{
"model_repo": "medmekk/Llama-3.2-1B-Instruct-bnb-nf4",
"tokenizer_repo": "meta-llama/Llama-3.2-1B",
"methodology": "bitsandbytes-NF4 forward-pass oracle (transformers + bitsandbytes, F32 compute on CUDA); validates candle-mi's anamnesis NF4 dequant load path",
"torch_version": "2.10.0+cu130",
"transformers_version": "5.1.0",
"bitsandbytes_version": "0.49.1",
"platform": "Windows-11-10.0.26200-SP0",
"model_type": "llama",
"quant_method": "QuantizationMethod.BITS_AND_BYTES",
"hidden_size": 2048,
"num_layers": 16,
"vocab_size": 128256,
"head_dim": 64,
"test_cases": [
{
"prompt": "The capital of France is",
"tokens": [
128000,
791,
6864,
315,
9822,
374
],
"top_10": [
{
"index": 12366,
"logit": 19.231300354003906
},
{
"index": 539,
"logit": 16.053695678710938
},
{
"index": 264,
"logit": 15.744446754455566
},
{
"index": 1131,
"logit": 15.438555717468262
},
{
"index": 279,
"logit": 14.940621376037598
},
{
"index": 20437,
"logit": 14.774496078491211
},
{
"index": 25,
"logit": 14.530152320861816
},
{
"index": 311,
"logit": 14.517041206359863
},
{
"index": 7559,
"logit": 14.354340553283691
},
{
"index": 3604,
"logit": 14.301971435546875
}
]
},
{
"prompt": "Two plus two equals",
"tokens": [
128000,
11874,
5636,
1403,
17239
],
"top_10": [
{
"index": 3116,
"logit": 20.51384925842285
},
{
"index": 4330,
"logit": 20.301528930664062
},
{
"index": 220,
"logit": 18.263551712036133
},
{
"index": 4400,
"logit": 18.191823959350586
},
{
"index": 8223,
"logit": 17.986309051513672
},
{
"index": 1131,
"logit": 17.86895179748535
},
{
"index": 8254,
"logit": 17.833688735961914
},
{
"index": 4848,
"logit": 17.661401748657227
},
{
"index": 198,
"logit": 17.351215362548828
},
{
"index": 482,
"logit": 17.265073776245117
}
]
},
{
"prompt": "Once upon a time, there was a",
"tokens": [
128000,
12805,
5304,
264,
892,
11,
1070,
574,
264
],
"top_10": [
{
"index": 3995,
"logit": 19.341646194458008
},
{
"index": 2678,
"logit": 17.349872589111328
},
{
"index": 893,
"logit": 17.160659790039062
},
{
"index": 6366,
"logit": 17.104965209960938
},
{
"index": 2697,
"logit": 16.60169219970703
},
{
"index": 8334,
"logit": 16.12689208984375
},
{
"index": 3828,
"logit": 16.021955490112305
},
{
"index": 1912,
"logit": 15.974161148071289
},
{
"index": 24632,
"logit": 15.948994636535645
},
{
"index": 5333,
"logit": 15.813974380493164
}
]
}
]
}