config.json
| 1 | { |
| 2 | "architectures": [ |
| 3 | "GPTNeoXForCausalLM" |
| 4 | ], |
| 5 | "bos_token_id": 0, |
| 6 | "eos_token_id": 0, |
| 7 | "hidden_act": "gelu", |
| 8 | "hidden_size": 768, |
| 9 | "initializer_range": 0.02, |
| 10 | "intermediate_size": 3072, |
| 11 | "layer_norm_eps": 1e-05, |
| 12 | "max_position_embeddings": 2048, |
| 13 | "model_type": "gpt_neox", |
| 14 | "num_attention_heads": 12, |
| 15 | "num_hidden_layers": 12, |
| 16 | "rotary_emb_base": 10000, |
| 17 | "rotary_pct": 0.25, |
| 18 | "tie_word_embeddings": false, |
| 19 | "torch_dtype": "float16", |
| 20 | "transformers_version": "4.24.0", |
| 21 | "use_cache": true, |
| 22 | "use_parallel_residual": true, |
| 23 | "vocab_size": 50304 |
| 24 | } |
| 25 | |