| { | |
| "architectures": [ | |
| "LlamaForCausalLM" | |
| ], | |
| "auto_map": { | |
| "AutoConfig": "configuration_llama.LlamaConfig", | |
| "AutoModel": "modeling_llama.LlamaModel", | |
| "AutoModelForCausalLM": "modeling_llama.LlamaForCausalLM" | |
| }, | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 128000, | |
| "eos_token_id": 128001, | |
| "hidden_act": "silu", | |
| "hidden_size": 4096, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 14336, | |
| "max_position_embeddings": 8192, | |
| "model_type": "llama", | |
| "num_attention_heads": 32, | |
| "num_hidden_layers": 32, | |
| "num_key_value_heads": 8, | |
| "pretraining_tp": 1, | |
| "rms_norm_eps": 1e-05, | |
| "rope_scaling": null, | |
| "rope_theta": 500000.0, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.40.0.dev0", | |
| "use_cache": true, | |
| "vocab_size": 128256, | |
| "layer_exec_plan": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31] | |
| } | |