| { | |
| "_name_or_path": "/mnt/petrelfs/wangjiong/unified_benchmark/pretrain/huggingface/models--lmsys--vicuna-7b-delta-v0/snapshots/f902a2f7e2ca5dfeedf40a0220320e50d2d4fa2a/", | |
| "architectures": [ | |
| "LlavaLlamaForCausalLM" | |
| ], | |
| "bos_token_id": 1, | |
| "eos_token_id": 2, | |
| "hidden_act": "silu", | |
| "hidden_size": 4096, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 11008, | |
| "max_position_embeddings": 2048, | |
| "max_sequence_length": 2048, | |
| "model_type": "llava", | |
| "num_attention_heads": 32, | |
| "num_hidden_layers": 32, | |
| "pad_token_id": 0, | |
| "rms_norm_eps": 1e-06, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "float16", | |
| "transformers_version": "4.28.0.dev0", | |
| "use_cache": true, | |
| "vocab_size": 32001 | |
| } | |