OpenGVLab/InternVL3_5-30B-A3B-Instruct

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/Qwen3-30B-A3B",17    "add_cross_attention": false,18    "architectures": [19      "Qwen3MoeForCausalLM"20    ],21    "attention_bias": false,22    "attention_dropout": 0.0,23    "bad_words_ids": null,24    "begin_suppress_tokens": null,25    "bos_token_id": 151643,26    "chunk_size_feed_forward": 0,27    "cross_attention_hidden_size": null,28    "decoder_sparse_step": 1,29    "decoder_start_token_id": null,30    "diversity_penalty": 0.0,31    "do_sample": false,32    "early_stopping": false,33    "encoder_no_repeat_ngram_size": 0,34    "eos_token_id": 151645,35    "exponential_decay_length_penalty": null,36    "finetuning_task": null,37    "forced_bos_token_id": null,38    "forced_eos_token_id": null,39    "head_dim": 128,40    "hidden_act": "silu",41    "hidden_size": 2048,42    "id2label": {43      "0": "LABEL_0",44      "1": "LABEL_1"45    },46    "initializer_range": 0.02,47    "intermediate_size": 6144,48    "is_decoder": false,49    "is_encoder_decoder": false,50    "label2id": {51      "LABEL_0": 0,52      "LABEL_1": 153    },54    "length_penalty": 1.0,55    "max_length": 20,56    "max_position_embeddings": 40960,57    "max_window_layers": 48,58    "min_length": 0,59    "mlp_only_layers": [],60    "model_type": "qwen3_moe",61    "moe_intermediate_size": 768,62    "no_repeat_ngram_size": 0,63    "norm_topk_prob": true,64    "num_attention_heads": 32,65    "num_beam_groups": 1,66    "num_beams": 1,67    "num_experts": 128,68    "num_experts_per_tok": 8,69    "num_hidden_layers": 48,70    "num_key_value_heads": 4,71    "num_return_sequences": 1,72    "output_attentions": false,73    "output_hidden_states": false,74    "output_router_logits": false,75    "output_scores": false,76    "pad_token_id": null,77    "prefix": null,78    "problem_type": null,79    "pruned_heads": {},80    "remove_invalid_values": false,81    "repetition_penalty": 1.0,82    "return_dict": true,83    "return_dict_in_generate": false,84    "rms_norm_eps": 1e-06,85    "rope_scaling": null,86    "rope_theta": 1000000.0,87    "router_aux_loss_coef": 0.001,88    "sep_token_id": null,89    "sliding_window": null,90    "suppress_tokens": null,91    "task_specific_params": null,92    "temperature": 1.0,93    "tf_legacy_loss": false,94    "tie_encoder_decoder": false,95    "tie_word_embeddings": false,96    "tokenizer_class": null,97    "top_k": 50,98    "top_p": 1.0,99    "torch_dtype": "bfloat16",100    "torchscript": false,101    "transformers_version": "4.51.1",102    "typical_p": 1.0,103    "use_bfloat16": false,104    "use_cache": true,105    "use_sliding_window": false,106    "vocab_size": 151936107  },108  "max_dynamic_patch": 12,109  "min_dynamic_patch": 1,110  "model_type": "internvl_chat",111  "pad2square": false,112  "ps_version": "v2",113  "select_layer": -1,114  "template": "internvl2_5",115  "tie_word_embeddings": false,116  "torch_dtype": "bfloat16",117  "transformers_version": null,118  "use_backbone_lora": 0,119  "use_llm_lora": 0,120  "use_thumbnail": true,121  "vision_config": {122    "_attn_implementation_autoset": false,123    "_name_or_path": "",124    "add_cross_attention": false,125    "architectures": [126      "InternVisionModel"127    ],128    "attention_dropout": 0.0,129    "auto_map": {130      "AutoConfig": "configuration_intern_vit.InternVisionConfig",131      "AutoModel": "modeling_intern_vit.InternVisionModel"132    },133    "bad_words_ids": null,134    "begin_suppress_tokens": null,135    "bos_token_id": null,136    "chunk_size_feed_forward": 0,137    "cross_attention_hidden_size": null,138    "decoder_start_token_id": null,139    "diversity_penalty": 0.0,140    "do_sample": false,141    "drop_path_rate": 0.1,142    "dropout": 0.0,143    "early_stopping": false,144    "encoder_no_repeat_ngram_size": 0,145    "eos_token_id": null,146    "exponential_decay_length_penalty": null,147    "finetuning_task": null,148    "forced_bos_token_id": null,149    "forced_eos_token_id": null,150    "hidden_act": "gelu",151    "hidden_size": 1024,152    "id2label": {153      "0": "LABEL_0",154      "1": "LABEL_1"155    },156    "image_size": 448,157    "initializer_factor": 1.0,158    "initializer_range": 0.02,159    "intermediate_size": 4096,160    "is_decoder": false,161    "is_encoder_decoder": false,162    "label2id": {163      "LABEL_0": 0,164      "LABEL_1": 1165    },166    "layer_norm_eps": 1e-06,167    "length_penalty": 1.0,168    "max_length": 20,169    "min_length": 0,170    "model_type": "intern_vit_6b",171    "no_repeat_ngram_size": 0,172    "norm_type": "layer_norm",173    "num_attention_heads": 16,174    "num_beam_groups": 1,175    "num_beams": 1,176    "num_channels": 3,177    "num_hidden_layers": 24,178    "num_return_sequences": 1,179    "output_attentions": false,180    "output_hidden_states": false,181    "output_scores": false,182    "pad_token_id": null,183    "patch_size": 14,184    "prefix": null,185    "problem_type": null,186    "pruned_heads": {},187    "qk_normalization": false,188    "qkv_bias": true,189    "remove_invalid_values": false,190    "repetition_penalty": 1.0,191    "return_dict": true,192    "return_dict_in_generate": false,193    "sep_token_id": null,194    "suppress_tokens": null,195    "task_specific_params": null,196    "temperature": 1.0,197    "tf_legacy_loss": false,198    "tie_encoder_decoder": false,199    "tie_word_embeddings": true,200    "tokenizer_class": null,201    "top_k": 50,202    "top_p": 1.0,203    "torch_dtype": "bfloat16",204    "torchscript": false,205    "transformers_version": "4.51.1",206    "typical_p": 1.0,207    "use_bfloat16": false,208    "use_flash_attn": true209  }210}211