microsoft/phi-2
3.5k573k
1{2 "_name_or_path": "microsoft/phi-2",3 "architectures": [4 "PhiForCausalLM"5 ],6 "attention_dropout": 0.0,7 "bos_token_id": 50256,8 "embd_pdrop": 0.0,9 "eos_token_id": 50256,10 "hidden_act": "gelu_new",11 "hidden_size": 2560,12 "initializer_range": 0.02,13 "intermediate_size": 10240,14 "layer_norm_eps": 1e-05,15 "max_position_embeddings": 2048,16 "model_type": "phi",17 "num_attention_heads": 32,18 "num_hidden_layers": 32,19 "num_key_value_heads": 32,20 "partial_rotary_factor": 0.4,21 "qk_layernorm": false,22 "resid_pdrop": 0.1,23 "rope_scaling": null,24 "rope_theta": 10000.0,25 "tie_word_embeddings": false,26 "torch_dtype": "float16",27 "transformers_version": "4.37.0",28 "use_cache": true,29 "vocab_size": 5120030}31 