| { |
| "architectures": [ |
| "LlamaForCausalLM" |
| ], |
| "attention_bias": false, |
| "attention_dropout": 0.0, |
| "bos_token_id": 0, |
| "eos_token_id": 2, |
| "head_dim": 64, |
| "hidden_act": "silu", |
| "hidden_size": 768, |
| "initializer_range": 0.02, |
| "intermediate_size": 3072, |
| "max_position_embeddings": 2048, |
| "mlp_bias": false, |
| "model_type": "llama", |
| "num_attention_heads": 12, |
| "num_hidden_layers": 2, |
| "num_key_value_heads": 12, |
| "pad_token_id": 1, |
| "pretraining_tp": 1, |
| "quantization_config": { |
| "include_input_output_embeddings": false, |
| "modules_to_not_convert": null, |
| "quant_method": "torchao", |
| "quant_type": "int4_weight_only", |
| "quant_type_kwargs": {}, |
| "untie_embedding_weights": false |
| }, |
| "rms_norm_eps": 1e-06, |
| "rope_scaling": null, |
| "rope_theta": 10000.0, |
| "tie_word_embeddings": false, |
| "torch_dtype": "bfloat16", |
| "transformers_version": "4.52.3", |
| "use_cache": true, |
| "vocab_size": 32000 |
| } |
|
|
