| { |
| "_name_or_path": "/data/cw_llm/models/merged_model", |
| "architectures": [ |
| "GPTNeoXForCausalLM" |
| ], |
| "attention_dropout": 0.0, |
| "bos_token_id": 0, |
| "classifier_dropout": 0.1, |
| "eos_token_id": 0, |
| "hidden_act": "gelu", |
| "hidden_dropout": 0.0, |
| "hidden_size": 4096, |
| "initializer_range": 0.02, |
| "intermediate_size": 16384, |
| "layer_norm_eps": 1e-05, |
| "max_position_embeddings": 2048, |
| "model_type": "gpt_neox", |
| "num_attention_heads": 16, |
| "num_hidden_layers": 28, |
| "num_steps": "global_step320000", |
| "rope_scaling": null, |
| "rotary_emb_base": 10000, |
| "rotary_pct": 0.25, |
| "tie_word_embeddings": false, |
| "torch_dtype": "float32", |
| "transformers_version": "4.34.1", |
| "use_cache": true, |
| "use_parallel_residual": true, |
| "vocab_size": 30080 |
| } |
|
|
