| { | |
| "_name_or_path": "/home/jovyan/testdata/zhangmengyu/gpt/checkpoints/zhinao2bbase_cmedqahn10rand10_2e5_18epoch_best", | |
| "architectures": [ | |
| "ZhinaoForCausalLM" | |
| ], | |
| "auto_map": { | |
| "AutoConfig": "configuration_zhinao.ZhinaoConfig", | |
| "AutoModelForCausalLM": "modeling_zhinao.ZhinaoForCausalLM" | |
| }, | |
| "bf16": true, | |
| "flah-attn_version": "2.5.5", | |
| "fp16": false, | |
| "hidden_act": "silu", | |
| "hidden_size": 2048, | |
| "initializer_range": 0.01, | |
| "intermediate_size": 5632, | |
| "max_position_embeddings": 4096, | |
| "model_max_length": 4096, | |
| "model_type": "zhinao", | |
| "num_attention_heads": 16, | |
| "num_hidden_layers": 24, | |
| "num_key_value_heads": 16, | |
| "rms_norm_eps": 1e-05, | |
| "rope_scaling": null, | |
| "rope_theta": 10000.0, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.34.0", | |
| "use_cache": false, | |
| "use_flash_attn": true, | |
| "vocab_size": 158464 | |
| } | |