CoolFace
Modelpublic

OpenGVLab/InternVL2_5-26B

sourceHugging Facemitupdated 2y agoView on Hugging Face
33likes1.5kdownloads
config.json146 linesDownload Raw Back to root
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    "_name_or_path": "internlm/internlm2_5-20b-chat",16    "add_cross_attention": false,17    "architectures": [18      "InternLM2ForCausalLM"19    ],20    "attn_implementation": "flash_attention_2",21    "auto_map": {22      "AutoConfig": "configuration_internlm2.InternLM2Config",23      "AutoModel": "modeling_internlm2.InternLM2ForCausalLM",24      "AutoModelForCausalLM": "modeling_internlm2.InternLM2ForCausalLM",25      "AutoModelForSequenceClassification": "modeling_internlm2.InternLM2ForSequenceClassification"26    },27    "bad_words_ids": null,28    "begin_suppress_tokens": null,29    "bias": false,30    "bos_token_id": 1,31    "chunk_size_feed_forward": 0,32    "cross_attention_hidden_size": null,33    "decoder_start_token_id": null,34    "diversity_penalty": 0.0,35    "do_sample": false,36    "early_stopping": false,37    "encoder_no_repeat_ngram_size": 0,38    "eos_token_id": 2,39    "exponential_decay_length_penalty": null,40    "finetuning_task": null,41    "forced_bos_token_id": null,42    "forced_eos_token_id": null,43    "hidden_act": "silu",44    "hidden_size": 6144,45    "id2label": {46      "0": "LABEL_0",47      "1": "LABEL_1"48    },49    "initializer_range": 0.02,50    "intermediate_size": 16384,51    "is_decoder": false,52    "is_encoder_decoder": false,53    "label2id": {54      "LABEL_0": 0,55      "LABEL_1": 156    },57    "length_penalty": 1.0,58    "max_length": 20,59    "max_position_embeddings": 32768,60    "min_length": 0,61    "model_type": "internlm2",62    "no_repeat_ngram_size": 0,63    "num_attention_heads": 48,64    "num_beam_groups": 1,65    "num_beams": 1,66    "num_hidden_layers": 48,67    "num_key_value_heads": 8,68    "num_return_sequences": 1,69    "output_attentions": false,70    "output_hidden_states": false,71    "output_scores": false,72    "pad_token_id": 2,73    "prefix": null,74    "pretraining_tp": 1,75    "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-05,82    "rope_scaling": {83      "factor": 2.5,84      "type": "dynamic"85    },86    "rope_theta": 50000000,87    "sep_token_id": null,88    "suppress_tokens": null,89    "task_specific_params": null,90    "temperature": 1.0,91    "tf_legacy_loss": false,92    "tie_encoder_decoder": false,93    "tie_word_embeddings": false,94    "tokenizer_class": null,95    "top_k": 50,96    "top_p": 1.0,97    "torch_dtype": "bfloat16",98    "torchscript": false,99    "transformers_version": "4.37.2",100    "typical_p": 1.0,101    "use_bfloat16": true,102    "use_cache": true,103    "vocab_size": 92553104  },105  "max_dynamic_patch": 12,106  "min_dynamic_patch": 1,107  "model_type": "internvl_chat",108  "ps_version": "v2",109  "select_layer": -1,110  "template": "internvl2_5",111  "torch_dtype": "bfloat16",112  "use_backbone_lora": 0,113  "use_llm_lora": 0,114  "use_thumbnail": true,115  "vision_config": {116    "architectures": [117      "InternVisionModel"118    ],119    "attention_dropout": 0.0,120    "drop_path_rate": 0.0,121    "dropout": 0.0,122    "hidden_act": "gelu",123    "hidden_size": 3200,124    "image_size": 448,125    "initializer_factor": 0.1,126    "initializer_range": 1e-10,127    "intermediate_size": 12800,128    "layer_norm_eps": 1e-06,129    "model_type": "intern_vit_6b",130    "norm_type": "rms_norm",131    "num_attention_heads": 25,132    "num_channels": 3,133    "num_hidden_layers": 45,134    "output_attentions": false,135    "output_hidden_states": false,136    "patch_size": 14,137    "qk_normalization": true,138    "qkv_bias": false,139    "return_dict": true,140    "torch_dtype": "bfloat16",141    "transformers_version": "4.37.2",142    "use_bfloat16": true,143    "use_flash_attn": true144  }145}146