| { | |
| "_name_or_path": "phi-600M-cont/checkpoint-5000", | |
| "activation_function": "gelu_new", | |
| "architectures": [ | |
| "PhiForCausalLM" | |
| ], | |
| "attention_dropout": 0.0, | |
| "attn_pdrop": 0.0, | |
| "auto_map": { | |
| "AutoConfig": "configuration_phi.PhiConfig", | |
| "AutoModelForCausalLM": "modeling_phi.PhiForCausalLM" | |
| }, | |
| "bos_token_id": 50256, | |
| "embd_pdrop": 0.0, | |
| "eos_token_id": 50256, | |
| "flash_attn": true, | |
| "flash_rotary": true, | |
| "fused_dense": true, | |
| "hidden_act": "gelu_new", | |
| "hidden_size": 2048, | |
| "img_processor": null, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 8192, | |
| "layer_norm_eps": 1e-05, | |
| "layer_norm_epsilon": 1e-05, | |
| "max_position_embeddings": 2048, | |
| "model_type": "phi", | |
| "n_embd": 1536, | |
| "n_head": 16, | |
| "n_head_kv": null, | |
| "n_inner": null, | |
| "n_layer": 16, | |
| "n_positions": 2048, | |
| "num_attention_heads": 32, | |
| "num_hidden_layers": 24, | |
| "num_key_value_heads": 32, | |
| "partial_rotary_factor": 0.5, | |
| "qk_layernorm": false, | |
| "resid_pdrop": 0.1, | |
| "rope_scaling": null, | |
| "rope_theta": 10000.0, | |
| "rotary_dim": 32, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.37.0.dev0", | |
| "use_cache": false, | |
| "vocab_size": 51200 | |
| } | |