aboros98/merlin1.1
061
1{2 "architectures": [3 "PhiForCausalLM"4 ],5 "auto_map": {6 "AutoConfig": "microsoft/phi-2--configuration_phi.PhiConfig",7 "AutoModelForCausalLM": "microsoft/phi-2--modeling_phi.PhiForCausalLM"8 },9 "attention_dropout": 0.0,10 "bos_token_id": 50296,11 "embd_pdrop": 0.0,12 "eos_token_id": 50297,13 "pad_token_id": 50295,14 "hidden_act": "gelu_new",15 "hidden_size": 2560,16 "initializer_range": 0.02,17 "intermediate_size": 10240,18 "layer_norm_eps": 1e-05,19 "max_position_embeddings": 2048,20 "model_type": "phi",21 "num_attention_heads": 32,22 "num_hidden_layers": 32,23 "num_key_value_heads": 32,24 "partial_rotary_factor": 0.4,25 "qk_layernorm": false,26 "resid_pdrop": 0.1,27 "rope_scaling": null,28 "rope_theta": 10000.0,29 "tie_word_embeddings": false,30 "torch_dtype": "float16",31 "transformers_version": "4.37.0",32 "use_cache": true,33 "vocab_size": 5120034}35 