| { | |
| "_name_or_path": "my_model_saves/checkpoint-224000", | |
| "architectures": [ | |
| "LlamaForCausalLM" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "attention_implementation": "flash_attention_2", | |
| "bos_token_id": 0, | |
| "eos_token_id": 2, | |
| "head_dim": 96, | |
| "hidden_act": "silu", | |
| "hidden_size": 1536, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 6144, | |
| "max_position_embeddings": 1024, | |
| "mlp_bias": false, | |
| "model_type": "llama", | |
| "num_attention_heads": 16, | |
| "num_hidden_layers": 12, | |
| "num_key_value_heads": 16, | |
| "pad_token_id": 1, | |
| "pretraining_tp": 1, | |
| "rms_norm_eps": 1e-06, | |
| "rope_scaling": { | |
| "factor": 2.0, | |
| "rope_type": "dynamic", | |
| "type": "dynamic" | |
| }, | |
| "rope_theta": 10000.0, | |
| "rotary_embedding_base": 10000, | |
| "tie_word_embeddings": true, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.48.0", | |
| "use_cache": true, | |
| "use_flash_attention": true, | |
| "use_memory_efficient_attention": true, | |
| "use_scaled_dot_product": true, | |
| "vocab_size": 32768 | |
| } | |