Multi-Domain-Expert-Learning/expert-github
129
1{2 "_name_or_path": "EleutherAI/pythia-1b-deduped",3 "architectures": [4 "GPTNeoXForCausalLM"5 ],6 "bos_token_id": 0,7 "eos_token_id": 0,8 "hidden_act": "gelu",9 "hidden_size": 2048,10 "initializer_range": 0.02,11 "intermediate_size": 8192,12 "layer_norm_eps": 1e-05,13 "max_position_embeddings": 2048,14 "model_type": "gpt_neox",15 "num_attention_heads": 8,16 "num_hidden_layers": 16,17 "rotary_emb_base": 10000,18 "rotary_pct": 0.25,19 "tie_word_embeddings": false,20 "torch_dtype": "float32",21 "transformers_version": "4.28.1",22 "use_cache": true,23 "use_parallel_residual": true,24 "vocab_size": 5030425}26 