OpenGVLab/InternVL3_5-8B-Pretrained

1{2  "_commit_hash": null,3  "architectures": [4    "InternVLChatModel"5  ],6  "auto_map": {7    "AutoConfig": "configuration_internvl_chat.InternVLChatConfig",8    "AutoModel": "modeling_internvl_chat.InternVLChatModel",9    "AutoModelForCausalLM": "modeling_internvl_chat.InternVLChatModel"10  },11  "downsample_ratio": 0.5,12  "dynamic_image_size": true,13  "force_image_size": 448,14  "llm_config": {15    "_attn_implementation_autoset": false,16    "_name_or_path": "/root/codespace/checkpoints/Qwen3-8B",17    "add_cross_attention": false,18    "architectures": [19      "Qwen3ForCausalLM"20    ],21    "attention_bias": false,22    "attention_dropout": 0.0,23    "attn_implementation": "flash_attention_2",24    "bad_words_ids": null,25    "begin_suppress_tokens": null,26    "bos_token_id": 151643,27    "chunk_size_feed_forward": 0,28    "cross_attention_hidden_size": null,29    "debug": false,30    "decoder_start_token_id": null,31    "diversity_penalty": 0.0,32    "do_sample": false,33    "early_stopping": false,34    "encoder_no_repeat_ngram_size": 0,35    "eos_token_id": 151645,36    "ep_size": 1,37    "exponential_decay_length_penalty": null,38    "finetuning_task": null,39    "forced_bos_token_id": null,40    "forced_eos_token_id": null,41    "head_dim": 128,42    "hidden_act": "silu",43    "hidden_size": 4096,44    "id2label": {45      "0": "LABEL_0",46      "1": "LABEL_1"47    },48    "initializer_range": 0.02,49    "intermediate_size": 12288,50    "is_decoder": false,51    "is_encoder_decoder": false,52    "label2id": {53      "LABEL_0": 0,54      "LABEL_1": 155    },56    "length_penalty": 1.0,57    "max_length": 20,58    "max_position_embeddings": 40960,59    "max_window_layers": 36,60    "micro_forward": false,61    "min_length": 0,62    "model_type": "qwen3",63    "no_repeat_ngram_size": 0,64    "num_attention_heads": 32,65    "num_beam_groups": 1,66    "num_beams": 1,67    "num_hidden_layers": 36,68    "num_key_value_heads": 8,69    "num_return_sequences": 1,70    "output_attentions": false,71    "output_hidden_states": false,72    "output_scores": false,73    "pad_token_id": null,74    "prefix": null,75    "problem_type": null,76    "pruned_heads": {},77    "remove_invalid_values": false,78    "repetition_penalty": 1.0,79    "return_dict": true,80    "return_dict_in_generate": false,81    "rms_norm_eps": 1e-06,82    "rope_scaling": null,83    "rope_theta": 1000000,84    "sep_token_id": null,85    "skip_checkpoint": false,86    "sliding_window": null,87    "suppress_tokens": null,88    "task_specific_params": null,89    "temperature": 1.0,90    "tf_legacy_loss": false,91    "tie_encoder_decoder": false,92    "tie_word_embeddings": false,93    "tokenizer_class": null,94    "top_k": 50,95    "top_p": 1.0,96    "torch_dtype": "bfloat16",97    "torchscript": false,98    "transformers_version": "4.51.1",99    "typical_p": 1.0,100    "use_bfloat16": false,101    "use_cache": false,102    "use_deepep": true,103    "use_sliding_window": false,104    "vocab_size": 151936105  },106  "max_dynamic_patch": 12,107  "min_dynamic_patch": 1,108  "model_type": "internvl_chat",109  "pad2square": false,110  "ps_version": "v2",111  "select_layer": -1,112  "template": "internvl2_5",113  "tie_word_embeddings": false,114  "torch_dtype": "bfloat16",115  "transformers_version": null,116  "use_backbone_lora": 0,117  "use_llm_lora": 0,118  "use_thumbnail": true,119  "vision_config": {120    "_attn_implementation_autoset": true,121    "_name_or_path": "",122    "add_cross_attention": false,123    "architectures": [124      "InternVisionModel"125    ],126    "attention_dropout": 0.0,127    "auto_map": {128      "AutoConfig": "configuration_intern_vit.InternVisionConfig",129      "AutoModel": "modeling_intern_vit.InternVisionModel"130    },131    "bad_words_ids": null,132    "begin_suppress_tokens": null,133    "bos_token_id": null,134    "chunk_size_feed_forward": 0,135    "cross_attention_hidden_size": null,136    "decoder_start_token_id": null,137    "diversity_penalty": 0.0,138    "do_sample": false,139    "drop_path_rate": 0.1,140    "dropout": 0.0,141    "early_stopping": false,142    "encoder_no_repeat_ngram_size": 0,143    "eos_token_id": null,144    "exponential_decay_length_penalty": null,145    "finetuning_task": null,146    "forced_bos_token_id": null,147    "forced_eos_token_id": null,148    "hidden_act": "gelu",149    "hidden_size": 1024,150    "id2label": {151      "0": "LABEL_0",152      "1": "LABEL_1"153    },154    "image_size": 448,155    "initializer_factor": 1.0,156    "initializer_range": 0.02,157    "intermediate_size": 4096,158    "is_decoder": false,159    "is_encoder_decoder": false,160    "label2id": {161      "LABEL_0": 0,162      "LABEL_1": 1163    },164    "layer_norm_eps": 1e-06,165    "length_penalty": 1.0,166    "max_length": 20,167    "min_length": 0,168    "model_type": "intern_vit_6b",169    "no_repeat_ngram_size": 0,170    "norm_type": "layer_norm",171    "num_attention_heads": 16,172    "num_beam_groups": 1,173    "num_beams": 1,174    "num_channels": 3,175    "num_hidden_layers": 24,176    "num_return_sequences": 1,177    "output_attentions": false,178    "output_hidden_states": false,179    "output_scores": false,180    "pad_token_id": null,181    "patch_size": 14,182    "prefix": null,183    "problem_type": null,184    "pruned_heads": {},185    "qk_normalization": false,186    "qkv_bias": true,187    "remove_invalid_values": false,188    "repetition_penalty": 1.0,189    "return_dict": true,190    "return_dict_in_generate": false,191    "sep_token_id": null,192    "suppress_tokens": null,193    "task_specific_params": null,194    "temperature": 1.0,195    "tf_legacy_loss": false,196    "tie_encoder_decoder": false,197    "tie_word_embeddings": true,198    "tokenizer_class": null,199    "top_k": 50,200    "top_p": 1.0,201    "torch_dtype": "bfloat16",202    "torchscript": false,203    "transformers_version": "4.51.1",204    "typical_p": 1.0,205    "use_bfloat16": false,206    "use_fa3": true,207    "use_flash_attn": true208  }209}