| { |
| "architectures": [ |
| "LlamaForCausalLM" |
| ], |
| "attention_bias": false, |
| "attention_dropout": 0.0, |
| "bos_token_id": 128000, |
| "eos_token_id": 128009, |
| "head_dim": 128, |
| "hidden_act": "silu", |
| "hidden_size": 4096, |
| "initializer_range": 0.02, |
| "intermediate_size": 14336, |
| "max_position_embeddings": 8192, |
| "mlp_bias": false, |
| "model_type": "llama", |
| "num_attention_heads": 32, |
| "num_hidden_layers": 32, |
| "num_key_value_heads": 8, |
| "pretraining_tp": 1, |
| "quantization_config": { |
| "modules_to_not_convert": null, |
| "quant_method": "torchao", |
| "quant_type": { |
| "default": { |
| "_data": { |
| "activation_dtype": { |
| "_data": "float8_e4m3fn", |
| "_type": "torch.dtype" |
| }, |
| "granularity": { |
| "_data": {}, |
| "_type": "PerTensor", |
| "_version": 1 |
| }, |
| "mm_config": { |
| "_data": { |
| "emulate": false, |
| "pad_inner_dim": false, |
| "use_fast_accum": true |
| }, |
| "_type": "Float8MMConfig", |
| "_version": 1 |
| }, |
| "set_inductor_config": true, |
| "weight_dtype": { |
| "_data": "float8_e4m3fn", |
| "_type": "torch.dtype" |
| } |
| }, |
| "_type": "Float8DynamicActivationFloat8WeightConfig", |
| "_version": 1 |
| } |
| }, |
| "quant_type_kwargs": {} |
| }, |
| "rms_norm_eps": 1e-05, |
| "rope_scaling": null, |
| "rope_theta": 500000.0, |
| "tie_word_embeddings": false, |
| "torch_dtype": "bfloat16", |
| "transformers_version": "4.51.3", |
| "use_cache": true, |
| "vocab_size": 128256 |
| } |
|
|
