{ "_name_or_path": "/nfs/a100-80G-17/jiyunjie/finetuned_ckpt/hf_llama_7b_expand_belle_tokenizer50k/wudao_200G_pretrain_filter_len2000_instr_l512_epoch=0-step=6400", "architectures": [ "LlamaForCausalLM" ], "bos_token_id": 1, "eos_token_id": 2, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 11008, "model_type": "llama", "num_attention_heads": 32, "num_hidden_layers": 32, "pad_token_id": 0, "rms_norm_eps": 1e-06, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "transformers_version": "4.28.0.dev0", "use_cache": true, "vocab_size": 79458 }