{ "_name_or_path": "/hpc_stor01/home/su.zhu/workspace/ckpts/chem-chinese-llama-13B-without-chem-tokens", "architectures": [ "LlamaForCausalLM" ], "attention_bias": false, "bos_token_id": 1, "end_token_id": 2, "eos_token_id": 2, "hidden_act": "silu", "hidden_size": 5120, "initializer_range": 0.02, "intermediate_size": 13824, "max_position_embeddings": 2048, "model_type": "llama", "num_attention_heads": 40, "num_hidden_layers": 40, "num_key_value_heads": 40, "pad_token_id": 2, "pretraining_tp": 1, "rms_norm_eps": 1e-06, "rope_scaling": null, "rope_theta": 10000, "tie_word_embeddings": false, "torch_dtype": "float16", "transformers_version": "4.35.0", "use_cache": true, "vocab_size": 39409 }