| { | |
| "_name_or_path": "/vsfs/deepspeed_chat/base-models/line-gpt-japanese-3.6b", | |
| "architectures": [ | |
| "GPTNeoXForCausalLM" | |
| ], | |
| "bos_token_id": 2, | |
| "classifier_dropout": 0.1, | |
| "end_token_id": 2, | |
| "eos_token_id": 2, | |
| "hidden_act": "gelu", | |
| "hidden_size": 3072, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 12288, | |
| "layer_norm_eps": 1e-05, | |
| "max_position_embeddings": 2048, | |
| "model_type": "gpt_neox", | |
| "num_attention_heads": 32, | |
| "num_hidden_layers": 30, | |
| "pad_token_id": 2, | |
| "rotary_emb_base": 10000, | |
| "rotary_pct": 1.0, | |
| "tie_word_embeddings": true, | |
| "torch_dtype": "float16", | |
| "transformers_version": "4.31.0.dev0", | |
| "use_cache": true, | |
| "use_parallel_residual": false, | |
| "vocab_size": 51200 | |
| } | |