| { | |
| "_name_or_path": "/local_home2/yurunpeng/DvD/output/DiM-v0.5.3-Instruct-7B-autoreg-instruct_llava_next_instruct_lr_5e-07_wd_0.0_bs_128_tt_dlm_9fe0af92_seed_0_autoreg-recovery", | |
| "architectures": [ | |
| "DimpleModel" | |
| ], | |
| "attention_dropout": 0.0, | |
| "auto_map": { | |
| "AutoConfig": "configuration_dimple.DimpleConfig", | |
| "AutoModel": "modeling_dimple.DimpleModel" | |
| }, | |
| "bos_token_id": 151643, | |
| "eos_token_id": 151643, | |
| "full_attn_mask": true, | |
| "hidden_act": "silu", | |
| "hidden_size": 3584, | |
| "image_token_id": 151655, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 18944, | |
| "mask_token_id": 151666, | |
| "max_position_embeddings": 131072, | |
| "max_window_layers": 28, | |
| "model_type": "dimple", | |
| "mrope_section": [ | |
| 16, | |
| 24, | |
| 24 | |
| ], | |
| "num_attention_heads": 28, | |
| "num_hidden_layers": 28, | |
| "num_key_value_heads": 4, | |
| "pad_token_id": 151643, | |
| "rms_norm_eps": 1e-06, | |
| "rope_scaling": null, | |
| "rope_theta": 1000000.0, | |
| "sliding_window": null, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.46.2", | |
| "use_cache": false, | |
| "use_mrope": false, | |
| "use_sliding_window": false, | |
| "video_token_id": 151656, | |
| "vision_config": { | |
| "in_chans": 3, | |
| "model_type": "dimple", | |
| "spatial_patch_size": 14 | |
| }, | |
| "vision_end_token_id": 151653, | |
| "vision_start_token_id": 151652, | |
| "vision_token_id": 151654, | |
| "vocab_size": 152064 | |
| } | |