{ "_name_or_path": "pythia-6.9b-hc3-qa-assistant", "architectures": [ "GPTNeoXForCausalLM" ], "bos_token_id": 0, "eos_token_id": 0, "hidden_act": "gelu", "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": 32, "num_hidden_layers": 32, "rotary_emb_base": 10000, "rotary_pct": 0.25, "tie_word_embeddings": false, "torch_dtype": "float32", "transformers_version": "4.27.0.dev0", "use_cache": true, "use_parallel_residual": true, "vocab_size": 50432 }