AbhayGoyal/content
017
1{2 "_name_or_path": "microsoft/phi-1_5",3 "activation_function": "gelu_new",4 "architectures": [5 "MixFormerSequentialForCausalLM"6 ],7 "auto_map": {8 "AutoConfig": "microsoft/phi-1_5--configuration_mixformer_sequential.MixFormerSequentialConfig",9 "AutoModelForCausalLM": "microsoft/phi-1_5--modeling_mixformer_sequential.MixFormerSequentialForCausalLM"10 },11 "embd_pdrop": 0.0,12 "initializer_range": 0.02,13 "layer_norm_epsilon": 1e-05,14 "model_type": "mixformer-sequential",15 "n_embd": 2048,16 "n_head": 32,17 "n_head_kv": null,18 "n_inner": null,19 "n_layer": 24,20 "n_positions": 2048,21 "resid_pdrop": 0.0,22 "rotary_dim": 32,23 "tie_word_embeddings": false,24 "torch_dtype": "float32",25 "transformers_version": "4.34.1",26 "vocab_size": 5120027}28 