ICTNLP/bayling-7b-diff
821
1{2 "_name_or_path": "/data/zhangshaolei/FastChat/checkpoints/imt.llama_7B.data=en-zh-de-fr.wmt_dev+IMT.v8+personal+gpt4_alpaca_zhen+sharegpt+pe.393739",3 "architectures": [4 "LlamaForCausalLM"5 ],6 "bos_token_id": 0,7 "eos_token_id": 1,8 "hidden_act": "silu",9 "hidden_size": 4096,10 "initializer_range": 0.02,11 "intermediate_size": 11008,12 "max_position_embeddings": 2048,13 "max_sequence_length": 2048,14 "model_type": "llama",15 "num_attention_heads": 32,16 "num_hidden_layers": 32,17 "pad_token_id": -1,18 "rms_norm_eps": 1e-06,19 "tie_word_embeddings": false,20 "torch_dtype": "float16",21 "transformers_version": "4.28.1",22 "use_cache": true,23 "vocab_size": 3200024}25 