"name": "speaker_encoder.blocks.3.se_block.conv2.bias",
"shape": [
512
],
"source": "model.safetensors"
},
{
"bytes": 131072,
"dtype": "BF16",
"elements": 65536,
"name": "speaker_encoder.blocks.3.se_block.conv2.weight",
"shape": [
512,
128,
1
],
"source": "model.safetensors"
},
{
"bytes": 1024,
"dtype": "BF16",
"elements": 512,
"name": "speaker_encoder.blocks.3.tdnn1.conv.bias",
"shape": [
512
],
"source": "model.safetensors"
},
{
"bytes": 524288,
"dtype": "BF16",
"elements": 262144,
"name": "speaker_encoder.blocks.3.tdnn1.conv.weight",
"shape": [
512,
512,
1
],
"source": "model.safetensors"
},
{
"bytes": 1024,
"dtype": "BF16",
"elements": 512,
"name": "speaker_encoder.blocks.3.tdnn2.conv.bias",
"shape": [
512
],
"source": "model.safetensors"
},
{
"bytes": 524288,
"dtype": "BF16",
"elements": 262144,
"name": "speaker_encoder.blocks.3.tdnn2.conv.weight",
"shape": [
512,
512,
1
],
"source": "model.safetensors"
},
{
"bytes": 2048,
"dtype": "BF16",
"elements": 1024,
"name": "speaker_encoder.fc.bias",
"shape": [
1024
],
"source": "model.safetensors"
},
{
"bytes": 6291456,
"dtype": "BF16",
"elements": 3145728,
"name": "speaker_encoder.fc.weight",
"shape": [
1024,
3072,
1
],
"source": "model.safetensors"
},
{
"bytes": 3072,
"dtype": "BF16",
"elements": 1536,
"name": "speaker_encoder.mfa.conv.bias",
"shape": [
1536
],
"source": "model.safetensors"
},
{
"bytes": 4718592,
"dtype": "BF16",
"elements": 2359296,
"name": "speaker_encoder.mfa.conv.weight",
"shape": [
1536,
1536,
1
],
"source": "model.safetensors"
},
{
"bytes": 4194304,
"dtype": "BF16",
"elements": 2097152,
"name": "talker.code_predictor.lm_head.0.weight",
"shape": [
2048,
1024
],
"source": "model.safetensors"
},
{
"bytes": 4194304,
"dtype": "BF16",
"elements": 2097152,
"name": "talker.code_predictor.lm_head.1.weight",
"shape": [
2048,
1024
],
"source": "model.safetensors"
},
{
"bytes": 4194304,
"dtype": "BF16",
"elements": 2097152,
"name": "talker.code_predictor.lm_head.10.weight",
"shape": [
2048,
1024
],
"source": "model.safetensors"
},
{
"bytes": 4194304,
"dtype": "BF16",
"elements": 2097152,
"name": "talker.code_predictor.lm_head.11.weight",
"shape": [
2048,
1024
],
"source": "model.safetensors"
},
{
"bytes": 4194304,
"dtype": "BF16",
"elements": 2097152,
"name": "talker.code_predictor.lm_head.12.weight",
"shape": [
2048,
1024
],
"source": "model.safetensors"
},
{
"bytes": 4194304,
"dtype": "BF16",
"elements": 2097152,
"name": "talker.code_predictor.lm_head.13.weight",
"shape": [
2048,
1024
],
"source": "model.safetensors"
},
{
"bytes": 4194304,
"dtype": "BF16",
"elements": 2097152,
"name": "talker.code_predictor.lm_head.14.weight",
"shape": [
2048,
1024
],
"source": "model.safetensors"
},
{
"bytes": 4194304,
"dtype": "BF16",
"elements": 2097152,
"name": "talker.code_predictor.lm_head.2.weight",
"shape": [
2048,
1024
],
"source": "model.safetensors"
},
{
"bytes": 4194304,
"dtype": "BF16",
"elements": 2097152,
"name": "talker.code_predictor.lm_head.3.weight",
"shape": [
2048,
1024
],
"source": "model.safetensors"
},
{
"bytes": 4194304,
"dtype": "BF16",
"elements": 2097152,
"name": "talker.code_predictor.lm_head.4.weight",
"shape": [
2048,
1024
],
"source": "model.safetensors"
},
{
"bytes": 4194304,
"dtype": "BF16",
"elements": 2097152,
"name": "talker.code_predictor.lm_head.5.weight",
"shape": [
2048,
1024
],
"source": "model.safetensors"
},
{
"bytes": 4194304,
"dtype": "BF16",
"elements": 2097152,
"name": "talker.code_predictor.lm_head.6.weight",
"shape": [
2048,
1024
],
"source": "model.safetensors"
},
{
"bytes": 4194304,
"dtype": "BF16",
"elements": 2097152,
"name": "talker.code_predictor.lm_head.7.weight",
"shape": [
2048,
1024
],
"source": "model.safetensors"
},
{
"bytes": 4194304,
"dtype": "BF16",
"elements": 2097152,
"name": "talker.code_predictor.lm_head.8.weight",
"shape": [
2048,
1024
],
"source": "model.safetensors"
},
{
"bytes": 4194304,
"dtype": "BF16",
"elements": 2097152,
"name": "talker.code_predictor.lm_head.9.weight",
"shape": [
2048,
1024
],
"source": "model.safetensors"
},
{
"bytes": 4194304,
"dtype": "BF16",
"elements": 2097152,
"name": "talker.code_predictor.model.codec_embedding.0.weight",
"shape": [
2048,
1024
],
"source": "model.safetensors"
},
{
"bytes": 4194304,
"dtype": "BF16",
"elements": 2097152,
"name": "talker.code_predictor.model.codec_embedding.1.weight",
"shape": [
2048,
1024
],
"source": "model.safetensors"
},
{
"bytes": 4194304,
"dtype": "BF16",
"elements": 2097152,
"name": "talker.code_predictor.model.codec_embedding.10.weight",
"shape": [
2048,
1024
],
"source": "model.safetensors"
},
{
"bytes": 4194304,
"dtype": "BF16",
"elements": 2097152,
"name": "talker.code_predictor.model.codec_embedding.11.weight",
"shape": [
2048,
1024
],
"source": "model.safetensors"
},
{
"bytes": 4194304,
"dtype": "BF16",
"elements": 2097152,
"name": "talker.code_predictor.model.codec_embedding.12.weight",
"shape": [
2048,
1024
],
"source": "model.safetensors"
},
{
"bytes": 4194304,
"dtype": "BF16",
"elements": 2097152,
"name": "talker.code_predictor.model.codec_embedding.13.weight",
"shape": [
2048,
1024
],
"source": "model.safetensors"
},
{
"bytes": 4194304,
"dtype": "BF16",
"elements": 2097152,
"name": "talker.code_predictor.model.codec_embedding.14.weight",
"shape": [
2048,
1024
],
"source": "model.safetensors"
},
{
"bytes": 4194304,
"dtype": "BF16",
"elements": 2097152,
"name": "talker.code_predictor.model.codec_embedding.2.weight",
"shape": [
2048,
1024
],
"source": "model.safetensors"
},
{
"bytes": 4194304,
"dtype": "BF16",
"elements": 2097152,
"name": "talker.code_predictor.model.codec_embedding.3.weight",
"shape": [
2048,
1024
],
"source": "model.safetensors"
},
{
"bytes": 4194304,
"dtype": "BF16",
"elements": 2097152,
"name": "talker.code_predictor.model.codec_embedding.4.weight",
"shape": [
2048,
1024
],
"source": "model.safetensors"
},
{
"bytes": 4194304,
"dtype": "BF16",
"elements": 2097152,
"name": "talker.code_predictor.model.codec_embedding.5.weight",
"shape": [
2048,
1024
],
"source": "model.safetensors"
},
{
"bytes": 4194304,
"dtype": "BF16",
"elements": 2097152,
"name": "talker.code_predictor.model.codec_embedding.6.weight",
"shape": [
2048,
1024
],
"source": "model.safetensors"
},
{
"bytes": 4194304,
"dtype": "BF16",
"elements": 2097152,
"name": "talker.code_predictor.model.codec_embedding.7.weight",
"shape": [
2048,
1024
],
"source": "model.safetensors"
},
{
"bytes": 4194304,
"dtype": "BF16",
"elements": 2097152,
"name": "talker.code_predictor.model.codec_embedding.8.weight",
"shape": [
2048,
1024
],
"source": "model.safetensors"
},
{
"bytes": 4194304,
"dtype": "BF16",
"elements": 2097152,
"name": "talker.code_predictor.model.codec_embedding.9.weight",
"shape": [
2048,
1024
],
"source": "model.safetensors"
},
{
"bytes": 2048,
"dtype": "BF16",
"elements": 1024,
"name": "talker.code_predictor.model.layers.0.input_layernorm.weight",
"shape": [
1024
],
"source": "model.safetensors"
},
{
"bytes": 6291456,
"dtype": "BF16",
"elements": 3145728,
"name": "talker.code_predictor.model.layers.0.mlp.down_proj.weight",
"shape": [
1024,
3072
],
"source": "model.safetensors"
},
{
"bytes": 6291456,
"dtype": "BF16",
"elements": 3145728,
"name": "talker.code_predictor.model.layers.0.mlp.gate_proj.weight",
"shape": [
3072,
1024
],
"source": "model.safetensors"
},
{
"bytes": 6291456,
"dtype": "BF16",
"elements": 3145728,
"name": "talker.code_predictor.model.layers.0.mlp.up_proj.weight",
"shape": [
3072,
1024
],
"source": "model.safetensors"
},
{
"bytes": 2048,
"dtype": "BF16",
"elements": 1024,
"name": "talker.code_predictor.model.layers.0.post_attention_layernorm.weight",
"shape": [
1024
],
"source": "model.safetensors"
},
{
"bytes": 256,
"dtype": "BF16",
"elements": 128,
"name": "talker.code_predictor.model.layers.0.self_attn.k_norm.weight",
"shape": [
128
],
"source": "model.safetensors"
},
{
"bytes": 2097152,
"dtype": "BF16",
"elements": 1048576,
"name": "talker.code_predictor.model.layers.0.self_attn.k_proj.weight",
"shape": [
1024,
1024
],
"source": "model.safetensors"
},
{
"bytes": 4194304,
"dtype": "BF16",
"elements": 2097152,
"name": "talker.code_predictor.model.layers.0.self_attn.o_proj.weight",
"shape": [
1024,
2048
],
"source": "model.safetensors"
},
{
"bytes": 256,
"dtype": "BF16",
"elements": 128,
"name": "talker.code_predictor.model.layers.0.self_attn.q_norm.weight",
"shape": [
128
],
"source": "model.safetensors"
},
{
"bytes": 4194304,
"dtype": "BF16",
"elements": 2097152,
"name": "talker.code_predictor.model.layers.0.self_attn.q_proj.weight",
"shape": [
2048,
1024
],
"source": "model.safetensors"
},
{
"bytes": 2097152,
"dtype": "BF16",
"elements": 1048576,
"name": "talker.code_predictor.model.layers.0.self_attn.v_proj.weight",
"shape": [
1024,
1024
],
"source": "model.safetensors"
},
{
"bytes": 2048,
"dtype": "BF16",
"elements": 1024,
"name": "talker.code_predictor.model.layers.1.input_layernorm.weight",
"shape": [
1024
],
"source": "model.safetensors"
},
{
"bytes": 6291456,
"dtype": "BF16",
"elements": 3145728,
"name": "talker.code_predictor.model.layers.1.mlp.down_proj.weight",
"shape": [
1024,
3072
],
"source": "model.safetensors"
},
{
"bytes": 6291456,
"dtype": "BF16",
"elements": 3145728,
"name": "talker.code_predictor.model.layers.1.mlp.gate_proj.weight",
"shape": [
3072,
1024
],
"source": "model.safetensors"
},
{
"bytes": 6291456,
"dtype": "BF16",
"elements": 3145728,
"name": "talker.code_predictor.model.layers.1.mlp.up_proj.weight",
"shape": [
3072,
1024
],
"source": "model.safetensors"
},
{
"bytes": 2048,
"dtype": "BF16",
"elements": 1024,
"name": "talker.code_predictor.model.layers.1.post_attention_layernorm.weight",
"shape": [
1024
],
"source": "model.safetensors"
},
{
"bytes": 256,
"dtype": "BF16",
"elements": 128,
"name": "talker.code_predictor.model.layers.1.self_attn.k_norm.weight",
"shape": [
128
],
"source": "model.safetensors"
},
{
"bytes": 2097152,
"dtype": "BF16",
"elements": 1048576,
"name": "talker.code_predictor.model.layers.1.self_attn.k_proj.weight",
"shape": [
1024,
1024
],
"source": "model.safetensors"
},
{
"bytes": 4194304,
"dtype": "BF16",
"elements": 2097152,
"name": "talker.code_predictor.model.layers.1.self_attn.o_proj.weight",
"shape": [
1024,
2048
],
"source": "model.safetensors"
},
{
"bytes": 256,
"dtype": "BF16",
"elements": 128,
"name": "talker.code_predictor.model.layers.1.self_attn.q_norm.weight",
"shape": [
128
],
"source": "model.safetensors"
},
{
"bytes": 4194304,
"dtype": "BF16",
"elements": 2097152,
"name": "talker.code_predictor.model.layers.1.self_attn.q_proj.weight",
"shape": [
2048,
1024
],
"source": "model.safetensors"
},
{
"bytes": 2097152,
"dtype": "BF16",
"elements": 1048576,
"name": "talker.code_predictor.model.layers.1.self_attn.v_proj.weight",
"shape": [
1024,
1024
],
"source": "model.safetensors"
},
{
"bytes": 2048,
"dtype": "BF16",
"elements": 1024,
"name": "talker.code_predictor.model.layers.2.input_layernorm.weight",
"shape": [
1024
],
"source": "model.safetensors"
},
{
"bytes": 6291456,
"dtype": "BF16",
"elements": 3145728,
"name": "talker.code_predictor.model.layers.2.mlp.down_proj.weight",
"shape": [
1024,
3072
],
"source": "model.safetensors"
},
{
"bytes": 6291456,
"dtype": "BF16",
"elements": 3145728,
"name": "talker.code_predictor.model.layers.2.mlp.gate_proj.weight",
"shape": [
3072,
1024
],
"source": "model.safetensors"
},
{
"bytes": 6291456,
"dtype": "BF16",
"elements": 3145728,
"name": "talker.code_predictor.model.layers.2.mlp.up_proj.weight",
"shape": [
3072,
1024
],
"source": "model.safetensors"
},
{
"bytes": 2048,
"dtype": "BF16",
"elements": 1024,
"name": "talker.code_predictor.model.layers.2.post_attention_layernorm.weight",
"shape": [
1024
],
"source": "model.safetensors"
},
{
"bytes": 256,
"dtype": "BF16",
"elements": 128,
"name": "talker.code_predictor.model.layers.2.self_attn.k_norm.weight",
"shape": [
128
],
"source": "model.safetensors"
},
{
"bytes": 2097152,
"dtype": "BF16",
"elements": 1048576,
"name": "talker.code_predictor.model.layers.2.self_attn.k_proj.weight",
"shape": [
1024,
1024
],
"source": "model.safetensors"
},
{
"bytes": 4194304,
"dtype": "BF16",
"elements": 2097152,
"name": "talker.code_predictor.model.layers.2.self_attn.o_proj.weight",
"shape": [
1024,
2048
],
"source": "model.safetensors"
},
{
"bytes": 256,
"dtype": "BF16",
"elements": 128,
"name": "talker.code_predictor.model.layers.2.self_attn.q_norm.weight",
"shape": [
128
],
"source": "model.safetensors"
},
{
"bytes": 4194304,
"dtype": "BF16",
"elements": 2097152,
"name": "talker.code_predictor.model.layers.2.self_attn.q_proj.weight",
"shape": [
2048,
1024
],
"source": "model.safetensors"
},
{
"bytes": 2097152,
"dtype": "BF16",
"elements": 1048576,
"name": "talker.code_predictor.model.layers.2.self_attn.v_proj.weight",
"shape": [
1024,
1024
],
"source": "model.safetensors"
},
{
"bytes": 2048,
"dtype": "BF16",
"elements": 1024,
"name": "talker.code_predictor.model.layers.3.input_layernorm.weight",
"shape": [
1024
],
"source": "model.safetensors"
},
{
"bytes": 6291456,
"dtype": "BF16",
"elements": 3145728,
"name": "talker.code_predictor.model.layers.3.mlp.down_proj.weight",
"shape": [
1024,
3072
],
"source": "model.safetensors"
},
{
"bytes": 6291456,
"dtype": "BF16",
"elements": 3145728,
"name": "talker.code_predictor.model.layers.3.mlp.gate_proj.weight",
"shape": [
3072,
1024
],
"source": "model.safetensors"
},
{
"bytes": 6291456,
"dtype": "BF16",
"elements": 3145728,
"name": "talker.code_predictor.model.layers.3.mlp.up_proj.weight",
"shape": [
3072,
1024
],
"source": "model.safetensors"
},
{
"bytes": 2048,
"dtype": "BF16",
"elements": 1024,
"name": "talker.code_predictor.model.layers.3.post_attention_layernorm.weight",
"shape": [
1024
],
"source": "model.safetensors"
},
{
"bytes": 256,
"dtype": "BF16",
"elements": 128,
"name": "talker.code_predictor.model.layers.3.self_attn.k_norm.weight",
"shape": [
128
],
"source": "model.safetensors"
},
{
"bytes": 2097152,
"dtype": "BF16",
"elements": 1048576,
"name": "talker.code_predictor.model.layers.3.self_attn.k_proj.weight",
"shape": [
1024,
1024
],
"source": "model.safetensors"
},
{
"bytes": 4194304,
"dtype": "BF16",
"elements": 2097152,
"name": "talker.code_predictor.model.layers.3.self_attn.o_proj.weight",
"shape": [
1024,
2048
],
"source": "model.safetensors"
},
{
"bytes": 256,
"dtype": "BF16",
"elements": 128,
"name": "talker.code_predictor.model.layers.3.self_attn.q_norm.weight",
"shape": [
128
],
"source": "model.safetensors"
},
{
"bytes": 4194304,
"dtype": "BF16",
"elements": 2097152,
"name": "talker.code_predictor.model.layers.3.self_attn.q_proj.weight",
"shape": [
2048,
1024
],
"source": "model.safetensors"
},
{
"bytes": 2097152,
"dtype": "BF16",
"elements": 1048576,
"name": "talker.code_predictor.model.layers.3.self_attn.v_proj.weight",
"shape": [
1024,
1024
],
"source": "model.safetensors"
},
{
"bytes": 2048,
"dtype": "BF16",
"elements": 1024,
"name": "talker.code_predictor.model.layers.4.input_layernorm.weight",
"shape": [
1024
],
"source": "model.safetensors"
},
{
"bytes": 6291456,
"dtype": "BF16",
"elements": 3145728,
"name": "talker.code_predictor.model.layers.4.mlp.down_proj.weight",
"shape": [
1024,
3072
],
"source": "model.safetensors"
},
{
"bytes": 6291456,
"dtype": "BF16",
"elements": 3145728,
"name": "talker.code_predictor.model.layers.4.mlp.gate_proj.weight",
"shape": [
3072,
1024
],
"source": "model.safetensors"
},
{
"bytes": 6291456,
"dtype": "BF16",
"elements": 3145728,
"name": "talker.code_predictor.model.layers.4.mlp.up_proj.weight",
"shape": [
3072,
1024
],
"source": "model.safetensors"
},
{
"bytes": 2048,
"dtype": "BF16",
"elements": 1024,
"name": "talker.code_predictor.model.layers.4.post_attention_layernorm.weight",
"shape": [
1024
],
"source": "model.safetensors"
},
{
"bytes": 256,
"dtype": "BF16",
"elements": 128,
"name": "talker.code_predictor.model.layers.4.self_attn.k_norm.weight",
"shape": [
128
],
"source": "model.safetensors"
},
{
"bytes": 2097152,
"dtype": "BF16",
"elements": 1048576,
"name": "talker.code_predictor.model.layers.4.self_attn.k_proj.weight",
"shape": [
1024,
1024
],
"source": "model.safetensors"
},
{
"bytes": 4194304,
"dtype": "BF16",
"elements": 2097152,
"name": "talker.code_predictor.model.layers.4.self_attn.o_proj.weight",
"shape": [
1024,
2048
],
"source": "model.safetensors"
},
{
"bytes": 256,
"dtype": "BF16",
"elements": 128,
"name": "talker.code_predictor.model.layers.4.self_attn.q_norm.weight",
"shape": [
128
],
"source": "model.safetensors"
},
{
"bytes": 4194304,
"dtype": "BF16",
"elements": 2097152,
"name": "talker.code_predictor.model.layers.4.self_attn.q_proj.weight",
"shape": [
2048,
1024
],
"source": "model.safetensors"
},
{
"bytes": 2097152,
"dtype": "BF16",
"elements": 1048576,
"name": "talker.code_predictor.model.layers.4.self_attn.v_proj.weight",
"shape": [
1024,
1024
],
"source": "model.safetensors"
},
{
"bytes": 2048,
"dtype": "BF16",
"elements": 1024,
"name": "talker.code_predictor.model.norm.weight",
"shape": [
1024
],
"source": "model.safetensors"
},
{
"bytes": 6291456,
"dtype": "BF16",
"elements": 3145728,
"name": "talker.codec_head.weight",
"shape": [
3072,
1024
],
"source": "model.safetensors"
},
{
"bytes": 6291456,
"dtype": "BF16",
"elements": 3145728,
"name": "talker.model.codec_embedding.weight",
"shape": [
3072,
1024
],
"source": "model.safetensors"
},
{
"bytes": 2048,
"dtype": "BF16",
"elements": 1024,
"name": "talker.model.layers.0.input_layernorm.weight",
"shape": [
1024
],
"source": "model.safetensors"
},
{
"bytes": 6291456,
"dtype": "BF16",
"elements": 3145728,
"name": "talker.model.layers.0.mlp.down_proj.weight",
"shape": [
1024,
3072
],
"source": "model.safetensors"
},
{
"bytes": 6291456,
"dtype": "BF16",
"elements": 3145728,
"name": "talker.model.layers.0.mlp.gate_proj.weight",
"shape": [
3072,
1024
],
"source": "model.safetensors"
},
{
"bytes": 6291456,
"dtype": "BF16",
"elements": 3145728,
"name": "talker.model.layers.0.mlp.up_proj.weight",
"shape": [
3072,
1024
],
"source": "model.safetensors"
},
{
"bytes": 2048,
"dtype": "BF16",
"elements": 1024,
"name": "talker.model.layers.0.post_attention_layernorm.weight",
"shape": [
1024
],
"source": "model.safetensors"
},
{
"bytes": 256,
"dtype": "BF16",
"elements": 128,
"name": "talker.model.layers.0.self_attn.k_norm.weight",
"shape": [
128
],
"source": "model.safetensors"
},
{
"bytes": 2097152,
"dtype": "BF16",
"elements": 1048576,
"name": "talker.model.layers.0.self_attn.k_proj.weight",
"shape": [
1024,
1024
],
"source": "model.safetensors"
},
{
"bytes": 4194304,
"dtype": "BF16",
"elements": 2097152,
"name": "talker.model.layers.0.self_attn.o_proj.weight",
"shape": [
1024,
2048
],
"source": "model.safetensors"
},
{
"bytes": 256,
"dtype": "BF16",
"elements": 128,
"name": "talker.model.layers.0.self_attn.q_norm.weight",
"shape": [
128
],
"source": "model.safetensors"
},
{
"bytes": 4194304,
"dtype": "BF16",
"elements": 2097152,
"name": "talker.model.layers.0.self_attn.q_proj.weight",
"shape": [
2048,
1024
],
"source": "model.safetensors"
},
{
"bytes": 2097152,
"dtype": "BF16",
"elements": 1048576,
"name": "talker.model.layers.0.self_attn.v_proj.weight",
"shape": [
1024,
1024
],
"source": "model.safetensors"
},
{
"bytes": 2048,
"dtype": "BF16",
"elements": 1024,
"name": "talker.model.layers.1.input_layernorm.weight",
"shape": [
1024
],
"source": "model.safetensors"
},
{
"bytes": 6291456,
"dtype": "BF16",
"elements": 3145728,
"name": "talker.model.layers.1.mlp.down_proj.weight",
"shape": [
1024,
3072
],
"source": "model.safetensors"
},
{
"bytes": 6291456,
"dtype": "BF16",
"elements": 3145728,
"name": "talker.model.layers.1.mlp.gate_proj.weight",
"shape": [
3072,
1024
],
"source": "model.safetensors"
},
{
"bytes": 6291456,
"dtype": "BF16",
"elements": 3145728,
"name": "talker.model.layers.1.mlp.up_proj.weight",
"shape": [
3072,
1024
],
"source": "model.safetensors"
},
{
"bytes": 2048,
"dtype": "BF16",
"elements": 1024,
"name": "talker.model.layers.1.post_attention_layernorm.weight",
"shape": [
1024
],
"source": "model.safetensors"
},
{
"bytes": 256,
"dtype": "BF16",
"elements": 128,
"name": "talker.model.layers.1.self_attn.k_norm.weight",
"shape": [
128
],
"source": "model.safetensors"
},
{
"bytes": 2097152,
"dtype": "BF16",
"elements": 1048576,
"name": "talker.model.layers.1.self_attn.k_proj.weight",
"shape": [
1024,
1024
],
"source": "model.safetensors"
},
{
"bytes": 4194304,
"dtype": "BF16",
"elements": 2097152,
"name": "talker.model.layers.1.self_attn.o_proj.weight",
"shape": [
1024,
2048
],
"source": "model.safetensors"
},
{
"bytes": 256,
"dtype": "BF16",
"elements": 128,
"name": "talker.model.layers.1.self_attn.q_norm.weight",
"shape": [
128
],
"source": "model.safetensors"
},
{
"bytes": 4194304,
"dtype": "BF16",
"elements": 2097152,
"name": "talker.model.layers.1.self_attn.q_proj.weight",
"shape": [
2048,
1024
],
"source": "model.safetensors"
},
{
"bytes": 2097152,
"dtype": "BF16",
"elements": 1048576,
"name": "talker.model.layers.1.self_attn.v_proj.weight",
"shape": [
1024,
1024
],
"source": "model.safetensors"
},
{
"bytes": 2048,
"dtype": "BF16",
"elements": 1024,
"name": "talker.model.layers.10.input_layernorm.weight",
"shape": [
1024
],
"source": "model.safetensors"
},
{
"bytes": 6291456,
"dtype": "BF16",
"elements": 3145728,
"name": "talker.model.layers.10.mlp.down_proj.weight",
"shape": [
1024,
3072
],
"source": "model.safetensors"
},
{
"bytes": 6291456,
"dtype": "BF16",
"elements": 3145728,
"name": "talker.model.layers.10.mlp.gate_proj.weight",
"shape": [
3072,
1024
],
"source": "model.safetensors"
},
{
"bytes": 6291456,
"dtype": "BF16",
"elements": 3145728,
"name": "talker.model.layers.10.mlp.up_proj.weight",
"shape": [
3072,
1024
],
"source": "model.safetensors"
},
{
"bytes": 2048,
"dtype": "BF16",
"elements": 1024,
"name": "talker.model.layers.10.post_attention_layernorm.weight",
"shape": [
1024
],
"source": "model.safetensors"
},
{
"bytes": 256,
"dtype": "BF16",
"elements": 128,
"name": "talker.model.layers.10.self_attn.k_norm.weight",
"shape": [
128
],
"source": "model.safetensors"
},
{
"bytes": 2097152,
"dtype": "BF16",
"elements": 1048576,
"name": "talker.model.layers.10.self_attn.k_proj.weight",
"shape": [
1024,
1024
],
"source": "model.safetensors"
},
{
"bytes": 4194304,
"dtype": "BF16",
"elements": 2097152,
"name": "talker.model.layers.10.self_attn.o_proj.weight",
"shape": [
1024,
2048
],
"source": "model.safetensors"
},
{
"bytes": 256,
"dtype": "BF16",
"elements": 128,
"name": "talker.model.layers.10.self_attn.q_norm.weight",
"shape": [
128
],
"source": "model.safetensors"
},
{
"bytes": 4194304,
"dtype": "BF16",
"elements": 2097152,
"name": "talker.model.layers.10.self_attn.q_proj.weight",
"shape": [
2048,
1024
],
"source": "model.safetensors"
},
{
"bytes": 2097152,
"dtype": "BF16",
"elements": 1048576,
"name": "talker.model.layers.10.self_attn.v_proj.weight",
"shape": [
1024,
1024
],
"source": "model.safetensors"
},
{
"bytes": 2048,
"dtype": "BF16",
"elements": 1024,
"name": "talker.model.layers.11.input_layernorm.weight",
"shape": [
1024
],
"source": "model.safetensors"
},
{
"bytes": 6291456,
"dtype": "BF16",
"elements": 3145728,
"name": "talker.model.layers.11.mlp.down_proj.weight",
"shape": [
1024,
3072
],
"source": "model.safetensors"
},
{
"bytes": 6291456,
"dtype": "BF16",
"elements": 3145728,
"name": "talker.model.layers.11.mlp.gate_proj.weight",
"shape": [
3072,
1024
],
"source": "model.safetensors"
},
{
"bytes": 6291456,
"dtype": "BF16",
"elements": 3145728,
"name": "talker.model.layers.11.mlp.up_proj.weight",
"shape": [
3072,
1024
],
"source": "model.safetensors"
},
{
"bytes": 2048,
"dtype": "BF16",
"elements": 1024,
"name": "talker.model.layers.11.post_attention_layernorm.weight",
"shape": [
1024
],
"source": "model.safetensors"
},
{
"bytes": 256,
"dtype": "BF16",
"elements": 128,
"name": "talker.model.layers.11.self_attn.k_norm.weight",
"shape": [
128
],
"source": "model.safetensors"
},
{
"bytes": 2097152,
"dtype": "BF16",
"elements": 1048576,
"name": "talker.model.layers.11.self_attn.k_proj.weight",
"shape": [
1024,
1024
],
"source": "model.safetensors"
},
{
"bytes": 4194304,
"dtype": "BF16",
"elements": 2097152,
"name": "talker.model.layers.11.self_attn.o_proj.weight",
"shape": [
1024,
2048
],
"source": "model.safetensors"
},
{
"bytes": 256,
"dtype": "BF16",
"elements": 128,
"name": "talker.model.layers.11.self_attn.q_norm.weight",
"shape": [
128
],
"source": "model.safetensors"
},
{
"bytes": 4194304,
"dtype": "BF16",
"elements": 2097152,
"name": "talker.model.layers.11.self_attn.q_proj.weight",
"shape": [
2048,
1024
],
"source": "model.safetensors"
},
{
"bytes": 2097152,
"dtype": "BF16",
"elements": 1048576,
"name": "talker.model.layers.11.self_attn.v_proj.weight",
"shape": [
1024,
1024
],
"source": "model.safetensors"
},
{
"bytes": 2048,
"dtype": "BF16",
"elements": 1024,
"name": "talker.model.layers.12.input_layernorm.weight",
"shape": [
1024
],
"source": "model.safetensors"
},
{
"bytes": 6291456,
"dtype": "BF16",
"elements": 3145728,
"name": "talker.model.layers.12.mlp.down_proj.weight",
"shape": [
1024,
3072
],
"source": "model.safetensors"
},
{
"bytes": 6291456,
"dtype": "BF16",
"elements": 3145728,
"name": "talker.model.layers.12.mlp.gate_proj.weight",
"shape": [
3072,
1024
],
"source": "model.safetensors"
},
{
"bytes": 6291456,
"dtype": "BF16",
"elements": 3145728,
"name": "talker.model.layers.12.mlp.up_proj.weight",
"shape": [
3072,
1024
],
"source": "model.safetensors"
},
{
"bytes": 2048,
"dtype": "BF16",
"elements": 1024,
"name": "talker.model.layers.12.post_attention_layernorm.weight",
"shape": [
1024
],
"source": "model.safetensors"
},
{
"bytes": 256,
"dtype": "BF16",
"elements": 128,
"name": "talker.model.layers.12.self_attn.k_norm.weight",
"shape": [
128
],
"source": "model.safetensors"
},
{
"bytes": 2097152,
"dtype": "BF16",
"elements": 1048576,
"name": "talker.model.layers.12.self_attn.k_proj.weight",
"shape": [
1024,
1024
],
"source": "model.safetensors"
},
{
"bytes": 4194304,
"dtype": "BF16",
"elements": 2097152,
"name": "talker.model.layers.12.self_attn.o_proj.weight",
"shape": [
1024,
2048
],
"source": "model.safetensors"
},
{
"bytes": 256,
"dtype": "BF16",
"elements": 128,
"name": "talker.model.layers.12.self_attn.q_norm.weight",
"shape": [
128
],
"source": "model.safetensors"
},
{
"bytes": 4194304,
"dtype": "BF16",
"elements": 2097152,
"name": "talker.model.layers.12.self_attn.q_proj.weight",
"shape": [
2048,
1024
],
"source": "model.safetensors"
},
{
"bytes": 2097152,
"dtype": "BF16",
"elements": 1048576,
"name": "talker.model.layers.12.self_attn.v_proj.weight",
"shape": [
1024,
1024
],
"source": "model.safetensors"
},
{
"bytes": 2048,
"dtype": "BF16",
"elements": 1024,
"name": "talker.model.layers.13.input_layernorm.weight",
"shape": [
1024
],
"source": "model.safetensors"
},
{
"bytes": 6291456,
"dtype": "BF16",
"elements": 3145728,
"name": "talker.model.layers.13.mlp.down_proj.weight",
"shape": [
1024,
3072
],
"source": "model.safetensors"
},
{
"bytes": 6291456,
"dtype": "BF16",
"elements": 3145728,
"name": "talker.model.layers.13.mlp.gate_proj.weight",
"shape": [
3072,
1024
],
"source": "model.safetensors"
},
{
"bytes": 6291456,
"dtype": "BF16",
"elements": 3145728,
"name": "talker.model.layers.13.mlp.up_proj.weight",
"shape": [
3072,
1024
],
"source": "model.safetensors"
},
{
"bytes": 2048,
"dtype": "BF16",
"elements": 1024,
"name": "talker.model.layers.13.post_attention_layernorm.weight",
"shape": [
1024
],
"source": "model.safetensors"
},
{
"bytes": 256,
"dtype": "BF16",
"elements": 128,
"name": "talker.model.layers.13.self_attn.k_norm.weight",
"shape": [
128
],
"source": "model.safetensors"
},
{
"bytes": 2097152,
"dtype": "BF16",
"elements": 1048576,
"name": "talker.model.layers.13.self_attn.k_proj.weight",
"shape": [
1024,
1024
],
"source": "model.safetensors"
},
{
"bytes": 4194304,
"dtype": "BF16",
"elements": 2097152,
"name": "talker.model.layers.13.self_attn.o_proj.weight",
"shape": [
1024,
2048
],
"source": "model.safetensors"
},
{
"bytes": 256,
"dtype": "BF16",
"elements": 128,
"name": "talker.model.layers.13.self_attn.q_norm.weight",
"shape": [
128
],
"source": "model.safetensors"
},
{
"bytes": 4194304,
"dtype": "BF16",
"elements": 2097152,
"name": "talker.model.layers.13.self_attn.q_proj.weight",
"shape": [
2048,
1024
],
"source": "model.safetensors"
},
{
"bytes": 2097152,
"dtype": "BF16",
"elements": 1048576,
"name": "talker.model.layers.13.self_attn.v_proj.weight",
"shape": [
1024,
1024
],
"source": "model.safetensors"
},
{
"bytes": 2048,
"dtype": "BF16",
"elements": 1024,
"name": "talker.model.layers.14.input_layernorm.weight",
"shape": [
1024
],
"source": "model.safetensors"
},
{
"bytes": 6291456,
"dtype": "BF16",
"elements": 3145728,
"name": "talker.model.layers.14.mlp.down_proj.weight",
"shape": [
1024,
3072
],
"source": "model.safetensors"
},
{
"bytes": 6291456,
"dtype": "BF16",
"elements": 3145728,
"name": "talker.model.layers.14.mlp.gate_proj.weight",
"shape": [
3072,
1024
],
"source": "model.safetensors"
},
{
"bytes": 6291456,
"dtype": "BF16",
"elements": 3145728,
"name": "talker.model.layers.14.mlp.up_proj.weight",
"shape": [
3072,
1024
],
"source": "model.safetensors"
},
{
"bytes": 2048,
"dtype": "BF16",
"elements": 1024,
"name": "talker.model.layers.14.post_attention_layernorm.weight",
"shape": [
1024
],
"source": "model.safetensors"
},
{
"bytes": 256,
"dtype": "BF16",
"elements": 128,
"name": "talker.model.layers.14.self_attn.k_norm.weight",
"shape": [
128
],
"source": "model.safetensors"
},
{
"bytes": 2097152,
"dtype": "BF16",
"elements": 1048576,
"name": "talker.model.layers.14.self_attn.k_proj.weight",
"shape": [
1024,
1024
],
"source": "model.safetensors"
},
{
"bytes": 4194304,
"dtype": "BF16",
"elements": 2097152,
"name": "talker.model.layers.14.self_attn.o_proj.weight",
"shape": [
1024,
2048
],
"source": "model.safetensors"
},
{
"bytes": 256,
"dtype": "BF16",
"elements": 128,
"name": "talker.model.layers.14.self_attn.q_norm.weight",
"shape": [
128
],
"source": "model.safetensors"
},
{
"bytes": 4194304,
"dtype": "BF16",
"elements": 2097152,
"name": "talker.model.layers.14.self_attn.q_proj.weight",
"shape": [
2048,
1024
],
"source": "model.safetensors"
},
{
"bytes": 2097152,
"dtype": "BF16",
"elements": 1048576,
"name": "talker.model.layers.14.self_attn.v_proj.weight",
"shape": [
1024,
1024
],
"source": "model.safetensors"
},
{
"bytes": 2048,
"dtype": "BF16",
"elements": 1024,
"name": "talker.model.layers.15.input_layernorm.weight",
"shape": [
1024
],
"source": "model.safetensors"
},
{
"bytes": 6291456,
"dtype": "BF16",
"elements": 3145728,
"name": "talker.model.layers.15.mlp.down_proj.weight",
"shape": [
1024,
3072
],
"source": "model.safetensors"
},
{
"bytes": 6291456,
"dtype": "BF16",
"elements": 3145728,
"name": "talker.model.layers.15.mlp.gate_proj.weight",
"shape": [
3072,
1024
],
"source": "model.safetensors"
},
{
"bytes": 6291456,
"dtype": "BF16",
"elements": 3145728,
"name": "talker.model.layers.15.mlp.up_proj.weight",
"shape": [
3072,
1024
],
"source": "model.safetensors"
},
{
"bytes": 2048,
"dtype": "BF16",
"elements": 1024,
"name": "talker.model.layers.15.post_attention_layernorm.weight",
"shape": [
1024
],
"source": "model.safetensors"
},
{
"bytes": 256,
"dtype": "BF16",
"elements": 128,
"name": "talker.model.layers.15.self_attn.k_norm.weight",
"shape": [
128
],
"source": "model.safetensors"
},
{
"bytes": 2097152,
"dtype": "BF16",
"elements": 1048576,
"name": "talker.model.layers.15.self_attn.k_proj.weight",
"shape": [
1024,
1024
],
"source": "model.safetensors"
},
{
"bytes": 4194304,
"dtype": "BF16",
"elements": 2097152,
"name": "talker.model.layers.15.self_attn.o_proj.weight",
"shape": [
1024,
2048
],
"source": "model.safetensors"
},
{
"bytes": 256,
"dtype": "BF16",
"elements": 128,
"name": "talker.model.layers.15.self_attn.q_norm.weight",
"shape": [
128
],
"source": "model.safetensors"
},
{
"bytes": 4194304,
"dtype": "BF16",
"elements": 2097152,
"name": "talker.model.layers.15.self_attn.q_proj.weight",
"shape": [
2048,
1024
],
"source": "model.safetensors"
},
{
"bytes": 2097152,
"dtype": "BF16",
"elements": 1048576,
"name": "talker.model.layers.15.self_attn.v_proj.weight",
"shape": [
1024,
1024
],
"source": "model.safetensors"
},
{
"bytes": 2048,
"dtype": "BF16",
"elements": 1024,
"name": "talker.model.layers.16.input_layernorm.weight",
"shape": [
1024
],
"source": "model.safetensors"
},
{
"bytes": 6291456,
"dtype": "BF16",
"elements": 3145728,
"name": "talker.model.layers.16.mlp.down_proj.weight",
"shape": [
1024,
3072
],
"source": "model.safetensors"
},
{
"bytes": 6291456,
"dtype": "BF16",
"elements": 3145728,
"name": "talker.model.layers.16.mlp.gate_proj.weight",
"shape": [
3072,
1024
],
"source": "model.safetensors"
},
{
"bytes": 6291456,
"dtype": "BF16",
"elements": 3145728,
"name": "talker.model.layers.16.mlp.up_proj.weight",
"shape": [
3072,
1024
],
"source": "model.safetensors"
},
{
"bytes": 2048,
"dtype": "BF16",
"elements": 1024,
"name": "talker.model.layers.16.post_attention_layernorm.weight",
"shape": [
1024
],
"source": "model.safetensors"
},
{
"bytes": 256,
"dtype": "BF16",
"elements": 128,
"name": "talker.model.layers.16.self_attn.k_norm.weight",
"shape": [
128
],
"source": "model.safetensors"
},
{
"bytes": 2097152,
"dtype": "BF16",
"elements": 1048576,
"name": "talker.model.layers.16.self_attn.k_proj.weight",
"shape": [
1024,
1024
],
"source": "model.safetensors"
},
{
"bytes": 4194304,
"dtype": "BF16",
"elements": 2097152,
"name": "talker.model.layers.16.self_attn.o_proj.weight",
"shape": [
1024,
2048
],
"source": "model.safetensors"
},
{
"bytes": 256,
"dtype": "BF16",
"elements": 128,
"name": "talker.model.layers.16.self_attn.q_norm.weight",
"shape": [
128
],
"source": "model.safetensors"
},
{
"bytes": 4194304,
"dtype": "BF16",
"elements": 2097152,
"name": "talker.model.layers.16.self_attn.q_proj.weight",
"shape": [
2048,
1024
],
"source": "model.safetensors"
},
{
"bytes": 2097152,
"dtype": "BF16",
"elements": 1048576,
"name": "talker.model.layers.16.self_attn.v_proj.weight",
"shape": [
1024,
1024
],
"source": "model.safetensors"
},
{
"bytes": 2048,
"dtype": "BF16",
"elements": 1024,
"name": "talker.model.layers.17.input_layernorm.weight",
"shape": [
1024
],
"source": "model.safetensors"
},
{
"bytes": 6291456,
"dtype": "BF16",
"elements": 3145728,
"name": "talker.model.layers.17.mlp.down_proj.weight",
"shape": [
1024,
3072
],
"source": "model.safetensors"
},
{
"bytes": 6291456,
"dtype": "BF16",
"elements": 3145728,
"name": "talker.model.layers.17.mlp.gate_proj.weight",
"shape": [
3072,
1024
],
"source": "model.safetensors"
},
{
"bytes": 6291456,
"dtype": "BF16",
"elements": 3145728,
"name": "talker.model.layers.17.mlp.up_proj.weight",
"shape": [
3072,
1024
],
"source": "model.safetensors"
},
{
"bytes": 2048,
"dtype": "BF16",
"elements": 1024,
"name": "talker.model.layers.17.post_attention_layernorm.weight",
"shape": [
1024
],
"source": "model.safetensors"
},
{
"bytes": 256,
"dtype": "BF16",
"elements": 128,
"name": "talker.model.layers.17.self_attn.k_norm.weight",
"shape": [
128
],
"source": "model.safetensors"
},
{
"bytes": 2097152,
"dtype": "BF16",
"elements": 1048576,
"name": "talker.model.layers.17.self_attn.k_proj.weight",
"shape": [
1024,
1024
],
"source": "model.safetensors"
},
{
"bytes": 4194304,
"dtype": "BF16",
"elements": 2097152,
"name": "talker.model.layers.17.self_attn.o_proj.weight",
"shape": [
1024,
2048
],
"source": "model.safetensors"
},
{
"bytes": 256,
"dtype": "BF16",
"elements": 128,
"name": "talker.model.layers.17.self_attn.q_norm.weight",
"shape": [
128
],
"source": "model.safetensors"
},
{
"bytes": 4194304,
"dtype": "BF16",
"elements": 2097152,
"name": "talker.model.layers.17.self_attn.q_proj.weight",
"shape": [
2048,
1024
],
"source": "model.safetensors"
},
{
"bytes": 2097152,
"dtype": "BF16",
"elements": 1048576,
"name": "talker.model.layers.17.self_attn.v_proj.weight",
"shape": [
1024,
1024
],
"source": "model.safetensors"
},
{
"bytes": 2048,
"dtype": "BF16",
"elements": 1024,
"name": "talker.model.layers.18.input_layernorm.weight",
"shape": [
1024
],
"source": "model.safetensors"
},
{
"bytes": 6291456,
"dtype": "BF16",
"elements": 3145728,
"name": "talker.model.layers.18.mlp.down_proj.weight",
"shape": [
1024,
3072
],
"source": "model.safetensors"
},
{
"bytes": 6291456,
"dtype": "BF16",
"elements": 3145728,
"name": "talker.model.layers.18.mlp.gate_proj.weight",
"shape": [
3072,
1024
],
"source": "model.safetensors"
},
{
"bytes": 6291456,
"dtype": "BF16",
"elements": 3145728,
"name": "talker.model.layers.18.mlp.up_proj.weight",
"shape": [
3072,
1024
],
"source": "model.safetensors"
},
{
"bytes": 2048,
"dtype": "BF16",
"elements": 1024,
"name": "talker.model.layers.18.post_attention_layernorm.weight",
"shape": [
1024
],
"source": "model.safetensors"
},
{
"bytes": 256,
"dtype": "BF16",
"elements": 128,
"name": "talker.model.layers.18.self_attn.k_norm.weight",
"shape": [
128
],
"source": "model.safetensors"
},
{
"bytes": 2097152,
"dtype": "BF16",
"elements": 1048576,
"name": "talker.model.layers.18.self_attn.k_proj.weight",
"shape": [
1024,
1024
],
"source": "model.safetensors"
},
{
"bytes": 4194304,
"dtype": "BF16",
"elements": 2097152,
"name": "talker.model.layers.18.self_attn.o_proj.weight",
"shape": [
1024,
2048
],
"source": "model.safetensors"
},
{
"bytes": 256,
"dtype": "BF16",
"elements": 128,
"name": "talker.model.layers.18.self_attn.q_norm.weight",
"shape": [
128
],
"source": "model.safetensors"
},
{
"bytes": 4194304,
"dtype": "BF16",
"elements": 2097152,
"name": "talker.model.layers.18.self_attn.q_proj.weight",
"shape": [
2048,
1024
],
"source": "model.safetensors"
},
{
"bytes": 2097152,
"dtype": "BF16",
"elements": 1048576,
"name": "talker.model.layers.18.self_attn.v_proj.weight",
"shape": [
1024,
1024
],
"source": "model.safetensors"
},
{
"bytes": 2048,
"dtype": "BF16",
"elements": 1024,
"name": "talker.model.layers.19.input_layernorm.weight",
"shape": [
1024
],
"source": "model.safetensors"
},
{
"bytes": 6291456,
"dtype": "BF16",
"elements": 3145728,
"name": "talker.model.layers.19.mlp.down_proj.weight",
"shape": [
1024,
3072
],
"source": "model.safetensors"
},
{
"bytes": 6291456,
"dtype": "BF16",
"elements": 3145728,
"name": "talker.model.layers.19.mlp.gate_proj.weight",
"shape": [
3072,
1024
],
"source": "model.safetensors"
},
{
"bytes": 6291456,
"dtype": "BF16",
"elements": 3145728,
"name": "talker.model.layers.19.mlp.up_proj.weight",
"shape": [
3072,
1024
],
"source": "model.safetensors"
},
{
"bytes": 2048,
"dtype": "BF16",
"elements": 1024,
"name": "talker.model.layers.19.post_attention_layernorm.weight",
"shape": [
1024
],
"source": "model.safetensors"
},
{
"bytes": 256,
"dtype": "BF16",
"elements": 128,
"name": "talker.model.layers.19.self_attn.k_norm.weight",
"shape": [
128
],
"source": "model.safetensors"
},
{
"bytes": 2097152,
"dtype": "BF16",
"elements": 1048576,
"name": "talker.model.layers.19.self_attn.k_proj.weight",
"shape": [
1024,
1024
],
"source": "model.safetensors"
},
{
"bytes": 4194304,
"dtype": "BF16",
"elements": 2097152,
"name": "talker.model.layers.19.self_attn.o_proj.weight",
"shape": [
1024,
2048
],
"source": "model.safetensors"
},
{
"bytes": 256,
"dtype": "BF16",
"elements": 128,
"name": "talker.model.layers.19.self_attn.q_norm.weight",
"shape": [
128
],
"source": "model.safetensors"
},
{
"bytes": 4194304,
"dtype": "BF16",
"elements": 2097152,
"name": "talker.model.layers.19.self_attn.q_proj.weight",
"shape": [
2048,
1024
],
"source": "model.safetensors"
},
{
"bytes": 2097152,
"dtype": "BF16",
"elements": 1048576,
"name": "talker.model.layers.19.self_attn.v_proj.weight",
"shape": [
1024,
1024
],
"source": "model.safetensors"
},
{
"bytes": 2048,
"dtype": "BF16",
"elements": 1024,
"name": "talker.model.layers.2.input_layernorm.weight",
"shape": [
1024
],
"source": "model.safetensors"
},
{
"bytes": 6291456,
"dtype": "BF16",
"elements": 3145728,
"name": "talker.model.layers.2.mlp.down_proj.weight",
"shape": [
1024,
3072
],
"source": "model.safetensors"
},
{
"bytes": 6291456,
"dtype": "BF16",
"elements": 3145728,
"name": "talker.model.layers.2.mlp.gate_proj.weight",
"shape": [
3072,
1024
],
"source": "model.safetensors"
},
{
"bytes": 6291456,
"dtype": "BF16",
"elements": 3145728,
"name": "talker.model.layers.2.mlp.up_proj.weight",
"shape": [
3072,
1024
],
"source": "model.safetensors"
},
{
"bytes": 2048,
"dtype": "BF16",
"elements": 1024,
"name": "talker.model.layers.2.post_attention_layernorm.weight",
"shape": [
1024
],
"source": "model.safetensors"
},
{
"bytes": 256,
"dtype": "BF16",
"elements": 128,
"name": "talker.model.layers.2.self_attn.k_norm.weight",
"shape": [
128
],
"source": "model.safetensors"
},
{
"bytes": 2097152,
"dtype": "BF16",
"elements": 1048576,
"name": "talker.model.layers.2.self_attn.k_proj.weight",
"shape": [
1024,
1024
],
"source": "model.safetensors"
},
{
"bytes": 4194304,
"dtype": "BF16",
"elements": 2097152,
"name": "talker.model.layers.2.self_attn.o_proj.weight",
"shape": [
1024,
2048
],
"source": "model.safetensors"
},
{
"bytes": 256,
"dtype": "BF16",
"elements": 128,
"name": "talker.model.layers.2.self_attn.q_norm.weight",
"shape": [
128
],
"source": "model.safetensors"
},
{
"bytes": 4194304,
"dtype": "BF16",
"elements": 2097152,
"name": "talker.model.layers.2.self_attn.q_proj.weight",
"shape": [
2048,
1024
],
"source": "model.safetensors"
},
{
"bytes": 2097152,
"dtype": "BF16",
"elements": 1048576,
"name": "talker.model.layers.2.self_attn.v_proj.weight",
"shape": [
1024,
1024
],
"source": "model.safetensors"
},
{
"bytes": 2048,
"dtype": "BF16",
"elements": 1024,
"name": "talker.model.layers.20.input_layernorm.weight",
"shape": [
1024
],
"source": "model.safetensors"
},
{
"bytes": 6291456,
"dtype": "BF16",
"elements": 3145728,
"name": "talker.model.layers.20.mlp.down_proj.weight",
"shape": [
1024,
3072
],
"source": "model.safetensors"
},
{
"bytes": 6291456,
"dtype": "BF16",
"elements": 3145728,
"name": "talker.model.layers.20.mlp.gate_proj.weight",
"shape": [
3072,
1024
],
"source": "model.safetensors"
},
{
"bytes": 6291456,
"dtype": "BF16",
"elements": 3145728,
"name": "talker.model.layers.20.mlp.up_proj.weight",
"shape": [
3072,
1024
],
"source": "model.safetensors"
},
{
"bytes": 2048,
"dtype": "BF16",
"elements": 1024,
"name": "talker.model.layers.20.post_attention_layernorm.weight",
"shape": [
1024
],
"source": "model.safetensors"
},
{
"bytes": 256,
"dtype": "BF16",
"elements": 128,
"name": "talker.model.layers.20.self_attn.k_norm.weight",
"shape": [
128
],
"source": "model.safetensors"
},
{
"bytes": 2097152,
"dtype": "BF16",
"elements": 1048576,
"name": "talker.model.layers.20.self_attn.k_proj.weight",
"shape": [
1024,
1024
],
"source": "model.safetensors"
},
{
"bytes": 4194304,
"dtype": "BF16",
"elements": 2097152,
"name": "talker.model.layers.20.self_attn.o_proj.weight",
"shape": [
1024,
2048
],
"source": "model.safetensors"
},
{
"bytes": 256,
"dtype": "BF16",
"elements": 128,
"name": "talker.model.layers.20.self_attn.q_norm.weight",
"shape": [
128
],
"source": "model.safetensors"
},
{
"bytes": 4194304,
"dtype": "BF16",
"elements": 2097152,
"name": "talker.model.layers.20.self_attn.q_proj.weight",
"shape": [
2048,
1024
],
"source": "model.safetensors"
},
{
"bytes": 2097152,
"dtype": "BF16",
"elements": 1048576,
"name": "talker.model.layers.20.self_attn.v_proj.weight",
"shape": [
1024,
1024
],
"source": "model.safetensors"
},
{
"bytes": 2048,
"dtype": "BF16",
"elements": 1024,
"name": "talker.model.layers.21.input_layernorm.weight",
"shape": [
1024
],
"source": "model.safetensors"
},
{
"bytes": 6291456,
"dtype": "BF16",
"elements": 3145728,
"name": "talker.model.layers.21.mlp.down_proj.weight",
"shape": [
1024,
3072
],
"source": "model.safetensors"
},
{
"bytes": 6291456,
"dtype": "BF16",
"elements": 3145728,
"name": "talker.model.layers.21.mlp.gate_proj.weight",
"shape": [
3072,
1024
],
"source": "model.safetensors"
},
{
"bytes": 6291456,
"dtype": "BF16",
"elements": 3145728,
"name": "talker.model.layers.21.mlp.up_proj.weight",
"shape": [
3072,
1024
],
"source": "model.safetensors"
},
{
"bytes": 2048,
"dtype": "BF16",
"elements": 1024,
"name": "talker.model.layers.21.post_attention_layernorm.weight",
"shape": [
1024
],
"source": "model.safetensors"
},
{
"bytes": 256,
"dtype": "BF16",
"elements": 128,
"name": "talker.model.layers.21.self_attn.k_norm.weight",
"shape": [
128
],
"source": "model.safetensors"
},
{
"bytes": 2097152,
"dtype": "BF16",
"elements": 1048576,
"name": "talker.model.layers.21.self_attn.k_proj.weight",
"shape": [
1024,
1024
],
"source": "model.safetensors"
},
{
"bytes": 4194304,
"dtype": "BF16",
"elements": 2097152,
"name": "talker.model.layers.21.self_attn.o_proj.weight",
"shape": [
1024,
2048
],
"source": "model.safetensors"
},
{
"bytes": 256,
"dtype": "BF16",
"elements": 128,
"name": "talker.model.layers.21.self_attn.q_norm.weight",
"shape": [
128
],
"source": "model.safetensors"
},
{
"bytes": 4194304,
"dtype": "BF16",
"elements": 2097152,
"name": "talker.model.layers.21.self_attn.q_proj.weight",
"shape": [
2048,
1024
],
"source": "model.safetensors"
},
{
"bytes": 2097152,
"dtype": "BF16",
"elements": 1048576,
"name": "talker.model.layers.21.self_attn.v_proj.weight",
"shape": [
1024,
1024
],
"source": "model.safetensors"
},
{
"bytes": 2048,
"dtype": "BF16",
"elements": 1024,
"name": "talker.model.layers.22.input_layernorm.weight",
"shape": [
1024
],
"source": "model.safetensors"
},
{
"bytes": 6291456,
"dtype": "BF16",
"elements": 3145728,
"name": "talker.model.layers.22.mlp.down_proj.weight",
"shape": [
1024,
3072
],
"source": "model.safetensors"
},
{
"bytes": 6291456,
"dtype": "BF16",
"elements": 3145728,
"name": "talker.model.layers.22.mlp.gate_proj.weight",
"shape": [
3072,
1024
],
"source": "model.safetensors"
},
{
"bytes": 6291456,
"dtype": "BF16",
"elements": 3145728,
"name": "talker.model.layers.22.mlp.up_proj.weight",
"shape": [
3072,
1024
],
"source": "model.safetensors"
},
{
"bytes": 2048,
"dtype": "BF16",
"elements": 1024,
"name": "talker.model.layers.22.post_attention_layernorm.weight",
"shape": [
1024
],
"source": "model.safetensors"
},
{
"bytes": 256,
"dtype": "BF16",
"elements": 128,
"name": "talker.model.layers.22.self_attn.k_norm.weight",
"shape": [
128
],
"source": "model.safetensors"
},
{
"bytes": 2097152,
"dtype": "BF16",
"elements": 1048576,
"name": "talker.model.layers.22.self_attn.k_proj.weight",
"shape": [
1024,
1024
],
"source": "model.safetensors"
},
{
"bytes": 4194304,
"dtype": "BF16",
"elements": 2097152,
"name": "talker.model.layers.22.self_attn.o_proj.weight",
"shape": [
1024,
2048
],
"source": "model.safetensors"
},
{
"bytes": 256,
"dtype": "BF16",
"elements": 128,
"name": "talker.model.layers.22.self_attn.q_norm.weight",
"shape": [
128
],
"source": "model.safetensors"
},
{
"bytes": 4194304,
"dtype": "BF16",
"elements": 2097152,
"name": "talker.model.layers.22.self_attn.q_proj.weight",
"shape": [
2048,
1024
],
"source": "model.safetensors"
},
{
"bytes": 2097152,
"dtype": "BF16",
"elements": 1048576,
"name": "talker.model.layers.22.self_attn.v_proj.weight",
"shape": [
1024,
1024
],
"source": "model.safetensors"
},
{
"bytes": 2048,
"dtype": "BF16",
"elements": 1024,
"name": "talker.model.layers.23.input_layernorm.weight",
"shape": [
1024
],
"source": "model.safetensors"
},
{
"bytes": 6291456,
"dtype": "BF16",
"elements": 3145728,
"name": "talker.model.layers.23.mlp.down_proj.weight",
"shape": [
1024,
3072
],
"source": "model.safetensors"
},
{
"bytes": 6291456,
"dtype": "BF16",
"elements": 3145728,
"name": "talker.model.layers.23.mlp.gate_proj.weight",
"shape": [
3072,
1024
],
"source": "model.safetensors"
},
{
"bytes": 6291456,
"dtype": "BF16",
"elements": 3145728,
"name": "talker.model.layers.23.mlp.up_proj.weight",
"shape": [
3072,
1024
],
"source": "model.safetensors"
},
{
"bytes": 2048,
"dtype": "BF16",
"elements": 1024,
"name": "talker.model.layers.23.post_attention_layernorm.weight",
"shape": [
1024
],
"source": "model.safetensors"
},
{
"bytes": 256,
"dtype": "BF16",
"elements": 128,
"name": "talker.model.layers.23.self_attn.k_norm.weight",
"shape": [
128
],
"source": "model.safetensors"
},
{
"bytes": 2097152,
"dtype": "BF16",
"elements": 1048576,
"name": "talker.model.layers.23.self_attn.k_proj.weight",
"shape": [
1024,
1024
],
"source": "model.safetensors"
},
{
"bytes": 4194304,
"dtype": "BF16",
"elements": 2097152,
"name": "talker.model.layers.23.self_attn.o_proj.weight",
"shape": [
1024,
2048
],
"source": "model.safetensors"
},
{
"bytes": 256,
"dtype": "BF16",
"elements": 128,
"name": "talker.model.layers.23.self_attn.q_norm.weight",
"shape": [
128
],
"source": "model.safetensors"
},
{
"bytes": 4194304,
"dtype": "BF16",
"elements": 2097152,
"name": "talker.model.layers.23.self_attn.q_proj.weight",
"shape": [
2048,
1024
],
"source": "model.safetensors"
},
{
"bytes": 2097152,
"dtype": "BF16",
"elements": 1048576,
"name": "talker.model.layers.23.self_attn.v_proj.weight",
"shape": [
1024,
1024
],
"source": "model.safetensors"
},
{
"bytes": 2048,
"dtype": "BF16",
"elements": 1024,
"name": "talker.model.layers.24.input_layernorm.weight",
"shape": [
1024
],
"source": "model.safetensors"
},
{
"bytes": 6291456,
"dtype": "BF16",
"elements": 3145728,
"name": "talker.model.layers.24.mlp.down_proj.weight",
"shape": [
1024,
3072
],
"source": "model.safetensors"
},
{
"bytes": 6291456,
"dtype": "BF16",
"elements": 3145728,
"name": "talker.model.layers.24.mlp.gate_proj.weight",
"shape": [
3072,
1024
],
"source": "model.safetensors"
},
{
"bytes": 6291456,
"dtype": "BF16",
"elements": 3145728,
"name": "talker.model.layers.24.mlp.up_proj.weight",
"shape": [
3072,
1024
],
"source": "model.safetensors"
},
{
"bytes": 2048,
"dtype": "BF16",
"elements": 1024,
"name": "talker.model.layers.24.post_attention_layernorm.weight",
"shape": [
1024
],
"source": "model.safetensors"
},
{
"bytes": 256,
"dtype": "BF16",
"elements": 128,
"name": "talker.model.layers.24.self_attn.k_norm.weight",
"shape": [
128
],
"source": "model.safetensors"
},
{
"bytes": 2097152,
"dtype": "BF16",
"elements": 1048576,
"name": "talker.model.layers.24.self_attn.k_proj.weight",
"shape": [
1024,
1024
],
"source": "model.safetensors"
},
{
"bytes": 4194304,
"dtype": "BF16",
"elements": 2097152,
"name": "talker.model.layers.24.self_attn.o_proj.weight",
"shape": [
1024,
2048
],
"source": "model.safetensors"
},
{
"bytes": 256,
"dtype": "BF16",
"elements": 128,
"name": "talker.model.layers.24.self_attn.q_norm.weight",
"shape": [
128
],
"source": "model.safetensors"
},
{
"bytes": 4194304,
"dtype": "BF16",
"elements": 2097152,
"name": "talker.model.layers.24.self_attn.q_proj.weight",
"shape": [
2048,
1024
],
"source": "model.safetensors"
},
{
"bytes": 2097152,
"dtype": "BF16",
"elements": 1048576,
"name": "talker.model.layers.24.self_attn.v_proj.weight",
"shape": [
1024,
1024
],
"source": "model.safetensors"
},
{
"bytes": 2048,
"dtype": "BF16",
"elements": 1024,
"name": "talker.model.layers.25.input_layernorm.weight",
"shape": [
1024
],
"source": "model.safetensors"
},
{
"bytes": 6291456,
"dtype": "BF16",
"elements": 3145728,
"name": "talker.model.layers.25.mlp.down_proj.weight",
"shape": [
1024,
3072
],
"source": "model.safetensors"
},
{
"bytes": 6291456,
"dtype": "BF16",
"elements": 3145728,
"name": "talker.model.layers.25.mlp.gate_proj.weight",
"shape": [
3072,
1024
],
"source": "model.safetensors"
},
{
"bytes": 6291456,
"dtype": "BF16",
"elements": 3145728,
"name": "talker.model.layers.25.mlp.up_proj.weight",
"shape": [
3072,
1024
],
"source": "model.safetensors"
},
{
"bytes": 2048,
"dtype": "BF16",
"elements": 1024,
"name": "talker.model.layers.25.post_attention_layernorm.weight",
"shape": [
1024
],
"source": "model.safetensors"
},
{
"bytes": 256,
"dtype": "BF16",
"elements": 128,
"name": "talker.model.layers.25.self_attn.k_norm.weight",
"shape": [
128
],
"source": "model.safetensors"
},
{
"bytes": 2097152,
"dtype": "BF16",
"elements": 1048576,
"name": "talker.model.layers.25.self_attn.k_proj.weight",
"shape": [
1024,
1024
],
"source": "model.safetensors"
},
{
"bytes": 4194304,
"dtype": "BF16",
"elements": 2097152,
"name": "talker.model.layers.25.self_attn.o_proj.weight",
"shape": [
1024,
2048
],
"source": "model.safetensors"
},
{
"bytes": 256,
"dtype": "BF16",
"elements": 128,
"name": "talker.model.layers.25.self_attn.q_norm.weight",
"shape": [
128
],
"source": "model.safetensors"
},
{
"bytes": 4194304,
"dtype": "BF16",
"elements": 2097152,
"name": "talker.model.layers.25.self_attn.q_proj.weight",
"shape": [
2048,
1024
],
"source": "model.safetensors"
},
{
"bytes": 2097152,
"dtype": "BF16",
"elements": 1048576,
"name": "talker.model.layers.25.self_attn.v_proj.weight",
"shape": [
1024,
1024
],
"source": "model.safetensors"
},
{
"bytes": 2048,
"dtype": "BF16",
"elements": 1024,
"name": "talker.model.layers.26.input_layernorm.weight",
"shape": [
1024
],
"source": "model.safetensors"
},
{
"bytes": 6291456,
"dtype": "BF16",
"elements": 3145728,
"name": "talker.model.layers.26.mlp.down_proj.weight",
"shape": [
1024,
3072
],
"source": "model.safetensors"
},
{
"bytes": 6291456,
"dtype": "BF16",
"elements": 3145728,
"name": "talker.model.layers.26.mlp.gate_proj.weight",
"shape": [
3072,
1024
],
"source": "model.safetensors"
},
{
"bytes": 6291456,
"dtype": "BF16",
"elements": 3145728,
"name": "talker.model.layers.26.mlp.up_proj.weight",
"shape": [
3072,
1024
],
"source": "model.safetensors"
},
{
"bytes": 2048,
"dtype": "BF16",
"elements": 1024,
"name": "talker.model.layers.26.post_attention_layernorm.weight",
"shape": [
1024
],
"source": "model.safetensors"
},
{
"bytes": 256,
"dtype": "BF16",
"elements": 128,
"name": "talker.model.layers.26.self_attn.k_norm.weight",
"shape": [
128
],
"source": "model.safetensors"
},
{
"bytes": 2097152,
"dtype": "BF16",
"elements": 1048576,
"name": "talker.model.layers.26.self_attn.k_proj.weight",
"shape": [
1024,
1024
],
"source": "model.safetensors"
},
{
"bytes": 4194304,
"dtype": "BF16",
"elements": 2097152,
"name": "talker.model.layers.26.self_attn.o_proj.weight",
"shape": [
1024,
2048
],
"source": "model.safetensors"
},
{
"bytes": 256,
"dtype": "BF16",
"elements": 128,
"name": "talker.model.layers.26.self_attn.q_norm.weight",
"shape": [
128
],
"source": "model.safetensors"
},
{
"bytes": 4194304,
"dtype": "BF16",
"elements": 2097152,
"name": "talker.model.layers.26.self_attn.q_proj.weight",
"shape": [
2048,
1024
],
"source": "model.safetensors"
},
{
"bytes": 2097152,
"dtype": "BF16",
"elements": 1048576,
"name": "talker.model.layers.26.self_attn.v_proj.weight",
"shape": [
1024,
1024
],
"source": "model.safetensors"
},
{
"bytes": 2048,
"dtype": "BF16",
"elements": 1024,
"name": "talker.model.layers.27.input_layernorm.weight",
"shape": [
1024
],
"source": "model.safetensors"
},
{
"bytes": 6291456,
"dtype": "BF16",
"elements": 3145728,
"name": "talker.model.layers.27.mlp.down_proj.weight",
"shape": [
1024,
3072
],
"source": "model.safetensors"
},
{
"bytes": 6291456,
"dtype": "BF16",
"elements": 3145728,
"name": "talker.model.layers.27.mlp.gate_proj.weight",
"shape": [
3072,
1024
],
"source": "model.safetensors"
},
{
"bytes": 6291456,
"dtype": "BF16",
"elements": 3145728,
"name": "talker.model.layers.27.mlp.up_proj.weight",
"shape": [
3072,
1024
],
"source": "model.safetensors"
},
{
"bytes": 2048,
"dtype": "BF16",
"elements": 1024,
"name": "talker.model.layers.27.post_attention_layernorm.weight",
"shape": [
1024
],
"source": "model.safetensors"
},
{
"bytes": 256,
"dtype": "BF16",
"elements": 128,
"name": "talker.model.layers.27.self_attn.k_norm.weight",
"shape": [
128
],
"source": "model.safetensors"
},
{
"bytes": 2097152,
"dtype": "BF16",
"elements": 1048576,
"name": "talker.model.layers.27.self_attn.k_proj.weight",
"shape": [
1024,
1024
],
"source": "model.safetensors"
},
{
"bytes": 4194304,
"dtype": "BF16",
"elements": 2097152,
"name": "talker.model.layers.27.self_attn.o_proj.weight",
"shape": [
1024,
2048
],
"source": "model.safetensors"
},
{
"bytes": 256,
"dtype": "BF16",
"elements": 128,
"name": "talker.model.layers.27.self_attn.q_norm.weight",
"shape": [
128
],
"source": "model.safetensors"
},
{
"bytes": 4194304,
"dtype": "BF16",
"elements": 2097152,
"name": "talker.model.layers.27.self_attn.q_proj.weight",
"shape": [
2048,
1024
],
"source": "model.safetensors"
},
{
"bytes": 2097152,
"dtype": "BF16",
"elements": 1048576,
"name": "talker.model.layers.27.self_attn.v_proj.weight",
"shape": [
1024,
1024
],
"source": "model.safetensors"
},
{
"bytes": 2048,
"dtype": "BF16",
"elements": 1024,
"name": "talker.model.layers.3.input_layernorm.weight",
"shape": [
1024
],
"source": "model.safetensors"
},
{
"bytes": 6291456,
"dtype": "BF16",
"elements": 3145728,
"name": "talker.model.layers.3.mlp.down_proj.weight",
"shape": [
1024,
3072
],
"source": "model.safetensors"
},
{
"bytes": 6291456,
"dtype": "BF16",
"elements": 3145728,
"name": "talker.model.layers.3.mlp.gate_proj.weight",
"shape": [
3072,
1024
],
"source": "model.safetensors"
},
{
"bytes": 6291456,
"dtype": "BF16",
"elements": 3145728,
"name": "talker.model.layers.3.mlp.up_proj.weight",
"shape": [
3072,
1024
],
"source": "model.safetensors"
},
{
"bytes": 2048,
"dtype": "BF16",
"elements": 1024,
"name": "talker.model.layers.3.post_attention_layernorm.weight",
"shape": [
1024
],
"source": "model.safetensors"
},
{
"bytes": 256,
"dtype": "BF16",
"elements": 128,
"name": "talker.model.layers.3.self_attn.k_norm.weight",
"shape": [
128
],
"source": "model.safetensors"
},
{
"bytes": 2097152,
"dtype": "BF16",
"elements": 1048576,
"name": "talker.model.layers.3.self_attn.k_proj.weight",
"shape": [
1024,
1024
],
"source": "model.safetensors"
},
{
"bytes": 4194304,
"dtype": "BF16",
"elements": 2097152,
"name": "talker.model.layers.3.self_attn.o_proj.weight",
"shape": [
1024,
2048
],
"source": "model.safetensors"
},
{
"bytes": 256,
"dtype": "BF16",
"elements": 128,
"name": "talker.model.layers.3.self_attn.q_norm.weight",
"shape": [
128
],
"source": "model.safetensors"
},
{
"bytes": 4194304,
"dtype": "BF16",
"elements": 2097152,
"name": "talker.model.layers.3.self_attn.q_proj.weight",
"shape": [
2048,
1024
],
"source": "model.safetensors"
},
{
"bytes": 2097152,
"dtype": "BF16",
"elements": 1048576,
"name": "talker.model.layers.3.self_attn.v_proj.weight",
"shape": [
1024,
1024
],
"source": "model.safetensors"
},
{
"bytes": 2048,
"dtype": "BF16",
"elements": 1024,
"name": "talker.model.layers.4.input_layernorm.weight",
"shape": [
1024
],
"source": "model.safetensors"
},
{
"bytes": 6291456,
"dtype": "BF16",
"elements": 3145728,
"name": "talker.model.layers.4.mlp.down_proj.weight",
"shape": [
1024,
3072
],
"source": "model.safetensors"
},
{
"bytes": 6291456,
"dtype": "BF16",
"elements": 3145728,
"name": "talker.model.layers.4.mlp.gate_proj.weight",
"shape": [
3072,
1024
],
"source": "model.safetensors"
},
{
"bytes": 6291456,
"dtype": "BF16",
"elements": 3145728,
"name": "talker.model.layers.4.mlp.up_proj.weight",
"shape": [
3072,
1024
],
"source": "model.safetensors"
},
{
"bytes": 2048,
"dtype": "BF16",
"elements": 1024,
"name": "talker.model.layers.4.post_attention_layernorm.weight",
"shape": [
1024
],
"source": "model.safetensors"
},
{
"bytes": 256,
"dtype": "BF16",
"elements": 128,
"name": "talker.model.layers.4.self_attn.k_norm.weight",
"shape": [
128
],
"source": "model.safetensors"
},
{
"bytes": 2097152,
"dtype": "BF16",
"elements": 1048576,
"name": "talker.model.layers.4.self_attn.k_proj.weight",
"shape": [
1024,
1024
],
"source": "model.safetensors"
},
{
"bytes": 4194304,
"dtype": "BF16",
"elements": 2097152,
"name": "talker.model.layers.4.self_attn.o_proj.weight",
"shape": [
1024,
2048
],
"source": "model.safetensors"
},
{
"bytes": 256,
"dtype": "BF16",
"elements": 128,
"name": "talker.model.layers.4.self_attn.q_norm.weight",
"shape": [
128
],
"source": "model.safetensors"
},
{
"bytes": 4194304,
"dtype": "BF16",
"elements": 2097152,
"name": "talker.model.layers.4.self_attn.q_proj.weight",
"shape": [
2048,
1024
],
"source": "model.safetensors"
},
{
"bytes": 2097152,
"dtype": "BF16",
"elements": 1048576,
"name": "talker.model.layers.4.self_attn.v_proj.weight",
"shape": [
1024,
1024
],
"source": "model.safetensors"
},
{
"bytes": 2048,
"dtype": "BF16",
"elements": 1024,
"name": "talker.model.layers.5.input_layernorm.weight",
"shape": [
1024
],
"source": "model.safetensors"
},
{
"bytes": 6291456,
"dtype": "BF16",
"elements": 3145728,
"name": "talker.model.layers.5.mlp.down_proj.weight",
"shape": [
1024,
3072
],
"source": "model.safetensors"
},
{
"bytes": 6291456,
"dtype": "BF16",
"elements": 3145728,
"name": "talker.model.layers.5.mlp.gate_proj.weight",
"shape": [
3072,
1024
],
"source": "model.safetensors"
},
{
"bytes": 6291456,
"dtype": "BF16",
"elements": 3145728,
"name": "talker.model.layers.5.mlp.up_proj.weight",
"shape": [
3072,
1024
],
"source": "model.safetensors"
},
{
"bytes": 2048,
"dtype": "BF16",
"elements": 1024,
"name": "talker.model.layers.5.post_attention_layernorm.weight",
"shape": [
1024
],
"source": "model.safetensors"
},
{
"bytes": 256,
"dtype": "BF16",
"elements": 128,
"name": "talker.model.layers.5.self_attn.k_norm.weight",
"shape": [
128
],
"source": "model.safetensors"
},
{
"bytes": 2097152,
"dtype": "BF16",
"elements": 1048576,
"name": "talker.model.layers.5.self_attn.k_proj.weight",
"shape": [
1024,
1024
],
"source": "model.safetensors"
},
{
"bytes": 4194304,
"dtype": "BF16",
"elements": 2097152,
"name": "talker.model.layers.5.self_attn.o_proj.weight",
"shape": [
1024,
2048
],
"source": "model.safetensors"
},
{
"bytes": 256,
"dtype": "BF16",
"elements": 128,
"name": "talker.model.layers.5.self_attn.q_norm.weight",
"shape": [
128
],
"source": "model.safetensors"
},
{
"bytes": 4194304,
"dtype": "BF16",
"elements": 2097152,
"name": "talker.model.layers.5.self_attn.q_proj.weight",
"shape": [
2048,
1024
],
"source": "model.safetensors"
},
{
"bytes": 2097152,
"dtype": "BF16",
"elements": 1048576,
"name": "talker.model.layers.5.self_attn.v_proj.weight",
"shape": [
1024,
1024
],
"source": "model.safetensors"
},
{
"bytes": 2048,
"dtype": "BF16",
"elements": 1024,
"name": "talker.model.layers.6.input_layernorm.weight",
"shape": [
1024
],
"source": "model.safetensors"
},
{
"bytes": 6291456,
"dtype": "BF16",
"elements": 3145728,
"name": "talker.model.layers.6.mlp.down_proj.weight",
"shape": [
1024,
3072
],
"source": "model.safetensors"
},
{
"bytes": 6291456,
"dtype": "BF16",
"elements": 3145728,
"name": "talker.model.layers.6.mlp.gate_proj.weight",
"shape": [
3072,
1024
],
"source": "model.safetensors"
},
{
"bytes": 6291456,
"dtype": "BF16",
"elements": 3145728,
"name": "talker.model.layers.6.mlp.up_proj.weight",
"shape": [
3072,
1024
],
"source": "model.safetensors"
},
{
"bytes": 2048,
"dtype": "BF16",
"elements": 1024,
"name": "talker.model.layers.6.post_attention_layernorm.weight",
"shape": [
1024
],
"source": "model.safetensors"
},
{
"bytes": 256,
"dtype": "BF16",
"elements": 128,
"name": "talker.model.layers.6.self_attn.k_norm.weight",
"shape": [
128
],
"source": "model.safetensors"
},
{
"bytes": 2097152,
"dtype": "BF16",
"elements": 1048576,
"name": "talker.model.layers.6.self_attn.k_proj.weight",
"shape": [
1024,
1024
],
"source": "model.safetensors"
},
{
"bytes": 4194304,
"dtype": "BF16",
"elements": 2097152,
"name": "talker.model.layers.6.self_attn.o_proj.weight",
"shape": [
1024,
2048
],
"source": "model.safetensors"
},
{
"bytes": 256,
"dtype": "BF16",
"elements": 128,
"name": "talker.model.layers.6.self_attn.q_norm.weight",
"shape": [
128
],
"source": "model.safetensors"
},
{
"bytes": 4194304,
"dtype": "BF16",
"elements": 2097152,
"name": "talker.model.layers.6.self_attn.q_proj.weight",
"shape": [
2048,
1024
],
"source": "model.safetensors"
},
{
"bytes": 2097152,
"dtype": "BF16",
"elements": 1048576,
"name": "talker.model.layers.6.self_attn.v_proj.weight",
"shape": [
1024,
1024
],
"source": "model.safetensors"
},
{
"bytes": 2048,
"dtype": "BF16",
"elements": 1024,
"name": "talker.model.layers.7.input_layernorm.weight",
"shape": [
1024
],
"source": "model.safetensors"
},
{
"bytes": 6291456,
"dtype": "BF16",
"elements": 3145728,
"name": "talker.model.layers.7.mlp.down_proj.weight",
"shape": [
1024,
3072
],
"source": "model.safetensors"
},
{
"bytes": 6291456,
"dtype": "BF16",
"elements": 3145728,
"name": "talker.model.layers.7.mlp.gate_proj.weight",
"shape": [
3072,
1024
],
"source": "model.safetensors"
},
{
"bytes": 6291456,
"dtype": "BF16",
"elements": 3145728,
"name": "talker.model.layers.7.mlp.up_proj.weight",
"shape": [
3072,
1024
],
"source": "model.safetensors"
},
{
"bytes": 2048,
"dtype": "BF16",
"elements": 1024,
"name": "talker.model.layers.7.post_attention_layernorm.weight",
"shape": [
1024
],
"source": "model.safetensors"
},
{
"bytes": 256,
"dtype": "BF16",
"elements": 128,
"name": "talker.model.layers.7.self_attn.k_norm.weight",
"shape": [
128
],
"source": "model.safetensors"
},
{
"bytes": 2097152,
"dtype": "BF16",
"elements": 1048576,
"name": "talker.model.layers.7.self_attn.k_proj.weight",
"shape": [
1024,
1024
],
"source": "model.safetensors"
},
{
"bytes": 4194304,
"dtype": "BF16",
"elements": 2097152,
"name": "talker.model.layers.7.self_attn.o_proj.weight",
"shape": [
1024,
2048
],
"source": "model.safetensors"
},
{
"bytes": 256,
"dtype": "BF16",
"elements": 128,
"name": "talker.model.layers.7.self_attn.q_norm.weight",
"shape": [
128
],
"source": "model.safetensors"
},
{
"bytes": 4194304,
"dtype": "BF16",
"elements": 2097152,
"name": "talker.model.layers.7.self_attn.q_proj.weight",
"shape": [
2048,
1024
],
"source": "model.safetensors"
},
{
"bytes": 2097152,
"dtype": "BF16",
"elements": 1048576,
"name": "talker.model.layers.7.self_attn.v_proj.weight",
"shape": [
1024,
1024
],
"source": "model.safetensors"
},
{
"bytes": 2048,
"dtype": "BF16",
"elements": 1024,
"name": "talker.model.layers.8.input_layernorm.weight",
"shape": [
1024
],
"source": "model.safetensors"
},
{
"bytes": 6291456,
"dtype": "BF16",
"elements": 3145728,
"name": "talker.model.layers.8.mlp.down_proj.weight",
"shape": [
1024,
3072
],
"source": "model.safetensors"
},
{
"bytes": 6291456,
"dtype": "BF16",
"elements": 3145728,
"name": "talker.model.layers.8.mlp.gate_proj.weight",
"shape": [
3072,
1024
],
"source": "model.safetensors"
},
{
"bytes": 6291456,
"dtype": "BF16",
"elements": 3145728,
"name": "talker.model.layers.8.mlp.up_proj.weight",
"shape": [
3072,
1024
],
"source": "model.safetensors"
},
{
"bytes": 2048,
"dtype": "BF16",
"elements": 1024,
"name": "talker.model.layers.8.post_attention_layernorm.weight",
"shape": [
1024
],
"source": "model.safetensors"
},
{
"bytes": 256,
"dtype": "BF16",
"elements": 128,
"name": "talker.model.layers.8.self_attn.k_norm.weight",
"shape": [
128
],
"source": "model.safetensors"
},
{
"bytes": 2097152,
"dtype": "BF16",
"elements": 1048576,
"name": "talker.model.layers.8.self_attn.k_proj.weight",
"shape": [
1024,
1024
],
"source": "model.safetensors"
},
{
"bytes": 4194304,
"dtype": "BF16",
"elements": 2097152,
"name": "talker.model.layers.8.self_attn.o_proj.weight",
"shape": [
1024,
2048
],
"source": "model.safetensors"
},
{
"bytes": 256,
"dtype": "BF16",
"elements": 128,
"name": "talker.model.layers.8.self_attn.q_norm.weight",
"shape": [
128
],
"source": "model.safetensors"
},
{
"bytes": 4194304,
"dtype": "BF16",
"elements": 2097152,
"name": "talker.model.layers.8.self_attn.q_proj.weight",
"shape": [
2048,
1024
],
"source": "model.safetensors"
},
{
"bytes": 2097152,
"dtype": "BF16",
"elements": 1048576,
"name": "talker.model.layers.8.self_attn.v_proj.weight",
"shape": [
1024,
1024
],
"source": "model.safetensors"
},
{
"bytes": 2048,
"dtype": "BF16",
"elements": 1024,
"name": "talker.model.layers.9.input_layernorm.weight",
"shape": [
1024
],
"source": "model.safetensors"
},
{
"bytes": 6291456,
"dtype": "BF16",
"elements": 3145728,
"name": "talker.model.layers.9.mlp.down_proj.weight",
"shape": [
1024,
3072
],
"source": "model.safetensors"
},
{
"bytes": 6291456,
"dtype": "BF16",
"elements": 3145728,
"name": "talker.model.layers.9.mlp.gate_proj.weight",
"shape": [
3072,
1024
],
"source": "model.safetensors"
},
{
"bytes": 6291456,
"dtype": "BF16",
"elements": 3145728,
"name": "talker.model.layers.9.mlp.up_proj.weight",
"shape": [
3072,
1024
],
"source": "model.safetensors"
},
{
"bytes": 2048,
"dtype": "BF16",
"elements": 1024,
"name": "talker.model.layers.9.post_attention_layernorm.weight",
"shape": [
1024
],
"source": "model.safetensors"
},
{
"bytes": 256,
"dtype": "BF16",
"elements": 128,
"name": "talker.model.layers.9.self_attn.k_norm.weight",
"shape": [
128
],
"source": "model.safetensors"
},
{
"bytes": 2097152,
"dtype": "BF16",
"elements": 1048576,
"name": "talker.model.layers.9.self_attn.k_proj.weight",
"shape": [
1024,
1024
],
"source": "model.safetensors"
},
{
"bytes": 4194304,
"dtype": "BF16",
"elements": 2097152,
"name": "talker.model.layers.9.self_attn.o_proj.weight",
"shape": [
1024,
2048
],
"source": "model.safetensors"
},
{
"bytes": 256,
"dtype": "BF16",
"elements": 128,
"name": "talker.model.layers.9.self_attn.q_norm.weight",
"shape": [
128
],
"source": "model.safetensors"
},
{
"bytes": 4194304,
"dtype": "BF16",
"elements": 2097152,
"name": "talker.model.layers.9.self_attn.q_proj.weight",
"shape": [
2048,
1024
],
"source": "model.safetensors"
},
{
"bytes": 2097152,
"dtype": "BF16",
"elements": 1048576,
"name": "talker.model.layers.9.self_attn.v_proj.weight",
"shape": [
1024,
1024
],
"source": "model.safetensors"
},
{
"bytes": 2048,
"dtype": "BF16",
"elements": 1024,
"name": "talker.model.norm.weight",
"shape": [
1024
],
"source": "model.safetensors"
},
{
"bytes": 622329856,
"dtype": "BF16",
"elements": 311164928,
"name": "talker.model.text_embedding.weight",
"shape": [
151936,
2048
],
"source": "model.safetensors"
},
{
"bytes": 4096,
"dtype": "BF16",
"elements": 2048,
"name": "talker.text_projection.linear_fc1.bias",
"shape": [
2048
],
"source": "model.safetensors"
},
{
"bytes": 8388608,
"dtype": "BF16",
"elements": 4194304,
"name": "talker.text_projection.linear_fc1.weight",
"shape": [
2048,
2048
],
"source": "model.safetensors"
},
{
"bytes": 2048,
"dtype": "BF16",
"elements": 1024,
"name": "talker.text_projection.linear_fc2.bias",
"shape": [
1024
],
"source": "model.safetensors"
},
{
"bytes": 4194304,
"dtype": "BF16",
"elements": 2097152,
"name": "talker.text_projection.linear_fc2.weight",
"shape": [
1024,
2048
],
"source": "model.safetensors"
},
{
"bytes": 6144,
"dtype": "F32",
"elements": 1536,
"name": "decoder.decoder.0.conv.bias",
"shape": [
1536
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 44040192,
"dtype": "F32",
"elements": 11010048,
"name": "decoder.decoder.0.conv.weight",
"shape": [
1536,
1024,
7
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 6144,
"dtype": "F32",
"elements": 1536,
"name": "decoder.decoder.1.block.0.alpha",
"shape": [
1536
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 6144,
"dtype": "F32",
"elements": 1536,
"name": "decoder.decoder.1.block.0.beta",
"shape": [
1536
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 3072,
"dtype": "F32",
"elements": 768,
"name": "decoder.decoder.1.block.1.conv.bias",
"shape": [
768
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 75497472,
"dtype": "F32",
"elements": 18874368,
"name": "decoder.decoder.1.block.1.conv.weight",
"shape": [
1536,
768,
16
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 3072,
"dtype": "F32",
"elements": 768,
"name": "decoder.decoder.1.block.2.act1.alpha",
"shape": [
768
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 3072,
"dtype": "F32",
"elements": 768,
"name": "decoder.decoder.1.block.2.act1.beta",
"shape": [
768
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 3072,
"dtype": "F32",
"elements": 768,
"name": "decoder.decoder.1.block.2.act2.alpha",
"shape": [
768
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 3072,
"dtype": "F32",
"elements": 768,
"name": "decoder.decoder.1.block.2.act2.beta",
"shape": [
768
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 3072,
"dtype": "F32",
"elements": 768,
"name": "decoder.decoder.1.block.2.conv1.conv.bias",
"shape": [
768
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 16515072,
"dtype": "F32",
"elements": 4128768,
"name": "decoder.decoder.1.block.2.conv1.conv.weight",
"shape": [
768,
768,
7
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 3072,
"dtype": "F32",
"elements": 768,
"name": "decoder.decoder.1.block.2.conv2.conv.bias",
"shape": [
768
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2359296,
"dtype": "F32",
"elements": 589824,
"name": "decoder.decoder.1.block.2.conv2.conv.weight",
"shape": [
768,
768,
1
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 3072,
"dtype": "F32",
"elements": 768,
"name": "decoder.decoder.1.block.3.act1.alpha",
"shape": [
768
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 3072,
"dtype": "F32",
"elements": 768,
"name": "decoder.decoder.1.block.3.act1.beta",
"shape": [
768
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 3072,
"dtype": "F32",
"elements": 768,
"name": "decoder.decoder.1.block.3.act2.alpha",
"shape": [
768
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 3072,
"dtype": "F32",
"elements": 768,
"name": "decoder.decoder.1.block.3.act2.beta",
"shape": [
768
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 3072,
"dtype": "F32",
"elements": 768,
"name": "decoder.decoder.1.block.3.conv1.conv.bias",
"shape": [
768
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 16515072,
"dtype": "F32",
"elements": 4128768,
"name": "decoder.decoder.1.block.3.conv1.conv.weight",
"shape": [
768,
768,
7
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 3072,
"dtype": "F32",
"elements": 768,
"name": "decoder.decoder.1.block.3.conv2.conv.bias",
"shape": [
768
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2359296,
"dtype": "F32",
"elements": 589824,
"name": "decoder.decoder.1.block.3.conv2.conv.weight",
"shape": [
768,
768,
1
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 3072,
"dtype": "F32",
"elements": 768,
"name": "decoder.decoder.1.block.4.act1.alpha",
"shape": [
768
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 3072,
"dtype": "F32",
"elements": 768,
"name": "decoder.decoder.1.block.4.act1.beta",
"shape": [
768
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 3072,
"dtype": "F32",
"elements": 768,
"name": "decoder.decoder.1.block.4.act2.alpha",
"shape": [
768
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 3072,
"dtype": "F32",
"elements": 768,
"name": "decoder.decoder.1.block.4.act2.beta",
"shape": [
768
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 3072,
"dtype": "F32",
"elements": 768,
"name": "decoder.decoder.1.block.4.conv1.conv.bias",
"shape": [
768
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 16515072,
"dtype": "F32",
"elements": 4128768,
"name": "decoder.decoder.1.block.4.conv1.conv.weight",
"shape": [
768,
768,
7
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 3072,
"dtype": "F32",
"elements": 768,
"name": "decoder.decoder.1.block.4.conv2.conv.bias",
"shape": [
768
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2359296,
"dtype": "F32",
"elements": 589824,
"name": "decoder.decoder.1.block.4.conv2.conv.weight",
"shape": [
768,
768,
1
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 3072,
"dtype": "F32",
"elements": 768,
"name": "decoder.decoder.2.block.0.alpha",
"shape": [
768
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 3072,
"dtype": "F32",
"elements": 768,
"name": "decoder.decoder.2.block.0.beta",
"shape": [
768
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 1536,
"dtype": "F32",
"elements": 384,
"name": "decoder.decoder.2.block.1.conv.bias",
"shape": [
384
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 11796480,
"dtype": "F32",
"elements": 2949120,
"name": "decoder.decoder.2.block.1.conv.weight",
"shape": [
768,
384,
10
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 1536,
"dtype": "F32",
"elements": 384,
"name": "decoder.decoder.2.block.2.act1.alpha",
"shape": [
384
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 1536,
"dtype": "F32",
"elements": 384,
"name": "decoder.decoder.2.block.2.act1.beta",
"shape": [
384
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 1536,
"dtype": "F32",
"elements": 384,
"name": "decoder.decoder.2.block.2.act2.alpha",
"shape": [
384
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 1536,
"dtype": "F32",
"elements": 384,
"name": "decoder.decoder.2.block.2.act2.beta",
"shape": [
384
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 1536,
"dtype": "F32",
"elements": 384,
"name": "decoder.decoder.2.block.2.conv1.conv.bias",
"shape": [
384
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 4128768,
"dtype": "F32",
"elements": 1032192,
"name": "decoder.decoder.2.block.2.conv1.conv.weight",
"shape": [
384,
384,
7
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 1536,
"dtype": "F32",
"elements": 384,
"name": "decoder.decoder.2.block.2.conv2.conv.bias",
"shape": [
384
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 589824,
"dtype": "F32",
"elements": 147456,
"name": "decoder.decoder.2.block.2.conv2.conv.weight",
"shape": [
384,
384,
1
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 1536,
"dtype": "F32",
"elements": 384,
"name": "decoder.decoder.2.block.3.act1.alpha",
"shape": [
384
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 1536,
"dtype": "F32",
"elements": 384,
"name": "decoder.decoder.2.block.3.act1.beta",
"shape": [
384
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 1536,
"dtype": "F32",
"elements": 384,
"name": "decoder.decoder.2.block.3.act2.alpha",
"shape": [
384
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 1536,
"dtype": "F32",
"elements": 384,
"name": "decoder.decoder.2.block.3.act2.beta",
"shape": [
384
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 1536,
"dtype": "F32",
"elements": 384,
"name": "decoder.decoder.2.block.3.conv1.conv.bias",
"shape": [
384
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 4128768,
"dtype": "F32",
"elements": 1032192,
"name": "decoder.decoder.2.block.3.conv1.conv.weight",
"shape": [
384,
384,
7
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 1536,
"dtype": "F32",
"elements": 384,
"name": "decoder.decoder.2.block.3.conv2.conv.bias",
"shape": [
384
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 589824,
"dtype": "F32",
"elements": 147456,
"name": "decoder.decoder.2.block.3.conv2.conv.weight",
"shape": [
384,
384,
1
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 1536,
"dtype": "F32",
"elements": 384,
"name": "decoder.decoder.2.block.4.act1.alpha",
"shape": [
384
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 1536,
"dtype": "F32",
"elements": 384,
"name": "decoder.decoder.2.block.4.act1.beta",
"shape": [
384
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 1536,
"dtype": "F32",
"elements": 384,
"name": "decoder.decoder.2.block.4.act2.alpha",
"shape": [
384
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 1536,
"dtype": "F32",
"elements": 384,
"name": "decoder.decoder.2.block.4.act2.beta",
"shape": [
384
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 1536,
"dtype": "F32",
"elements": 384,
"name": "decoder.decoder.2.block.4.conv1.conv.bias",
"shape": [
384
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 4128768,
"dtype": "F32",
"elements": 1032192,
"name": "decoder.decoder.2.block.4.conv1.conv.weight",
"shape": [
384,
384,
7
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 1536,
"dtype": "F32",
"elements": 384,
"name": "decoder.decoder.2.block.4.conv2.conv.bias",
"shape": [
384
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 589824,
"dtype": "F32",
"elements": 147456,
"name": "decoder.decoder.2.block.4.conv2.conv.weight",
"shape": [
384,
384,
1
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 1536,
"dtype": "F32",
"elements": 384,
"name": "decoder.decoder.3.block.0.alpha",
"shape": [
384
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 1536,
"dtype": "F32",
"elements": 384,
"name": "decoder.decoder.3.block.0.beta",
"shape": [
384
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 768,
"dtype": "F32",
"elements": 192,
"name": "decoder.decoder.3.block.1.conv.bias",
"shape": [
192
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2359296,
"dtype": "F32",
"elements": 589824,
"name": "decoder.decoder.3.block.1.conv.weight",
"shape": [
384,
192,
8
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 768,
"dtype": "F32",
"elements": 192,
"name": "decoder.decoder.3.block.2.act1.alpha",
"shape": [
192
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 768,
"dtype": "F32",
"elements": 192,
"name": "decoder.decoder.3.block.2.act1.beta",
"shape": [
192
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 768,
"dtype": "F32",
"elements": 192,
"name": "decoder.decoder.3.block.2.act2.alpha",
"shape": [
192
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 768,
"dtype": "F32",
"elements": 192,
"name": "decoder.decoder.3.block.2.act2.beta",
"shape": [
192
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 768,
"dtype": "F32",
"elements": 192,
"name": "decoder.decoder.3.block.2.conv1.conv.bias",
"shape": [
192
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 1032192,
"dtype": "F32",
"elements": 258048,
"name": "decoder.decoder.3.block.2.conv1.conv.weight",
"shape": [
192,
192,
7
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 768,
"dtype": "F32",
"elements": 192,
"name": "decoder.decoder.3.block.2.conv2.conv.bias",
"shape": [
192
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 147456,
"dtype": "F32",
"elements": 36864,
"name": "decoder.decoder.3.block.2.conv2.conv.weight",
"shape": [
192,
192,
1
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 768,
"dtype": "F32",
"elements": 192,
"name": "decoder.decoder.3.block.3.act1.alpha",
"shape": [
192
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 768,
"dtype": "F32",
"elements": 192,
"name": "decoder.decoder.3.block.3.act1.beta",
"shape": [
192
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 768,
"dtype": "F32",
"elements": 192,
"name": "decoder.decoder.3.block.3.act2.alpha",
"shape": [
192
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 768,
"dtype": "F32",
"elements": 192,
"name": "decoder.decoder.3.block.3.act2.beta",
"shape": [
192
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 768,
"dtype": "F32",
"elements": 192,
"name": "decoder.decoder.3.block.3.conv1.conv.bias",
"shape": [
192
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 1032192,
"dtype": "F32",
"elements": 258048,
"name": "decoder.decoder.3.block.3.conv1.conv.weight",
"shape": [
192,
192,
7
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 768,
"dtype": "F32",
"elements": 192,
"name": "decoder.decoder.3.block.3.conv2.conv.bias",
"shape": [
192
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 147456,
"dtype": "F32",
"elements": 36864,
"name": "decoder.decoder.3.block.3.conv2.conv.weight",
"shape": [
192,
192,
1
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 768,
"dtype": "F32",
"elements": 192,
"name": "decoder.decoder.3.block.4.act1.alpha",
"shape": [
192
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 768,
"dtype": "F32",
"elements": 192,
"name": "decoder.decoder.3.block.4.act1.beta",
"shape": [
192
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 768,
"dtype": "F32",
"elements": 192,
"name": "decoder.decoder.3.block.4.act2.alpha",
"shape": [
192
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 768,
"dtype": "F32",
"elements": 192,
"name": "decoder.decoder.3.block.4.act2.beta",
"shape": [
192
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 768,
"dtype": "F32",
"elements": 192,
"name": "decoder.decoder.3.block.4.conv1.conv.bias",
"shape": [
192
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 1032192,
"dtype": "F32",
"elements": 258048,
"name": "decoder.decoder.3.block.4.conv1.conv.weight",
"shape": [
192,
192,
7
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 768,
"dtype": "F32",
"elements": 192,
"name": "decoder.decoder.3.block.4.conv2.conv.bias",
"shape": [
192
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 147456,
"dtype": "F32",
"elements": 36864,
"name": "decoder.decoder.3.block.4.conv2.conv.weight",
"shape": [
192,
192,
1
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 768,
"dtype": "F32",
"elements": 192,
"name": "decoder.decoder.4.block.0.alpha",
"shape": [
192
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 768,
"dtype": "F32",
"elements": 192,
"name": "decoder.decoder.4.block.0.beta",
"shape": [
192
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 384,
"dtype": "F32",
"elements": 96,
"name": "decoder.decoder.4.block.1.conv.bias",
"shape": [
96
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 442368,
"dtype": "F32",
"elements": 110592,
"name": "decoder.decoder.4.block.1.conv.weight",
"shape": [
192,
96,
6
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 384,
"dtype": "F32",
"elements": 96,
"name": "decoder.decoder.4.block.2.act1.alpha",
"shape": [
96
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 384,
"dtype": "F32",
"elements": 96,
"name": "decoder.decoder.4.block.2.act1.beta",
"shape": [
96
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 384,
"dtype": "F32",
"elements": 96,
"name": "decoder.decoder.4.block.2.act2.alpha",
"shape": [
96
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 384,
"dtype": "F32",
"elements": 96,
"name": "decoder.decoder.4.block.2.act2.beta",
"shape": [
96
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 384,
"dtype": "F32",
"elements": 96,
"name": "decoder.decoder.4.block.2.conv1.conv.bias",
"shape": [
96
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 258048,
"dtype": "F32",
"elements": 64512,
"name": "decoder.decoder.4.block.2.conv1.conv.weight",
"shape": [
96,
96,
7
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 384,
"dtype": "F32",
"elements": 96,
"name": "decoder.decoder.4.block.2.conv2.conv.bias",
"shape": [
96
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 36864,
"dtype": "F32",
"elements": 9216,
"name": "decoder.decoder.4.block.2.conv2.conv.weight",
"shape": [
96,
96,
1
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 384,
"dtype": "F32",
"elements": 96,
"name": "decoder.decoder.4.block.3.act1.alpha",
"shape": [
96
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 384,
"dtype": "F32",
"elements": 96,
"name": "decoder.decoder.4.block.3.act1.beta",
"shape": [
96
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 384,
"dtype": "F32",
"elements": 96,
"name": "decoder.decoder.4.block.3.act2.alpha",
"shape": [
96
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 384,
"dtype": "F32",
"elements": 96,
"name": "decoder.decoder.4.block.3.act2.beta",
"shape": [
96
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 384,
"dtype": "F32",
"elements": 96,
"name": "decoder.decoder.4.block.3.conv1.conv.bias",
"shape": [
96
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 258048,
"dtype": "F32",
"elements": 64512,
"name": "decoder.decoder.4.block.3.conv1.conv.weight",
"shape": [
96,
96,
7
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 384,
"dtype": "F32",
"elements": 96,
"name": "decoder.decoder.4.block.3.conv2.conv.bias",
"shape": [
96
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 36864,
"dtype": "F32",
"elements": 9216,
"name": "decoder.decoder.4.block.3.conv2.conv.weight",
"shape": [
96,
96,
1
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 384,
"dtype": "F32",
"elements": 96,
"name": "decoder.decoder.4.block.4.act1.alpha",
"shape": [
96
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 384,
"dtype": "F32",
"elements": 96,
"name": "decoder.decoder.4.block.4.act1.beta",
"shape": [
96
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 384,
"dtype": "F32",
"elements": 96,
"name": "decoder.decoder.4.block.4.act2.alpha",
"shape": [
96
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 384,
"dtype": "F32",
"elements": 96,
"name": "decoder.decoder.4.block.4.act2.beta",
"shape": [
96
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 384,
"dtype": "F32",
"elements": 96,
"name": "decoder.decoder.4.block.4.conv1.conv.bias",
"shape": [
96
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 258048,
"dtype": "F32",
"elements": 64512,
"name": "decoder.decoder.4.block.4.conv1.conv.weight",
"shape": [
96,
96,
7
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 384,
"dtype": "F32",
"elements": 96,
"name": "decoder.decoder.4.block.4.conv2.conv.bias",
"shape": [
96
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 36864,
"dtype": "F32",
"elements": 9216,
"name": "decoder.decoder.4.block.4.conv2.conv.weight",
"shape": [
96,
96,
1
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 384,
"dtype": "F32",
"elements": 96,
"name": "decoder.decoder.5.alpha",
"shape": [
96
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 384,
"dtype": "F32",
"elements": 96,
"name": "decoder.decoder.5.beta",
"shape": [
96
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 4,
"dtype": "F32",
"elements": 1,
"name": "decoder.decoder.6.conv.bias",
"shape": [
1
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2688,
"dtype": "F32",
"elements": 672,
"name": "decoder.decoder.6.conv.weight",
"shape": [
1,
96,
7
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 4096,
"dtype": "F32",
"elements": 1024,
"name": "decoder.pre_conv.conv.bias",
"shape": [
1024
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 6291456,
"dtype": "F32",
"elements": 1572864,
"name": "decoder.pre_conv.conv.weight",
"shape": [
1024,
512,
3
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2048,
"dtype": "F32",
"elements": 512,
"name": "decoder.pre_transformer.input_proj.bias",
"shape": [
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2097152,
"dtype": "F32",
"elements": 524288,
"name": "decoder.pre_transformer.input_proj.weight",
"shape": [
512,
1024
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2048,
"dtype": "F32",
"elements": 512,
"name": "decoder.pre_transformer.layers.0.input_layernorm.weight",
"shape": [
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2097152,
"dtype": "F32",
"elements": 524288,
"name": "decoder.pre_transformer.layers.0.mlp.down_proj.weight",
"shape": [
512,
1024
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2097152,
"dtype": "F32",
"elements": 524288,
"name": "decoder.pre_transformer.layers.0.mlp.gate_proj.weight",
"shape": [
1024,
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2097152,
"dtype": "F32",
"elements": 524288,
"name": "decoder.pre_transformer.layers.0.mlp.up_proj.weight",
"shape": [
1024,
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2048,
"dtype": "F32",
"elements": 512,
"name": "decoder.pre_transformer.layers.0.mlp_layer_scale.scale",
"shape": [
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2048,
"dtype": "F32",
"elements": 512,
"name": "decoder.pre_transformer.layers.0.post_attention_layernorm.weight",
"shape": [
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2097152,
"dtype": "F32",
"elements": 524288,
"name": "decoder.pre_transformer.layers.0.self_attn.k_proj.weight",
"shape": [
1024,
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2097152,
"dtype": "F32",
"elements": 524288,
"name": "decoder.pre_transformer.layers.0.self_attn.o_proj.weight",
"shape": [
512,
1024
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2097152,
"dtype": "F32",
"elements": 524288,
"name": "decoder.pre_transformer.layers.0.self_attn.q_proj.weight",
"shape": [
1024,
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2097152,
"dtype": "F32",
"elements": 524288,
"name": "decoder.pre_transformer.layers.0.self_attn.v_proj.weight",
"shape": [
1024,
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2048,
"dtype": "F32",
"elements": 512,
"name": "decoder.pre_transformer.layers.0.self_attn_layer_scale.scale",
"shape": [
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2048,
"dtype": "F32",
"elements": 512,
"name": "decoder.pre_transformer.layers.1.input_layernorm.weight",
"shape": [
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2097152,
"dtype": "F32",
"elements": 524288,
"name": "decoder.pre_transformer.layers.1.mlp.down_proj.weight",
"shape": [
512,
1024
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2097152,
"dtype": "F32",
"elements": 524288,
"name": "decoder.pre_transformer.layers.1.mlp.gate_proj.weight",
"shape": [
1024,
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2097152,
"dtype": "F32",
"elements": 524288,
"name": "decoder.pre_transformer.layers.1.mlp.up_proj.weight",
"shape": [
1024,
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2048,
"dtype": "F32",
"elements": 512,
"name": "decoder.pre_transformer.layers.1.mlp_layer_scale.scale",
"shape": [
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2048,
"dtype": "F32",
"elements": 512,
"name": "decoder.pre_transformer.layers.1.post_attention_layernorm.weight",
"shape": [
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2097152,
"dtype": "F32",
"elements": 524288,
"name": "decoder.pre_transformer.layers.1.self_attn.k_proj.weight",
"shape": [
1024,
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2097152,
"dtype": "F32",
"elements": 524288,
"name": "decoder.pre_transformer.layers.1.self_attn.o_proj.weight",
"shape": [
512,
1024
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2097152,
"dtype": "F32",
"elements": 524288,
"name": "decoder.pre_transformer.layers.1.self_attn.q_proj.weight",
"shape": [
1024,
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2097152,
"dtype": "F32",
"elements": 524288,
"name": "decoder.pre_transformer.layers.1.self_attn.v_proj.weight",
"shape": [
1024,
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2048,
"dtype": "F32",
"elements": 512,
"name": "decoder.pre_transformer.layers.1.self_attn_layer_scale.scale",
"shape": [
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2048,
"dtype": "F32",
"elements": 512,
"name": "decoder.pre_transformer.layers.2.input_layernorm.weight",
"shape": [
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2097152,
"dtype": "F32",
"elements": 524288,
"name": "decoder.pre_transformer.layers.2.mlp.down_proj.weight",
"shape": [
512,
1024
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2097152,
"dtype": "F32",
"elements": 524288,
"name": "decoder.pre_transformer.layers.2.mlp.gate_proj.weight",
"shape": [
1024,
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2097152,
"dtype": "F32",
"elements": 524288,
"name": "decoder.pre_transformer.layers.2.mlp.up_proj.weight",
"shape": [
1024,
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2048,
"dtype": "F32",
"elements": 512,
"name": "decoder.pre_transformer.layers.2.mlp_layer_scale.scale",
"shape": [
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2048,
"dtype": "F32",
"elements": 512,
"name": "decoder.pre_transformer.layers.2.post_attention_layernorm.weight",
"shape": [
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2097152,
"dtype": "F32",
"elements": 524288,
"name": "decoder.pre_transformer.layers.2.self_attn.k_proj.weight",
"shape": [
1024,
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2097152,
"dtype": "F32",
"elements": 524288,
"name": "decoder.pre_transformer.layers.2.self_attn.o_proj.weight",
"shape": [
512,
1024
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2097152,
"dtype": "F32",
"elements": 524288,
"name": "decoder.pre_transformer.layers.2.self_attn.q_proj.weight",
"shape": [
1024,
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2097152,
"dtype": "F32",
"elements": 524288,
"name": "decoder.pre_transformer.layers.2.self_attn.v_proj.weight",
"shape": [
1024,
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2048,
"dtype": "F32",
"elements": 512,
"name": "decoder.pre_transformer.layers.2.self_attn_layer_scale.scale",
"shape": [
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2048,
"dtype": "F32",
"elements": 512,
"name": "decoder.pre_transformer.layers.3.input_layernorm.weight",
"shape": [
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2097152,
"dtype": "F32",
"elements": 524288,
"name": "decoder.pre_transformer.layers.3.mlp.down_proj.weight",
"shape": [
512,
1024
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2097152,
"dtype": "F32",
"elements": 524288,
"name": "decoder.pre_transformer.layers.3.mlp.gate_proj.weight",
"shape": [
1024,
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2097152,
"dtype": "F32",
"elements": 524288,
"name": "decoder.pre_transformer.layers.3.mlp.up_proj.weight",
"shape": [
1024,
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2048,
"dtype": "F32",
"elements": 512,
"name": "decoder.pre_transformer.layers.3.mlp_layer_scale.scale",
"shape": [
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2048,
"dtype": "F32",
"elements": 512,
"name": "decoder.pre_transformer.layers.3.post_attention_layernorm.weight",
"shape": [
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2097152,
"dtype": "F32",
"elements": 524288,
"name": "decoder.pre_transformer.layers.3.self_attn.k_proj.weight",
"shape": [
1024,
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2097152,
"dtype": "F32",
"elements": 524288,
"name": "decoder.pre_transformer.layers.3.self_attn.o_proj.weight",
"shape": [
512,
1024
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2097152,
"dtype": "F32",
"elements": 524288,
"name": "decoder.pre_transformer.layers.3.self_attn.q_proj.weight",
"shape": [
1024,
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2097152,
"dtype": "F32",
"elements": 524288,
"name": "decoder.pre_transformer.layers.3.self_attn.v_proj.weight",
"shape": [
1024,
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2048,
"dtype": "F32",
"elements": 512,
"name": "decoder.pre_transformer.layers.3.self_attn_layer_scale.scale",
"shape": [
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2048,
"dtype": "F32",
"elements": 512,
"name": "decoder.pre_transformer.layers.4.input_layernorm.weight",
"shape": [
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2097152,
"dtype": "F32",
"elements": 524288,
"name": "decoder.pre_transformer.layers.4.mlp.down_proj.weight",
"shape": [
512,
1024
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2097152,
"dtype": "F32",
"elements": 524288,
"name": "decoder.pre_transformer.layers.4.mlp.gate_proj.weight",
"shape": [
1024,
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2097152,
"dtype": "F32",
"elements": 524288,
"name": "decoder.pre_transformer.layers.4.mlp.up_proj.weight",
"shape": [
1024,
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2048,
"dtype": "F32",
"elements": 512,
"name": "decoder.pre_transformer.layers.4.mlp_layer_scale.scale",
"shape": [
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2048,
"dtype": "F32",
"elements": 512,
"name": "decoder.pre_transformer.layers.4.post_attention_layernorm.weight",
"shape": [
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2097152,
"dtype": "F32",
"elements": 524288,
"name": "decoder.pre_transformer.layers.4.self_attn.k_proj.weight",
"shape": [
1024,
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2097152,
"dtype": "F32",
"elements": 524288,
"name": "decoder.pre_transformer.layers.4.self_attn.o_proj.weight",
"shape": [
512,
1024
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2097152,
"dtype": "F32",
"elements": 524288,
"name": "decoder.pre_transformer.layers.4.self_attn.q_proj.weight",
"shape": [
1024,
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2097152,
"dtype": "F32",
"elements": 524288,
"name": "decoder.pre_transformer.layers.4.self_attn.v_proj.weight",
"shape": [
1024,
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2048,
"dtype": "F32",
"elements": 512,
"name": "decoder.pre_transformer.layers.4.self_attn_layer_scale.scale",
"shape": [
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2048,
"dtype": "F32",
"elements": 512,
"name": "decoder.pre_transformer.layers.5.input_layernorm.weight",
"shape": [
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2097152,
"dtype": "F32",
"elements": 524288,
"name": "decoder.pre_transformer.layers.5.mlp.down_proj.weight",
"shape": [
512,
1024
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2097152,
"dtype": "F32",
"elements": 524288,
"name": "decoder.pre_transformer.layers.5.mlp.gate_proj.weight",
"shape": [
1024,
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2097152,
"dtype": "F32",
"elements": 524288,
"name": "decoder.pre_transformer.layers.5.mlp.up_proj.weight",
"shape": [
1024,
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2048,
"dtype": "F32",
"elements": 512,
"name": "decoder.pre_transformer.layers.5.mlp_layer_scale.scale",
"shape": [
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2048,
"dtype": "F32",
"elements": 512,
"name": "decoder.pre_transformer.layers.5.post_attention_layernorm.weight",
"shape": [
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2097152,
"dtype": "F32",
"elements": 524288,
"name": "decoder.pre_transformer.layers.5.self_attn.k_proj.weight",
"shape": [
1024,
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2097152,
"dtype": "F32",
"elements": 524288,
"name": "decoder.pre_transformer.layers.5.self_attn.o_proj.weight",
"shape": [
512,
1024
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2097152,
"dtype": "F32",
"elements": 524288,
"name": "decoder.pre_transformer.layers.5.self_attn.q_proj.weight",
"shape": [
1024,
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2097152,
"dtype": "F32",
"elements": 524288,
"name": "decoder.pre_transformer.layers.5.self_attn.v_proj.weight",
"shape": [
1024,
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2048,
"dtype": "F32",
"elements": 512,
"name": "decoder.pre_transformer.layers.5.self_attn_layer_scale.scale",
"shape": [
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2048,
"dtype": "F32",
"elements": 512,
"name": "decoder.pre_transformer.layers.6.input_layernorm.weight",
"shape": [
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2097152,
"dtype": "F32",
"elements": 524288,
"name": "decoder.pre_transformer.layers.6.mlp.down_proj.weight",
"shape": [
512,
1024
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2097152,
"dtype": "F32",
"elements": 524288,
"name": "decoder.pre_transformer.layers.6.mlp.gate_proj.weight",
"shape": [
1024,
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2097152,
"dtype": "F32",
"elements": 524288,
"name": "decoder.pre_transformer.layers.6.mlp.up_proj.weight",
"shape": [
1024,
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2048,
"dtype": "F32",
"elements": 512,
"name": "decoder.pre_transformer.layers.6.mlp_layer_scale.scale",
"shape": [
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2048,
"dtype": "F32",
"elements": 512,
"name": "decoder.pre_transformer.layers.6.post_attention_layernorm.weight",
"shape": [
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2097152,
"dtype": "F32",
"elements": 524288,
"name": "decoder.pre_transformer.layers.6.self_attn.k_proj.weight",
"shape": [
1024,
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2097152,
"dtype": "F32",
"elements": 524288,
"name": "decoder.pre_transformer.layers.6.self_attn.o_proj.weight",
"shape": [
512,
1024
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2097152,
"dtype": "F32",
"elements": 524288,
"name": "decoder.pre_transformer.layers.6.self_attn.q_proj.weight",
"shape": [
1024,
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2097152,
"dtype": "F32",
"elements": 524288,
"name": "decoder.pre_transformer.layers.6.self_attn.v_proj.weight",
"shape": [
1024,
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2048,
"dtype": "F32",
"elements": 512,
"name": "decoder.pre_transformer.layers.6.self_attn_layer_scale.scale",
"shape": [
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2048,
"dtype": "F32",
"elements": 512,
"name": "decoder.pre_transformer.layers.7.input_layernorm.weight",
"shape": [
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2097152,
"dtype": "F32",
"elements": 524288,
"name": "decoder.pre_transformer.layers.7.mlp.down_proj.weight",
"shape": [
512,
1024
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2097152,
"dtype": "F32",
"elements": 524288,
"name": "decoder.pre_transformer.layers.7.mlp.gate_proj.weight",
"shape": [
1024,
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2097152,
"dtype": "F32",
"elements": 524288,
"name": "decoder.pre_transformer.layers.7.mlp.up_proj.weight",
"shape": [
1024,
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2048,
"dtype": "F32",
"elements": 512,
"name": "decoder.pre_transformer.layers.7.mlp_layer_scale.scale",
"shape": [
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2048,
"dtype": "F32",
"elements": 512,
"name": "decoder.pre_transformer.layers.7.post_attention_layernorm.weight",
"shape": [
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2097152,
"dtype": "F32",
"elements": 524288,
"name": "decoder.pre_transformer.layers.7.self_attn.k_proj.weight",
"shape": [
1024,
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2097152,
"dtype": "F32",
"elements": 524288,
"name": "decoder.pre_transformer.layers.7.self_attn.o_proj.weight",
"shape": [
512,
1024
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2097152,
"dtype": "F32",
"elements": 524288,
"name": "decoder.pre_transformer.layers.7.self_attn.q_proj.weight",
"shape": [
1024,
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2097152,
"dtype": "F32",
"elements": 524288,
"name": "decoder.pre_transformer.layers.7.self_attn.v_proj.weight",
"shape": [
1024,
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2048,
"dtype": "F32",
"elements": 512,
"name": "decoder.pre_transformer.layers.7.self_attn_layer_scale.scale",
"shape": [
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2048,
"dtype": "F32",
"elements": 512,
"name": "decoder.pre_transformer.norm.weight",
"shape": [
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 4096,
"dtype": "F32",
"elements": 1024,
"name": "decoder.pre_transformer.output_proj.bias",
"shape": [
1024
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2097152,
"dtype": "F32",
"elements": 524288,
"name": "decoder.pre_transformer.output_proj.weight",
"shape": [
1024,
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 524288,
"dtype": "F32",
"elements": 131072,
"name": "decoder.quantizer.rvq_first.input_proj.weight",
"shape": [
256,
512,
1
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 524288,
"dtype": "F32",
"elements": 131072,
"name": "decoder.quantizer.rvq_first.output_proj.weight",
"shape": [
512,
256,
1
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 8192,
"dtype": "F32",
"elements": 2048,
"name": "decoder.quantizer.rvq_first.vq.layers.0._codebook.cluster_usage",
"shape": [
2048
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2097152,
"dtype": "F32",
"elements": 524288,
"name": "decoder.quantizer.rvq_first.vq.layers.0._codebook.embedding_sum",
"shape": [
2048,
256
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 524288,
"dtype": "F32",
"elements": 131072,
"name": "decoder.quantizer.rvq_rest.input_proj.weight",
"shape": [
256,
512,
1
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 524288,
"dtype": "F32",
"elements": 131072,
"name": "decoder.quantizer.rvq_rest.output_proj.weight",
"shape": [
512,
256,
1
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 8192,
"dtype": "F32",
"elements": 2048,
"name": "decoder.quantizer.rvq_rest.vq.layers.0._codebook.cluster_usage",
"shape": [
2048
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2097152,
"dtype": "F32",
"elements": 524288,
"name": "decoder.quantizer.rvq_rest.vq.layers.0._codebook.embedding_sum",
"shape": [
2048,
256
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 8192,
"dtype": "F32",
"elements": 2048,
"name": "decoder.quantizer.rvq_rest.vq.layers.1._codebook.cluster_usage",
"shape": [
2048
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2097152,
"dtype": "F32",
"elements": 524288,
"name": "decoder.quantizer.rvq_rest.vq.layers.1._codebook.embedding_sum",
"shape": [
2048,
256
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 8192,
"dtype": "F32",
"elements": 2048,
"name": "decoder.quantizer.rvq_rest.vq.layers.10._codebook.cluster_usage",
"shape": [
2048
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2097152,
"dtype": "F32",
"elements": 524288,
"name": "decoder.quantizer.rvq_rest.vq.layers.10._codebook.embedding_sum",
"shape": [
2048,
256
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 8192,
"dtype": "F32",
"elements": 2048,
"name": "decoder.quantizer.rvq_rest.vq.layers.11._codebook.cluster_usage",
"shape": [
2048
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2097152,
"dtype": "F32",
"elements": 524288,
"name": "decoder.quantizer.rvq_rest.vq.layers.11._codebook.embedding_sum",
"shape": [
2048,
256
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 8192,
"dtype": "F32",
"elements": 2048,
"name": "decoder.quantizer.rvq_rest.vq.layers.12._codebook.cluster_usage",
"shape": [
2048
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2097152,
"dtype": "F32",
"elements": 524288,
"name": "decoder.quantizer.rvq_rest.vq.layers.12._codebook.embedding_sum",
"shape": [
2048,
256
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 8192,
"dtype": "F32",
"elements": 2048,
"name": "decoder.quantizer.rvq_rest.vq.layers.13._codebook.cluster_usage",
"shape": [
2048
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2097152,
"dtype": "F32",
"elements": 524288,
"name": "decoder.quantizer.rvq_rest.vq.layers.13._codebook.embedding_sum",
"shape": [
2048,
256
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 8192,
"dtype": "F32",
"elements": 2048,
"name": "decoder.quantizer.rvq_rest.vq.layers.14._codebook.cluster_usage",
"shape": [
2048
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2097152,
"dtype": "F32",
"elements": 524288,
"name": "decoder.quantizer.rvq_rest.vq.layers.14._codebook.embedding_sum",
"shape": [
2048,
256
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 8192,
"dtype": "F32",
"elements": 2048,
"name": "decoder.quantizer.rvq_rest.vq.layers.2._codebook.cluster_usage",
"shape": [
2048
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2097152,
"dtype": "F32",
"elements": 524288,
"name": "decoder.quantizer.rvq_rest.vq.layers.2._codebook.embedding_sum",
"shape": [
2048,
256
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 8192,
"dtype": "F32",
"elements": 2048,
"name": "decoder.quantizer.rvq_rest.vq.layers.3._codebook.cluster_usage",
"shape": [
2048
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2097152,
"dtype": "F32",
"elements": 524288,
"name": "decoder.quantizer.rvq_rest.vq.layers.3._codebook.embedding_sum",
"shape": [
2048,
256
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 8192,
"dtype": "F32",
"elements": 2048,
"name": "decoder.quantizer.rvq_rest.vq.layers.4._codebook.cluster_usage",
"shape": [
2048
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2097152,
"dtype": "F32",
"elements": 524288,
"name": "decoder.quantizer.rvq_rest.vq.layers.4._codebook.embedding_sum",
"shape": [
2048,
256
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 8192,
"dtype": "F32",
"elements": 2048,
"name": "decoder.quantizer.rvq_rest.vq.layers.5._codebook.cluster_usage",
"shape": [
2048
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2097152,
"dtype": "F32",
"elements": 524288,
"name": "decoder.quantizer.rvq_rest.vq.layers.5._codebook.embedding_sum",
"shape": [
2048,
256
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 8192,
"dtype": "F32",
"elements": 2048,
"name": "decoder.quantizer.rvq_rest.vq.layers.6._codebook.cluster_usage",
"shape": [
2048
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2097152,
"dtype": "F32",
"elements": 524288,
"name": "decoder.quantizer.rvq_rest.vq.layers.6._codebook.embedding_sum",
"shape": [
2048,
256
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 8192,
"dtype": "F32",
"elements": 2048,
"name": "decoder.quantizer.rvq_rest.vq.layers.7._codebook.cluster_usage",
"shape": [
2048
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2097152,
"dtype": "F32",
"elements": 524288,
"name": "decoder.quantizer.rvq_rest.vq.layers.7._codebook.embedding_sum",
"shape": [
2048,
256
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 8192,
"dtype": "F32",
"elements": 2048,
"name": "decoder.quantizer.rvq_rest.vq.layers.8._codebook.cluster_usage",
"shape": [
2048
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2097152,
"dtype": "F32",
"elements": 524288,
"name": "decoder.quantizer.rvq_rest.vq.layers.8._codebook.embedding_sum",
"shape": [
2048,
256
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 8192,
"dtype": "F32",
"elements": 2048,
"name": "decoder.quantizer.rvq_rest.vq.layers.9._codebook.cluster_usage",
"shape": [
2048
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2097152,
"dtype": "F32",
"elements": 524288,
"name": "decoder.quantizer.rvq_rest.vq.layers.9._codebook.embedding_sum",
"shape": [
2048,
256
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 4096,
"dtype": "F32",
"elements": 1024,
"name": "decoder.upsample.0.0.conv.bias",
"shape": [
1024
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 8388608,
"dtype": "F32",
"elements": 2097152,
"name": "decoder.upsample.0.0.conv.weight",
"shape": [
1024,
1024,
2
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 4096,
"dtype": "F32",
"elements": 1024,
"name": "decoder.upsample.0.1.dwconv.conv.bias",
"shape": [
1024
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 28672,
"dtype": "F32",
"elements": 7168,
"name": "decoder.upsample.0.1.dwconv.conv.weight",
"shape": [
1024,
1,
7
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 4096,
"dtype": "F32",
"elements": 1024,
"name": "decoder.upsample.0.1.gamma",
"shape": [
1024
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 4096,
"dtype": "F32",
"elements": 1024,
"name": "decoder.upsample.0.1.norm.bias",
"shape": [
1024
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 4096,
"dtype": "F32",
"elements": 1024,
"name": "decoder.upsample.0.1.norm.weight",
"shape": [
1024
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 16384,
"dtype": "F32",
"elements": 4096,
"name": "decoder.upsample.0.1.pwconv1.bias",
"shape": [
4096
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 16777216,
"dtype": "F32",
"elements": 4194304,
"name": "decoder.upsample.0.1.pwconv1.weight",
"shape": [
4096,
1024
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 4096,
"dtype": "F32",
"elements": 1024,
"name": "decoder.upsample.0.1.pwconv2.bias",
"shape": [
1024
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 16777216,
"dtype": "F32",
"elements": 4194304,
"name": "decoder.upsample.0.1.pwconv2.weight",
"shape": [
1024,
4096
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 4096,
"dtype": "F32",
"elements": 1024,
"name": "decoder.upsample.1.0.conv.bias",
"shape": [
1024
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 8388608,
"dtype": "F32",
"elements": 2097152,
"name": "decoder.upsample.1.0.conv.weight",
"shape": [
1024,
1024,
2
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 4096,
"dtype": "F32",
"elements": 1024,
"name": "decoder.upsample.1.1.dwconv.conv.bias",
"shape": [
1024
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 28672,
"dtype": "F32",
"elements": 7168,
"name": "decoder.upsample.1.1.dwconv.conv.weight",
"shape": [
1024,
1,
7
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 4096,
"dtype": "F32",
"elements": 1024,
"name": "decoder.upsample.1.1.gamma",
"shape": [
1024
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 4096,
"dtype": "F32",
"elements": 1024,
"name": "decoder.upsample.1.1.norm.bias",
"shape": [
1024
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 4096,
"dtype": "F32",
"elements": 1024,
"name": "decoder.upsample.1.1.norm.weight",
"shape": [
1024
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 16384,
"dtype": "F32",
"elements": 4096,
"name": "decoder.upsample.1.1.pwconv1.bias",
"shape": [
4096
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 16777216,
"dtype": "F32",
"elements": 4194304,
"name": "decoder.upsample.1.1.pwconv1.weight",
"shape": [
4096,
1024
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 4096,
"dtype": "F32",
"elements": 1024,
"name": "decoder.upsample.1.1.pwconv2.bias",
"shape": [
1024
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 16777216,
"dtype": "F32",
"elements": 4194304,
"name": "decoder.upsample.1.1.pwconv2.weight",
"shape": [
1024,
4096
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 4194304,
"dtype": "F32",
"elements": 1048576,
"name": "encoder.downsample.conv.weight",
"shape": [
512,
512,
4
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 256,
"dtype": "F32",
"elements": 64,
"name": "encoder.encoder.layers.0.conv.bias",
"shape": [
64
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 1792,
"dtype": "F32",
"elements": 448,
"name": "encoder.encoder.layers.0.conv.weight",
"shape": [
64,
1,
7
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 128,
"dtype": "F32",
"elements": 32,
"name": "encoder.encoder.layers.1.block.1.conv.bias",
"shape": [
32
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 24576,
"dtype": "F32",
"elements": 6144,
"name": "encoder.encoder.layers.1.block.1.conv.weight",
"shape": [
32,
64,
3
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 256,
"dtype": "F32",
"elements": 64,
"name": "encoder.encoder.layers.1.block.3.conv.bias",
"shape": [
64
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 8192,
"dtype": "F32",
"elements": 2048,
"name": "encoder.encoder.layers.1.block.3.conv.weight",
"shape": [
64,
32,
1
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 1024,
"dtype": "F32",
"elements": 256,
"name": "encoder.encoder.layers.10.block.1.conv.bias",
"shape": [
256
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 1572864,
"dtype": "F32",
"elements": 393216,
"name": "encoder.encoder.layers.10.block.1.conv.weight",
"shape": [
256,
512,
3
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2048,
"dtype": "F32",
"elements": 512,
"name": "encoder.encoder.layers.10.block.3.conv.bias",
"shape": [
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 524288,
"dtype": "F32",
"elements": 131072,
"name": "encoder.encoder.layers.10.block.3.conv.weight",
"shape": [
512,
256,
1
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 4096,
"dtype": "F32",
"elements": 1024,
"name": "encoder.encoder.layers.12.conv.bias",
"shape": [
1024
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 33554432,
"dtype": "F32",
"elements": 8388608,
"name": "encoder.encoder.layers.12.conv.weight",
"shape": [
1024,
512,
16
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2048,
"dtype": "F32",
"elements": 512,
"name": "encoder.encoder.layers.14.conv.bias",
"shape": [
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 6291456,
"dtype": "F32",
"elements": 1572864,
"name": "encoder.encoder.layers.14.conv.weight",
"shape": [
512,
1024,
3
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 512,
"dtype": "F32",
"elements": 128,
"name": "encoder.encoder.layers.3.conv.bias",
"shape": [
128
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 262144,
"dtype": "F32",
"elements": 65536,
"name": "encoder.encoder.layers.3.conv.weight",
"shape": [
128,
64,
8
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 256,
"dtype": "F32",
"elements": 64,
"name": "encoder.encoder.layers.4.block.1.conv.bias",
"shape": [
64
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 98304,
"dtype": "F32",
"elements": 24576,
"name": "encoder.encoder.layers.4.block.1.conv.weight",
"shape": [
64,
128,
3
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 512,
"dtype": "F32",
"elements": 128,
"name": "encoder.encoder.layers.4.block.3.conv.bias",
"shape": [
128
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 32768,
"dtype": "F32",
"elements": 8192,
"name": "encoder.encoder.layers.4.block.3.conv.weight",
"shape": [
128,
64,
1
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 1024,
"dtype": "F32",
"elements": 256,
"name": "encoder.encoder.layers.6.conv.bias",
"shape": [
256
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 1310720,
"dtype": "F32",
"elements": 327680,
"name": "encoder.encoder.layers.6.conv.weight",
"shape": [
256,
128,
10
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 512,
"dtype": "F32",
"elements": 128,
"name": "encoder.encoder.layers.7.block.1.conv.bias",
"shape": [
128
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 393216,
"dtype": "F32",
"elements": 98304,
"name": "encoder.encoder.layers.7.block.1.conv.weight",
"shape": [
128,
256,
3
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 1024,
"dtype": "F32",
"elements": 256,
"name": "encoder.encoder.layers.7.block.3.conv.bias",
"shape": [
256
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 131072,
"dtype": "F32",
"elements": 32768,
"name": "encoder.encoder.layers.7.block.3.conv.weight",
"shape": [
256,
128,
1
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2048,
"dtype": "F32",
"elements": 512,
"name": "encoder.encoder.layers.9.conv.bias",
"shape": [
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 6291456,
"dtype": "F32",
"elements": 1572864,
"name": "encoder.encoder.layers.9.conv.weight",
"shape": [
512,
256,
12
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2048,
"dtype": "F32",
"elements": 512,
"name": "encoder.encoder_transformer.layers.0.input_layernorm.bias",
"shape": [
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2048,
"dtype": "F32",
"elements": 512,
"name": "encoder.encoder_transformer.layers.0.input_layernorm.weight",
"shape": [
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 4194304,
"dtype": "F32",
"elements": 1048576,
"name": "encoder.encoder_transformer.layers.0.mlp.fc1.weight",
"shape": [
2048,
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 4194304,
"dtype": "F32",
"elements": 1048576,
"name": "encoder.encoder_transformer.layers.0.mlp.fc2.weight",
"shape": [
512,
2048
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2048,
"dtype": "F32",
"elements": 512,
"name": "encoder.encoder_transformer.layers.0.mlp_layer_scale.scale",
"shape": [
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2048,
"dtype": "F32",
"elements": 512,
"name": "encoder.encoder_transformer.layers.0.post_attention_layernorm.bias",
"shape": [
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2048,
"dtype": "F32",
"elements": 512,
"name": "encoder.encoder_transformer.layers.0.post_attention_layernorm.weight",
"shape": [
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 1048576,
"dtype": "F32",
"elements": 262144,
"name": "encoder.encoder_transformer.layers.0.self_attn.k_proj.weight",
"shape": [
512,
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 1048576,
"dtype": "F32",
"elements": 262144,
"name": "encoder.encoder_transformer.layers.0.self_attn.o_proj.weight",
"shape": [
512,
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 1048576,
"dtype": "F32",
"elements": 262144,
"name": "encoder.encoder_transformer.layers.0.self_attn.q_proj.weight",
"shape": [
512,
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 1048576,
"dtype": "F32",
"elements": 262144,
"name": "encoder.encoder_transformer.layers.0.self_attn.v_proj.weight",
"shape": [
512,
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2048,
"dtype": "F32",
"elements": 512,
"name": "encoder.encoder_transformer.layers.0.self_attn_layer_scale.scale",
"shape": [
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2048,
"dtype": "F32",
"elements": 512,
"name": "encoder.encoder_transformer.layers.1.input_layernorm.bias",
"shape": [
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2048,
"dtype": "F32",
"elements": 512,
"name": "encoder.encoder_transformer.layers.1.input_layernorm.weight",
"shape": [
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 4194304,
"dtype": "F32",
"elements": 1048576,
"name": "encoder.encoder_transformer.layers.1.mlp.fc1.weight",
"shape": [
2048,
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 4194304,
"dtype": "F32",
"elements": 1048576,
"name": "encoder.encoder_transformer.layers.1.mlp.fc2.weight",
"shape": [
512,
2048
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2048,
"dtype": "F32",
"elements": 512,
"name": "encoder.encoder_transformer.layers.1.mlp_layer_scale.scale",
"shape": [
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2048,
"dtype": "F32",
"elements": 512,
"name": "encoder.encoder_transformer.layers.1.post_attention_layernorm.bias",
"shape": [
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2048,
"dtype": "F32",
"elements": 512,
"name": "encoder.encoder_transformer.layers.1.post_attention_layernorm.weight",
"shape": [
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 1048576,
"dtype": "F32",
"elements": 262144,
"name": "encoder.encoder_transformer.layers.1.self_attn.k_proj.weight",
"shape": [
512,
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 1048576,
"dtype": "F32",
"elements": 262144,
"name": "encoder.encoder_transformer.layers.1.self_attn.o_proj.weight",
"shape": [
512,
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 1048576,
"dtype": "F32",
"elements": 262144,
"name": "encoder.encoder_transformer.layers.1.self_attn.q_proj.weight",
"shape": [
512,
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 1048576,
"dtype": "F32",
"elements": 262144,
"name": "encoder.encoder_transformer.layers.1.self_attn.v_proj.weight",
"shape": [
512,
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2048,
"dtype": "F32",
"elements": 512,
"name": "encoder.encoder_transformer.layers.1.self_attn_layer_scale.scale",
"shape": [
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2048,
"dtype": "F32",
"elements": 512,
"name": "encoder.encoder_transformer.layers.2.input_layernorm.bias",
"shape": [
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2048,
"dtype": "F32",
"elements": 512,
"name": "encoder.encoder_transformer.layers.2.input_layernorm.weight",
"shape": [
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 4194304,
"dtype": "F32",
"elements": 1048576,
"name": "encoder.encoder_transformer.layers.2.mlp.fc1.weight",
"shape": [
2048,
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 4194304,
"dtype": "F32",
"elements": 1048576,
"name": "encoder.encoder_transformer.layers.2.mlp.fc2.weight",
"shape": [
512,
2048
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2048,
"dtype": "F32",
"elements": 512,
"name": "encoder.encoder_transformer.layers.2.mlp_layer_scale.scale",
"shape": [
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2048,
"dtype": "F32",
"elements": 512,
"name": "encoder.encoder_transformer.layers.2.post_attention_layernorm.bias",
"shape": [
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2048,
"dtype": "F32",
"elements": 512,
"name": "encoder.encoder_transformer.layers.2.post_attention_layernorm.weight",
"shape": [
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 1048576,
"dtype": "F32",
"elements": 262144,
"name": "encoder.encoder_transformer.layers.2.self_attn.k_proj.weight",
"shape": [
512,
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 1048576,
"dtype": "F32",
"elements": 262144,
"name": "encoder.encoder_transformer.layers.2.self_attn.o_proj.weight",
"shape": [
512,
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 1048576,
"dtype": "F32",
"elements": 262144,
"name": "encoder.encoder_transformer.layers.2.self_attn.q_proj.weight",
"shape": [
512,
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 1048576,
"dtype": "F32",
"elements": 262144,
"name": "encoder.encoder_transformer.layers.2.self_attn.v_proj.weight",
"shape": [
512,
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2048,
"dtype": "F32",
"elements": 512,
"name": "encoder.encoder_transformer.layers.2.self_attn_layer_scale.scale",
"shape": [
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2048,
"dtype": "F32",
"elements": 512,
"name": "encoder.encoder_transformer.layers.3.input_layernorm.bias",
"shape": [
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2048,
"dtype": "F32",
"elements": 512,
"name": "encoder.encoder_transformer.layers.3.input_layernorm.weight",
"shape": [
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 4194304,
"dtype": "F32",
"elements": 1048576,
"name": "encoder.encoder_transformer.layers.3.mlp.fc1.weight",
"shape": [
2048,
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 4194304,
"dtype": "F32",
"elements": 1048576,
"name": "encoder.encoder_transformer.layers.3.mlp.fc2.weight",
"shape": [
512,
2048
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2048,
"dtype": "F32",
"elements": 512,
"name": "encoder.encoder_transformer.layers.3.mlp_layer_scale.scale",
"shape": [
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2048,
"dtype": "F32",
"elements": 512,
"name": "encoder.encoder_transformer.layers.3.post_attention_layernorm.bias",
"shape": [
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2048,
"dtype": "F32",
"elements": 512,
"name": "encoder.encoder_transformer.layers.3.post_attention_layernorm.weight",
"shape": [
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 1048576,
"dtype": "F32",
"elements": 262144,
"name": "encoder.encoder_transformer.layers.3.self_attn.k_proj.weight",
"shape": [
512,
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 1048576,
"dtype": "F32",
"elements": 262144,
"name": "encoder.encoder_transformer.layers.3.self_attn.o_proj.weight",
"shape": [
512,
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 1048576,
"dtype": "F32",
"elements": 262144,
"name": "encoder.encoder_transformer.layers.3.self_attn.q_proj.weight",
"shape": [
512,
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 1048576,
"dtype": "F32",
"elements": 262144,
"name": "encoder.encoder_transformer.layers.3.self_attn.v_proj.weight",
"shape": [
512,
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2048,
"dtype": "F32",
"elements": 512,
"name": "encoder.encoder_transformer.layers.3.self_attn_layer_scale.scale",
"shape": [
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2048,
"dtype": "F32",
"elements": 512,
"name": "encoder.encoder_transformer.layers.4.input_layernorm.bias",
"shape": [
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2048,
"dtype": "F32",
"elements": 512,
"name": "encoder.encoder_transformer.layers.4.input_layernorm.weight",
"shape": [
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 4194304,
"dtype": "F32",
"elements": 1048576,
"name": "encoder.encoder_transformer.layers.4.mlp.fc1.weight",
"shape": [
2048,
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 4194304,
"dtype": "F32",
"elements": 1048576,
"name": "encoder.encoder_transformer.layers.4.mlp.fc2.weight",
"shape": [
512,
2048
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2048,
"dtype": "F32",
"elements": 512,
"name": "encoder.encoder_transformer.layers.4.mlp_layer_scale.scale",
"shape": [
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2048,
"dtype": "F32",
"elements": 512,
"name": "encoder.encoder_transformer.layers.4.post_attention_layernorm.bias",
"shape": [
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2048,
"dtype": "F32",
"elements": 512,
"name": "encoder.encoder_transformer.layers.4.post_attention_layernorm.weight",
"shape": [
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 1048576,
"dtype": "F32",
"elements": 262144,
"name": "encoder.encoder_transformer.layers.4.self_attn.k_proj.weight",
"shape": [
512,
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 1048576,
"dtype": "F32",
"elements": 262144,
"name": "encoder.encoder_transformer.layers.4.self_attn.o_proj.weight",
"shape": [
512,
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 1048576,
"dtype": "F32",
"elements": 262144,
"name": "encoder.encoder_transformer.layers.4.self_attn.q_proj.weight",
"shape": [
512,
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 1048576,
"dtype": "F32",
"elements": 262144,
"name": "encoder.encoder_transformer.layers.4.self_attn.v_proj.weight",
"shape": [
512,
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2048,
"dtype": "F32",
"elements": 512,
"name": "encoder.encoder_transformer.layers.4.self_attn_layer_scale.scale",
"shape": [
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2048,
"dtype": "F32",
"elements": 512,
"name": "encoder.encoder_transformer.layers.5.input_layernorm.bias",
"shape": [
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2048,
"dtype": "F32",
"elements": 512,
"name": "encoder.encoder_transformer.layers.5.input_layernorm.weight",
"shape": [
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 4194304,
"dtype": "F32",
"elements": 1048576,
"name": "encoder.encoder_transformer.layers.5.mlp.fc1.weight",
"shape": [
2048,
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 4194304,
"dtype": "F32",
"elements": 1048576,
"name": "encoder.encoder_transformer.layers.5.mlp.fc2.weight",
"shape": [
512,
2048
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2048,
"dtype": "F32",
"elements": 512,
"name": "encoder.encoder_transformer.layers.5.mlp_layer_scale.scale",
"shape": [
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2048,
"dtype": "F32",
"elements": 512,
"name": "encoder.encoder_transformer.layers.5.post_attention_layernorm.bias",
"shape": [
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2048,
"dtype": "F32",
"elements": 512,
"name": "encoder.encoder_transformer.layers.5.post_attention_layernorm.weight",
"shape": [
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 1048576,
"dtype": "F32",
"elements": 262144,
"name": "encoder.encoder_transformer.layers.5.self_attn.k_proj.weight",
"shape": [
512,
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 1048576,
"dtype": "F32",
"elements": 262144,
"name": "encoder.encoder_transformer.layers.5.self_attn.o_proj.weight",
"shape": [
512,
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 1048576,
"dtype": "F32",
"elements": 262144,
"name": "encoder.encoder_transformer.layers.5.self_attn.q_proj.weight",
"shape": [
512,
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 1048576,
"dtype": "F32",
"elements": 262144,
"name": "encoder.encoder_transformer.layers.5.self_attn.v_proj.weight",
"shape": [
512,
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2048,
"dtype": "F32",
"elements": 512,
"name": "encoder.encoder_transformer.layers.5.self_attn_layer_scale.scale",
"shape": [
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2048,
"dtype": "F32",
"elements": 512,
"name": "encoder.encoder_transformer.layers.6.input_layernorm.bias",
"shape": [
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2048,
"dtype": "F32",
"elements": 512,
"name": "encoder.encoder_transformer.layers.6.input_layernorm.weight",
"shape": [
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 4194304,
"dtype": "F32",
"elements": 1048576,
"name": "encoder.encoder_transformer.layers.6.mlp.fc1.weight",
"shape": [
2048,
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 4194304,
"dtype": "F32",
"elements": 1048576,
"name": "encoder.encoder_transformer.layers.6.mlp.fc2.weight",
"shape": [
512,
2048
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2048,
"dtype": "F32",
"elements": 512,
"name": "encoder.encoder_transformer.layers.6.mlp_layer_scale.scale",
"shape": [
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2048,
"dtype": "F32",
"elements": 512,
"name": "encoder.encoder_transformer.layers.6.post_attention_layernorm.bias",
"shape": [
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2048,
"dtype": "F32",
"elements": 512,
"name": "encoder.encoder_transformer.layers.6.post_attention_layernorm.weight",
"shape": [
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 1048576,
"dtype": "F32",
"elements": 262144,
"name": "encoder.encoder_transformer.layers.6.self_attn.k_proj.weight",
"shape": [
512,
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 1048576,
"dtype": "F32",
"elements": 262144,
"name": "encoder.encoder_transformer.layers.6.self_attn.o_proj.weight",
"shape": [
512,
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 1048576,
"dtype": "F32",
"elements": 262144,
"name": "encoder.encoder_transformer.layers.6.self_attn.q_proj.weight",
"shape": [
512,
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 1048576,
"dtype": "F32",
"elements": 262144,
"name": "encoder.encoder_transformer.layers.6.self_attn.v_proj.weight",
"shape": [
512,
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2048,
"dtype": "F32",
"elements": 512,
"name": "encoder.encoder_transformer.layers.6.self_attn_layer_scale.scale",
"shape": [
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2048,
"dtype": "F32",
"elements": 512,
"name": "encoder.encoder_transformer.layers.7.input_layernorm.bias",
"shape": [
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2048,
"dtype": "F32",
"elements": 512,
"name": "encoder.encoder_transformer.layers.7.input_layernorm.weight",
"shape": [
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 4194304,
"dtype": "F32",
"elements": 1048576,
"name": "encoder.encoder_transformer.layers.7.mlp.fc1.weight",
"shape": [
2048,
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 4194304,
"dtype": "F32",
"elements": 1048576,
"name": "encoder.encoder_transformer.layers.7.mlp.fc2.weight",
"shape": [
512,
2048
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2048,
"dtype": "F32",
"elements": 512,
"name": "encoder.encoder_transformer.layers.7.mlp_layer_scale.scale",
"shape": [
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2048,
"dtype": "F32",
"elements": 512,
"name": "encoder.encoder_transformer.layers.7.post_attention_layernorm.bias",
"shape": [
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2048,
"dtype": "F32",
"elements": 512,
"name": "encoder.encoder_transformer.layers.7.post_attention_layernorm.weight",
"shape": [
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 1048576,
"dtype": "F32",
"elements": 262144,
"name": "encoder.encoder_transformer.layers.7.self_attn.k_proj.weight",
"shape": [
512,
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 1048576,
"dtype": "F32",
"elements": 262144,
"name": "encoder.encoder_transformer.layers.7.self_attn.o_proj.weight",
"shape": [
512,
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 1048576,
"dtype": "F32",
"elements": 262144,
"name": "encoder.encoder_transformer.layers.7.self_attn.q_proj.weight",
"shape": [
512,
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 1048576,
"dtype": "F32",
"elements": 262144,
"name": "encoder.encoder_transformer.layers.7.self_attn.v_proj.weight",
"shape": [
512,
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2048,
"dtype": "F32",
"elements": 512,
"name": "encoder.encoder_transformer.layers.7.self_attn_layer_scale.scale",
"shape": [
512
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 524288,
"dtype": "F32",
"elements": 131072,
"name": "encoder.quantizer.acoustic_residual_vector_quantizer.input_proj.weight",
"shape": [
256,
512,
1
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 8192,
"dtype": "F32",
"elements": 2048,
"name": "encoder.quantizer.acoustic_residual_vector_quantizer.layers.0.codebook.cluster_usage",
"shape": [
2048
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2097152,
"dtype": "F32",
"elements": 524288,
"name": "encoder.quantizer.acoustic_residual_vector_quantizer.layers.0.codebook.embed_sum",
"shape": [
2048,
256
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 4,
"dtype": "F32",
"elements": 1,
"name": "encoder.quantizer.acoustic_residual_vector_quantizer.layers.0.codebook.initialized",
"shape": [
1
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 8192,
"dtype": "F32",
"elements": 2048,
"name": "encoder.quantizer.acoustic_residual_vector_quantizer.layers.1.codebook.cluster_usage",
"shape": [
2048
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2097152,
"dtype": "F32",
"elements": 524288,
"name": "encoder.quantizer.acoustic_residual_vector_quantizer.layers.1.codebook.embed_sum",
"shape": [
2048,
256
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 4,
"dtype": "F32",
"elements": 1,
"name": "encoder.quantizer.acoustic_residual_vector_quantizer.layers.1.codebook.initialized",
"shape": [
1
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 8192,
"dtype": "F32",
"elements": 2048,
"name": "encoder.quantizer.acoustic_residual_vector_quantizer.layers.10.codebook.cluster_usage",
"shape": [
2048
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2097152,
"dtype": "F32",
"elements": 524288,
"name": "encoder.quantizer.acoustic_residual_vector_quantizer.layers.10.codebook.embed_sum",
"shape": [
2048,
256
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 4,
"dtype": "F32",
"elements": 1,
"name": "encoder.quantizer.acoustic_residual_vector_quantizer.layers.10.codebook.initialized",
"shape": [
1
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 8192,
"dtype": "F32",
"elements": 2048,
"name": "encoder.quantizer.acoustic_residual_vector_quantizer.layers.11.codebook.cluster_usage",
"shape": [
2048
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2097152,
"dtype": "F32",
"elements": 524288,
"name": "encoder.quantizer.acoustic_residual_vector_quantizer.layers.11.codebook.embed_sum",
"shape": [
2048,
256
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 4,
"dtype": "F32",
"elements": 1,
"name": "encoder.quantizer.acoustic_residual_vector_quantizer.layers.11.codebook.initialized",
"shape": [
1
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 8192,
"dtype": "F32",
"elements": 2048,
"name": "encoder.quantizer.acoustic_residual_vector_quantizer.layers.12.codebook.cluster_usage",
"shape": [
2048
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2097152,
"dtype": "F32",
"elements": 524288,
"name": "encoder.quantizer.acoustic_residual_vector_quantizer.layers.12.codebook.embed_sum",
"shape": [
2048,
256
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 4,
"dtype": "F32",
"elements": 1,
"name": "encoder.quantizer.acoustic_residual_vector_quantizer.layers.12.codebook.initialized",
"shape": [
1
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 8192,
"dtype": "F32",
"elements": 2048,
"name": "encoder.quantizer.acoustic_residual_vector_quantizer.layers.13.codebook.cluster_usage",
"shape": [
2048
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2097152,
"dtype": "F32",
"elements": 524288,
"name": "encoder.quantizer.acoustic_residual_vector_quantizer.layers.13.codebook.embed_sum",
"shape": [
2048,
256
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 4,
"dtype": "F32",
"elements": 1,
"name": "encoder.quantizer.acoustic_residual_vector_quantizer.layers.13.codebook.initialized",
"shape": [
1
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 8192,
"dtype": "F32",
"elements": 2048,
"name": "encoder.quantizer.acoustic_residual_vector_quantizer.layers.14.codebook.cluster_usage",
"shape": [
2048
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2097152,
"dtype": "F32",
"elements": 524288,
"name": "encoder.quantizer.acoustic_residual_vector_quantizer.layers.14.codebook.embed_sum",
"shape": [
2048,
256
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 4,
"dtype": "F32",
"elements": 1,
"name": "encoder.quantizer.acoustic_residual_vector_quantizer.layers.14.codebook.initialized",
"shape": [
1
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 8192,
"dtype": "F32",
"elements": 2048,
"name": "encoder.quantizer.acoustic_residual_vector_quantizer.layers.15.codebook.cluster_usage",
"shape": [
2048
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2097152,
"dtype": "F32",
"elements": 524288,
"name": "encoder.quantizer.acoustic_residual_vector_quantizer.layers.15.codebook.embed_sum",
"shape": [
2048,
256
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 4,
"dtype": "F32",
"elements": 1,
"name": "encoder.quantizer.acoustic_residual_vector_quantizer.layers.15.codebook.initialized",
"shape": [
1
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 8192,
"dtype": "F32",
"elements": 2048,
"name": "encoder.quantizer.acoustic_residual_vector_quantizer.layers.16.codebook.cluster_usage",
"shape": [
2048
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2097152,
"dtype": "F32",
"elements": 524288,
"name": "encoder.quantizer.acoustic_residual_vector_quantizer.layers.16.codebook.embed_sum",
"shape": [
2048,
256
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 4,
"dtype": "F32",
"elements": 1,
"name": "encoder.quantizer.acoustic_residual_vector_quantizer.layers.16.codebook.initialized",
"shape": [
1
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 8192,
"dtype": "F32",
"elements": 2048,
"name": "encoder.quantizer.acoustic_residual_vector_quantizer.layers.17.codebook.cluster_usage",
"shape": [
2048
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2097152,
"dtype": "F32",
"elements": 524288,
"name": "encoder.quantizer.acoustic_residual_vector_quantizer.layers.17.codebook.embed_sum",
"shape": [
2048,
256
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 4,
"dtype": "F32",
"elements": 1,
"name": "encoder.quantizer.acoustic_residual_vector_quantizer.layers.17.codebook.initialized",
"shape": [
1
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 8192,
"dtype": "F32",
"elements": 2048,
"name": "encoder.quantizer.acoustic_residual_vector_quantizer.layers.18.codebook.cluster_usage",
"shape": [
2048
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2097152,
"dtype": "F32",
"elements": 524288,
"name": "encoder.quantizer.acoustic_residual_vector_quantizer.layers.18.codebook.embed_sum",
"shape": [
2048,
256
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 4,
"dtype": "F32",
"elements": 1,
"name": "encoder.quantizer.acoustic_residual_vector_quantizer.layers.18.codebook.initialized",
"shape": [
1
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 8192,
"dtype": "F32",
"elements": 2048,
"name": "encoder.quantizer.acoustic_residual_vector_quantizer.layers.19.codebook.cluster_usage",
"shape": [
2048
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2097152,
"dtype": "F32",
"elements": 524288,
"name": "encoder.quantizer.acoustic_residual_vector_quantizer.layers.19.codebook.embed_sum",
"shape": [
2048,
256
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 4,
"dtype": "F32",
"elements": 1,
"name": "encoder.quantizer.acoustic_residual_vector_quantizer.layers.19.codebook.initialized",
"shape": [
1
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 8192,
"dtype": "F32",
"elements": 2048,
"name": "encoder.quantizer.acoustic_residual_vector_quantizer.layers.2.codebook.cluster_usage",
"shape": [
2048
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2097152,
"dtype": "F32",
"elements": 524288,
"name": "encoder.quantizer.acoustic_residual_vector_quantizer.layers.2.codebook.embed_sum",
"shape": [
2048,
256
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 4,
"dtype": "F32",
"elements": 1,
"name": "encoder.quantizer.acoustic_residual_vector_quantizer.layers.2.codebook.initialized",
"shape": [
1
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 8192,
"dtype": "F32",
"elements": 2048,
"name": "encoder.quantizer.acoustic_residual_vector_quantizer.layers.20.codebook.cluster_usage",
"shape": [
2048
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2097152,
"dtype": "F32",
"elements": 524288,
"name": "encoder.quantizer.acoustic_residual_vector_quantizer.layers.20.codebook.embed_sum",
"shape": [
2048,
256
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 4,
"dtype": "F32",
"elements": 1,
"name": "encoder.quantizer.acoustic_residual_vector_quantizer.layers.20.codebook.initialized",
"shape": [
1
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 8192,
"dtype": "F32",
"elements": 2048,
"name": "encoder.quantizer.acoustic_residual_vector_quantizer.layers.21.codebook.cluster_usage",
"shape": [
2048
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2097152,
"dtype": "F32",
"elements": 524288,
"name": "encoder.quantizer.acoustic_residual_vector_quantizer.layers.21.codebook.embed_sum",
"shape": [
2048,
256
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 4,
"dtype": "F32",
"elements": 1,
"name": "encoder.quantizer.acoustic_residual_vector_quantizer.layers.21.codebook.initialized",
"shape": [
1
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 8192,
"dtype": "F32",
"elements": 2048,
"name": "encoder.quantizer.acoustic_residual_vector_quantizer.layers.22.codebook.cluster_usage",
"shape": [
2048
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2097152,
"dtype": "F32",
"elements": 524288,
"name": "encoder.quantizer.acoustic_residual_vector_quantizer.layers.22.codebook.embed_sum",
"shape": [
2048,
256
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 4,
"dtype": "F32",
"elements": 1,
"name": "encoder.quantizer.acoustic_residual_vector_quantizer.layers.22.codebook.initialized",
"shape": [
1
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 8192,
"dtype": "F32",
"elements": 2048,
"name": "encoder.quantizer.acoustic_residual_vector_quantizer.layers.23.codebook.cluster_usage",
"shape": [
2048
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2097152,
"dtype": "F32",
"elements": 524288,
"name": "encoder.quantizer.acoustic_residual_vector_quantizer.layers.23.codebook.embed_sum",
"shape": [
2048,
256
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 4,
"dtype": "F32",
"elements": 1,
"name": "encoder.quantizer.acoustic_residual_vector_quantizer.layers.23.codebook.initialized",
"shape": [
1
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 8192,
"dtype": "F32",
"elements": 2048,
"name": "encoder.quantizer.acoustic_residual_vector_quantizer.layers.24.codebook.cluster_usage",
"shape": [
2048
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2097152,
"dtype": "F32",
"elements": 524288,
"name": "encoder.quantizer.acoustic_residual_vector_quantizer.layers.24.codebook.embed_sum",
"shape": [
2048,
256
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 4,
"dtype": "F32",
"elements": 1,
"name": "encoder.quantizer.acoustic_residual_vector_quantizer.layers.24.codebook.initialized",
"shape": [
1
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 8192,
"dtype": "F32",
"elements": 2048,
"name": "encoder.quantizer.acoustic_residual_vector_quantizer.layers.25.codebook.cluster_usage",
"shape": [
2048
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2097152,
"dtype": "F32",
"elements": 524288,
"name": "encoder.quantizer.acoustic_residual_vector_quantizer.layers.25.codebook.embed_sum",
"shape": [
2048,
256
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 4,
"dtype": "F32",
"elements": 1,
"name": "encoder.quantizer.acoustic_residual_vector_quantizer.layers.25.codebook.initialized",
"shape": [
1
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 8192,
"dtype": "F32",
"elements": 2048,
"name": "encoder.quantizer.acoustic_residual_vector_quantizer.layers.26.codebook.cluster_usage",
"shape": [
2048
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2097152,
"dtype": "F32",
"elements": 524288,
"name": "encoder.quantizer.acoustic_residual_vector_quantizer.layers.26.codebook.embed_sum",
"shape": [
2048,
256
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 4,
"dtype": "F32",
"elements": 1,
"name": "encoder.quantizer.acoustic_residual_vector_quantizer.layers.26.codebook.initialized",
"shape": [
1
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 8192,
"dtype": "F32",
"elements": 2048,
"name": "encoder.quantizer.acoustic_residual_vector_quantizer.layers.27.codebook.cluster_usage",
"shape": [
2048
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2097152,
"dtype": "F32",
"elements": 524288,
"name": "encoder.quantizer.acoustic_residual_vector_quantizer.layers.27.codebook.embed_sum",
"shape": [
2048,
256
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 4,
"dtype": "F32",
"elements": 1,
"name": "encoder.quantizer.acoustic_residual_vector_quantizer.layers.27.codebook.initialized",
"shape": [
1
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 8192,
"dtype": "F32",
"elements": 2048,
"name": "encoder.quantizer.acoustic_residual_vector_quantizer.layers.28.codebook.cluster_usage",
"shape": [
2048
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2097152,
"dtype": "F32",
"elements": 524288,
"name": "encoder.quantizer.acoustic_residual_vector_quantizer.layers.28.codebook.embed_sum",
"shape": [
2048,
256
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 4,
"dtype": "F32",
"elements": 1,
"name": "encoder.quantizer.acoustic_residual_vector_quantizer.layers.28.codebook.initialized",
"shape": [
1
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 8192,
"dtype": "F32",
"elements": 2048,
"name": "encoder.quantizer.acoustic_residual_vector_quantizer.layers.29.codebook.cluster_usage",
"shape": [
2048
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2097152,
"dtype": "F32",
"elements": 524288,
"name": "encoder.quantizer.acoustic_residual_vector_quantizer.layers.29.codebook.embed_sum",
"shape": [
2048,
256
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 4,
"dtype": "F32",
"elements": 1,
"name": "encoder.quantizer.acoustic_residual_vector_quantizer.layers.29.codebook.initialized",
"shape": [
1
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 8192,
"dtype": "F32",
"elements": 2048,
"name": "encoder.quantizer.acoustic_residual_vector_quantizer.layers.3.codebook.cluster_usage",
"shape": [
2048
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2097152,
"dtype": "F32",
"elements": 524288,
"name": "encoder.quantizer.acoustic_residual_vector_quantizer.layers.3.codebook.embed_sum",
"shape": [
2048,
256
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 4,
"dtype": "F32",
"elements": 1,
"name": "encoder.quantizer.acoustic_residual_vector_quantizer.layers.3.codebook.initialized",
"shape": [
1
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 8192,
"dtype": "F32",
"elements": 2048,
"name": "encoder.quantizer.acoustic_residual_vector_quantizer.layers.30.codebook.cluster_usage",
"shape": [
2048
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2097152,
"dtype": "F32",
"elements": 524288,
"name": "encoder.quantizer.acoustic_residual_vector_quantizer.layers.30.codebook.embed_sum",
"shape": [
2048,
256
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 4,
"dtype": "F32",
"elements": 1,
"name": "encoder.quantizer.acoustic_residual_vector_quantizer.layers.30.codebook.initialized",
"shape": [
1
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 8192,
"dtype": "F32",
"elements": 2048,
"name": "encoder.quantizer.acoustic_residual_vector_quantizer.layers.4.codebook.cluster_usage",
"shape": [
2048
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2097152,
"dtype": "F32",
"elements": 524288,
"name": "encoder.quantizer.acoustic_residual_vector_quantizer.layers.4.codebook.embed_sum",
"shape": [
2048,
256
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 4,
"dtype": "F32",
"elements": 1,
"name": "encoder.quantizer.acoustic_residual_vector_quantizer.layers.4.codebook.initialized",
"shape": [
1
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 8192,
"dtype": "F32",
"elements": 2048,
"name": "encoder.quantizer.acoustic_residual_vector_quantizer.layers.5.codebook.cluster_usage",
"shape": [
2048
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2097152,
"dtype": "F32",
"elements": 524288,
"name": "encoder.quantizer.acoustic_residual_vector_quantizer.layers.5.codebook.embed_sum",
"shape": [
2048,
256
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 4,
"dtype": "F32",
"elements": 1,
"name": "encoder.quantizer.acoustic_residual_vector_quantizer.layers.5.codebook.initialized",
"shape": [
1
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 8192,
"dtype": "F32",
"elements": 2048,
"name": "encoder.quantizer.acoustic_residual_vector_quantizer.layers.6.codebook.cluster_usage",
"shape": [
2048
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2097152,
"dtype": "F32",
"elements": 524288,
"name": "encoder.quantizer.acoustic_residual_vector_quantizer.layers.6.codebook.embed_sum",
"shape": [
2048,
256
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 4,
"dtype": "F32",
"elements": 1,
"name": "encoder.quantizer.acoustic_residual_vector_quantizer.layers.6.codebook.initialized",
"shape": [
1
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 8192,
"dtype": "F32",
"elements": 2048,
"name": "encoder.quantizer.acoustic_residual_vector_quantizer.layers.7.codebook.cluster_usage",
"shape": [
2048
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2097152,
"dtype": "F32",
"elements": 524288,
"name": "encoder.quantizer.acoustic_residual_vector_quantizer.layers.7.codebook.embed_sum",
"shape": [
2048,
256
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 4,
"dtype": "F32",
"elements": 1,
"name": "encoder.quantizer.acoustic_residual_vector_quantizer.layers.7.codebook.initialized",
"shape": [
1
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 8192,
"dtype": "F32",
"elements": 2048,
"name": "encoder.quantizer.acoustic_residual_vector_quantizer.layers.8.codebook.cluster_usage",
"shape": [
2048
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2097152,
"dtype": "F32",
"elements": 524288,
"name": "encoder.quantizer.acoustic_residual_vector_quantizer.layers.8.codebook.embed_sum",
"shape": [
2048,
256
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 4,
"dtype": "F32",
"elements": 1,
"name": "encoder.quantizer.acoustic_residual_vector_quantizer.layers.8.codebook.initialized",
"shape": [
1
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 8192,
"dtype": "F32",
"elements": 2048,
"name": "encoder.quantizer.acoustic_residual_vector_quantizer.layers.9.codebook.cluster_usage",
"shape": [
2048
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2097152,
"dtype": "F32",
"elements": 524288,
"name": "encoder.quantizer.acoustic_residual_vector_quantizer.layers.9.codebook.embed_sum",
"shape": [
2048,
256
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 4,
"dtype": "F32",
"elements": 1,
"name": "encoder.quantizer.acoustic_residual_vector_quantizer.layers.9.codebook.initialized",
"shape": [
1
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 524288,
"dtype": "F32",
"elements": 131072,
"name": "encoder.quantizer.acoustic_residual_vector_quantizer.output_proj.weight",
"shape": [
512,
256,
1
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 524288,
"dtype": "F32",
"elements": 131072,
"name": "encoder.quantizer.semantic_residual_vector_quantizer.input_proj.weight",
"shape": [
256,
512,
1
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 8192,
"dtype": "F32",
"elements": 2048,
"name": "encoder.quantizer.semantic_residual_vector_quantizer.layers.0.codebook.cluster_usage",
"shape": [
2048
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 2097152,
"dtype": "F32",
"elements": 524288,
"name": "encoder.quantizer.semantic_residual_vector_quantizer.layers.0.codebook.embed_sum",
"shape": [
2048,
256
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 4,
"dtype": "F32",
"elements": 1,
"name": "encoder.quantizer.semantic_residual_vector_quantizer.layers.0.codebook.initialized",
"shape": [
1
],
"source": "speech_tokenizer/model.safetensors"
},
{
"bytes": 524288,
"dtype": "F32",
"elements": 131072,
"name": "encoder.quantizer.semantic_residual_vector_quantizer.output_proj.weight",
"shape": [
512,
256,
1
],
"source": "speech_tokenizer/model.safetensors"
}
]
}