{ "_name_or_path": "/workspace/models/phi-1_5", "activation_function": "gelu_new", "architecture": { "block_cls": "parallel", "mixer": {}, "mlp": { "mlp_cls": "mlp" } }, "architectures": [ "MixFormerSequentialForCausalLM" ], "auto_map": { "AutoConfig": "configuration_mixformer_sequential.MixFormerSequentialConfig", "AutoModelForCausalLM": "modeling_mixformer_sequential.MixFormerSequentialForCausalLM" }, "embd_layer": "default", "embd_pdrop": 0.0, "initializer_range": 0.02, "layer_norm_epsilon": 1e-05, "model_type": "mixformer-sequential", "n_embd": 2048, "n_head": 32, "n_inner": null, "n_layer": 24, "n_positions": 2048, "phyagi_version": "0.0.4.dev", "resid_pdrop": 0.0, "rotary_dim": 32, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "transformers_version": "4.33.1", "use_cache": false, "vocab_size": 50304 }