| { | |
| "_name_or_path": "mojanjp/phi-2", | |
| "activation_function": "gelu_new", | |
| "architecture": { | |
| "block_cls": "parallel", | |
| "mlp": { | |
| "mlp_cls": "fused_mlp" | |
| } | |
| }, | |
| "architectures": [ | |
| "MixFormerSequentialForCausalLM" | |
| ], | |
| "attn_pdrop": 0.0, | |
| "auto_map": { | |
| "AutoConfig": "configuration_mixformer_sequential.MixFormerSequentialConfig", | |
| "AutoModelForCausalLM": "modeling_mixformer_sequential.MixFormerSequentialForCausalLM" | |
| }, | |
| "embd_pdrop": 0.0, | |
| "flash_rotary": false, | |
| "fused_dense": false, | |
| "initializer_range": 0.02, | |
| "layer_norm_epsilon": 1e-05, | |
| "model_type": "mixformer-sequential", | |
| "n_embd": 2560, | |
| "n_head": 32, | |
| "n_head_kv": null, | |
| "n_inner": null, | |
| "n_layer": 32, | |
| "n_positions": 2048, | |
| "resid_pdrop": 0.0, | |
| "rotary_dim": 32, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.34.0", | |
| "vocab_size": 51200 | |
| } | |