| { | |
| "_name_or_path": "../vicuna-7b-v1.5-16k", | |
| "architectures": [ | |
| "HeteroLlamaForCausalLM" | |
| ], | |
| "bos_token_id": 1, | |
| "eos_token_id": 2, | |
| "freeze_graph_mlp_adapter": false, | |
| "graph_hidden_size": 768, | |
| "graph_select_layer": -2, | |
| "graph_tower": "MetaHGT_imdb_dblp_epoch5", | |
| "hidden_act": "silu", | |
| "hidden_size": 4096, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 11008, | |
| "max_position_embeddings": 4096, | |
| "max_sequence_length": 16384, | |
| "model_type": "HeteroLlama", | |
| "num_attention_heads": 32, | |
| "num_hidden_layers": 32, | |
| "num_key_value_heads": 32, | |
| "out_hidden_size": 768, | |
| "pad_token_id": 0, | |
| "pretrain_graph_model_path": "/root/paddlejob/workspace/env_run/jupyter_notes/HeteGPT/MetaHGT_imdb_dblp_epoch5", | |
| "pretraining_tp": 1, | |
| "rms_norm_eps": 1e-05, | |
| "rope_scaling": { | |
| "factor": 4.0, | |
| "type": "linear" | |
| }, | |
| "sep_graph_conv_front": false, | |
| "text_cfg": { | |
| "context_length": 512, | |
| "heads": 10, | |
| "layers": 6, | |
| "vocab_size": 49408, | |
| "width": 640 | |
| }, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.31.0", | |
| "tune_graph_mlp_adapter": true, | |
| "use_cache": false, | |
| "use_graph_proj": true, | |
| "use_graph_start_end": true, | |
| "vocab_size": 32003 | |
| } | |