| { | |
| "_name_or_path": "rinna/japanese-gpt-neox-3.6b-instruction-ppo", | |
| "architectures": [ | |
| "GPTNeoXForCausalLM" | |
| ], | |
| "attention_probs_dropout_prob": 0.0, | |
| "bos_token_id": 2, | |
| "custom_pipelines": { | |
| "text-generation": { | |
| "impl": "h2oai_pipeline.H2OTextGenerationPipeline", | |
| "pt": "AutoModelForCausalLM" | |
| } | |
| }, | |
| "eos_token_id": 3, | |
| "hidden_act": "gelu", | |
| "hidden_dropout_prob": 0.0, | |
| "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, | |
| "rotary_emb_base": 10000, | |
| "rotary_pct": 1.0, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "float16", | |
| "transformers_version": "4.28.1", | |
| "use_cache": true, | |
| "use_parallel_residual": false, | |
| "vocab_size": 32000 | |
| } | |