Expand description
Model-related types and configurations
Structs§
- Attention
Config - Attention configuration for model architecture
- Model
Config - Model configuration for runtime
- Model
Info - Model information and metadata
- Model
Memory Requirements - Memory requirements for model inference
- Rope
Scaling - RoPE (Rotary Position Embedding) scaling configuration
- Token
Usage - Token usage statistics
Enums§
- Activation
- Activation function type
- Model
Source - Model loading source specification
- Model
Type - Model type enumeration
- Norm
Type - Normalization type used in the model
- Quantization
Config - Quantization configuration