| { | |
| "_name_or_path": "EleutherAI/pythia-1.3b-deduped", | |
| "architectures": [ | |
| "GPTNeoXForCausalLM" | |
| ], | |
| "bad_words_ids": [ | |
| [ | |
| 434, | |
| 15694, | |
| 66, | |
| 27, | |
| 209 | |
| ], | |
| [ | |
| 15362 | |
| ], | |
| [ | |
| 1713 | |
| ], | |
| [ | |
| 1713, | |
| 64 | |
| ], | |
| [ | |
| 1713, | |
| 876 | |
| ], | |
| [ | |
| 2016, | |
| 251, | |
| 857, | |
| 75, | |
| 9194, | |
| 35478 | |
| ], | |
| [ | |
| 2391 | |
| ], | |
| [ | |
| 20340 | |
| ], | |
| [ | |
| 33021 | |
| ], | |
| [ | |
| 2391, | |
| 1051 | |
| ], | |
| [ | |
| 5638 | |
| ], | |
| [ | |
| 2391, | |
| 20340 | |
| ], | |
| [ | |
| 5638, | |
| 537 | |
| ], | |
| [ | |
| 1559, | |
| 2345 | |
| ], | |
| [ | |
| 1559, | |
| 7849 | |
| ], | |
| [ | |
| 1559, | |
| 17379 | |
| ], | |
| [ | |
| 25321, | |
| 4611 | |
| ] | |
| ], | |
| "bos_token_id": 0, | |
| "eos_token_id": 0, | |
| "hidden_act": "gelu", | |
| "hidden_size": 2048, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 8192, | |
| "layer_norm_eps": 1e-05, | |
| "max_position_embeddings": 2048, | |
| "model_type": "gpt_neox", | |
| "num_attention_heads": 16, | |
| "num_hidden_layers": 24, | |
| "rotary_emb_base": 10000, | |
| "rotary_pct": 0.25, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "float16", | |
| "transformers_version": "4.25.1", | |
| "use_cache": true, | |
| "use_parallel_residual": true, | |
| "vocab_size": 50304 | |
| } | |