| { | |
| "_name_or_path": "rinna/bilingual-gpt-neox-4b-instruction-sft", | |
| "architectures": [ | |
| "GPTNeoXForCausalLM" | |
| ], | |
| "attention_bias": true, | |
| "attention_dropout": 0.1, | |
| "bos_token_id": 2, | |
| "classifier_dropout": 0.1, | |
| "eos_token_id": 3, | |
| "hidden_act": "gelu", | |
| "hidden_dropout": 0.1, | |
| "hidden_size": 2816, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 11264, | |
| "layer_norm_eps": 1e-05, | |
| "max_position_embeddings": 2048, | |
| "model_type": "gpt_neox", | |
| "num_attention_heads": 22, | |
| "num_hidden_layers": 36, | |
| "rope_scaling": null, | |
| "rotary_emb_base": 10000, | |
| "rotary_pct": 1.0, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.38.2", | |
| "use_cache": false, | |
| "use_parallel_residual": false, | |
| "vocab_size": 65536 | |
| } | |