Sayan01/Phi2-by2
0107
1{2 "_name_or_path": "microsoft/phi-2",3 "architectures": [4 "PhiForCausalLM"5 ],6 "attention_dropout": 0.0,7 "bos_token_id": 50256,8 "early_stopping": null,9 "embd_pdrop": 0.0,10 "eos_token_id": 50256,11 "hidden_act": "gelu_new",12 "hidden_size": 2560,13 "initializer_range": 0.02,14 "intermediate_size": 2560,15 "layer_norm_eps": 1e-05,16 "max_position_embeddings": 2048,17 "model_type": "phi",18 "num_attention_heads": 32,19 "num_beams": null,20 "num_hidden_layers": 32,21 "num_key_value_heads": 32,22 "partial_rotary_factor": 0.4,23 "qk_layernorm": false,24 "resid_pdrop": 0.1,25 "rope_scaling": null,26 "rope_theta": 10000.0,27 "tie_word_embeddings": false,28 "torch_dtype": "bfloat16",29 "transformers_version": "4.45.2",30 "use_cache": true,31 "vocab_size": 5120032}33 