Image-Text-to-Text
Transformers
Safetensors
English
internvl_chat
feature-extraction
mathematics
reasoning
multi-modal-qa
math-qa
figure-qa
geometry-qa
math-word-problem
textbook-qa
vqa
geometry-diagram
synthetic-scene
chart
plot
scientific-figure
table
function-plot
abstract-scene
puzzle-test
document-image
science
conversational
custom_code
| { | |
| "_commit_hash": null, | |
| "_name_or_path": "./pretrained/Mini-InternVL-Chat-2B-V1-5", | |
| "architectures": [ | |
| "InternVLChatModel" | |
| ], | |
| "auto_map": { | |
| "AutoConfig": "configuration_internvl_chat.InternVLChatConfig", | |
| "AutoModel": "modeling_internvl_chat.InternVLChatModel", | |
| "AutoModelForCausalLM": "modeling_internvl_chat.InternVLChatModel" | |
| }, | |
| "downsample_ratio": 0.5, | |
| "dynamic_image_size": true, | |
| "force_image_size": 448, | |
| "llm_config": { | |
| "_name_or_path": "pretrained/internlm2-chat-1_8b", | |
| "add_cross_attention": false, | |
| "architectures": [ | |
| "InternLM2ForCausalLM" | |
| ], | |
| "attn_implementation": "flash_attention_2", | |
| "auto_map": { | |
| "AutoConfig": "configuration_internlm2.InternLM2Config", | |
| "AutoModel": "modeling_internlm2.InternLM2ForCausalLM", | |
| "AutoModelForCausalLM": "modeling_internlm2.InternLM2ForCausalLM" | |
| }, | |
| "bad_words_ids": null, | |
| "begin_suppress_tokens": null, | |
| "bias": false, | |
| "bos_token_id": 1, | |
| "chunk_size_feed_forward": 0, | |
| "cross_attention_hidden_size": null, | |
| "decoder_start_token_id": null, | |
| "diversity_penalty": 0.0, | |
| "do_sample": false, | |
| "early_stopping": false, | |
| "encoder_no_repeat_ngram_size": 0, | |
| "eos_token_id": 2, | |
| "exponential_decay_length_penalty": null, | |
| "finetuning_task": null, | |
| "forced_bos_token_id": null, | |
| "forced_eos_token_id": null, | |
| "hidden_act": "silu", | |
| "hidden_size": 2048, | |
| "id2label": { | |
| "0": "LABEL_0", | |
| "1": "LABEL_1" | |
| }, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 8192, | |
| "is_decoder": false, | |
| "is_encoder_decoder": false, | |
| "label2id": { | |
| "LABEL_0": 0, | |
| "LABEL_1": 1 | |
| }, | |
| "length_penalty": 1.0, | |
| "max_length": 20, | |
| "max_position_embeddings": 32768, | |
| "min_length": 0, | |
| "model_type": "internlm2", | |
| "no_repeat_ngram_size": 0, | |
| "num_attention_heads": 16, | |
| "num_beam_groups": 1, | |
| "num_beams": 1, | |
| "num_hidden_layers": 24, | |
| "num_key_value_heads": 8, | |
| "num_return_sequences": 1, | |
| "output_attentions": false, | |
| "output_hidden_states": false, | |
| "output_scores": false, | |
| "pad_token_id": 2, | |
| "prefix": null, | |
| "problem_type": null, | |
| "pruned_heads": {}, | |
| "remove_invalid_values": false, | |
| "repetition_penalty": 1.0, | |
| "return_dict": true, | |
| "return_dict_in_generate": false, | |
| "rms_norm_eps": 1e-05, | |
| "rope_scaling": { | |
| "factor": 3.0, | |
| "type": "dynamic" | |
| }, | |
| "rope_theta": 1000000, | |
| "sep_token_id": null, | |
| "suppress_tokens": null, | |
| "task_specific_params": null, | |
| "temperature": 1.0, | |
| "tf_legacy_loss": false, | |
| "tie_encoder_decoder": false, | |
| "tie_word_embeddings": false, | |
| "tokenizer_class": null, | |
| "top_k": 50, | |
| "top_p": 1.0, | |
| "torch_dtype": "bfloat16", | |
| "torchscript": false, | |
| "transformers_version": "4.39.0", | |
| "typical_p": 1.0, | |
| "use_bfloat16": false, | |
| "use_cache": false, | |
| "vocab_size": 92557 | |
| }, | |
| "max_dynamic_patch": 12, | |
| "min_dynamic_patch": 1, | |
| "model_type": "internvl_chat", | |
| "pad2square": false, | |
| "ps_version": "v2", | |
| "select_layer": -1, | |
| "template": "internlm2-chat", | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": null, | |
| "use_backbone_lora": 0, | |
| "use_llm_lora": 0, | |
| "use_thumbnail": true, | |
| "vision_config": { | |
| "_name_or_path": "OpenGVLab/InternViT-300M-448px", | |
| "add_cross_attention": false, | |
| "architectures": [ | |
| "InternVisionModel" | |
| ], | |
| "attention_dropout": 0.0, | |
| "auto_map": { | |
| "AutoConfig": "configuration_intern_vit.InternVisionConfig", | |
| "AutoModel": "modeling_intern_vit.InternVisionModel" | |
| }, | |
| "bad_words_ids": null, | |
| "begin_suppress_tokens": null, | |
| "bos_token_id": null, | |
| "chunk_size_feed_forward": 0, | |
| "cross_attention_hidden_size": null, | |
| "decoder_start_token_id": null, | |
| "diversity_penalty": 0.0, | |
| "do_sample": false, | |
| "drop_path_rate": 0.1, | |
| "dropout": 0.0, | |
| "early_stopping": false, | |
| "encoder_no_repeat_ngram_size": 0, | |
| "eos_token_id": null, | |
| "exponential_decay_length_penalty": null, | |
| "finetuning_task": null, | |
| "forced_bos_token_id": null, | |
| "forced_eos_token_id": null, | |
| "hidden_act": "gelu", | |
| "hidden_size": 1024, | |
| "id2label": { | |
| "0": "LABEL_0", | |
| "1": "LABEL_1" | |
| }, | |
| "image_size": 448, | |
| "initializer_factor": 1.0, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 4096, | |
| "is_decoder": false, | |
| "is_encoder_decoder": false, | |
| "label2id": { | |
| "LABEL_0": 0, | |
| "LABEL_1": 1 | |
| }, | |
| "layer_norm_eps": 1e-06, | |
| "length_penalty": 1.0, | |
| "max_length": 20, | |
| "min_length": 0, | |
| "model_type": "intern_vit_6b", | |
| "no_repeat_ngram_size": 0, | |
| "norm_type": "layer_norm", | |
| "num_attention_heads": 16, | |
| "num_beam_groups": 1, | |
| "num_beams": 1, | |
| "num_channels": 3, | |
| "num_hidden_layers": 24, | |
| "num_return_sequences": 1, | |
| "output_attentions": false, | |
| "output_hidden_states": false, | |
| "output_scores": false, | |
| "pad_token_id": null, | |
| "patch_size": 14, | |
| "prefix": null, | |
| "problem_type": null, | |
| "pruned_heads": {}, | |
| "qk_normalization": false, | |
| "qkv_bias": true, | |
| "remove_invalid_values": false, | |
| "repetition_penalty": 1.0, | |
| "return_dict": true, | |
| "return_dict_in_generate": false, | |
| "sep_token_id": null, | |
| "suppress_tokens": null, | |
| "task_specific_params": null, | |
| "temperature": 1.0, | |
| "tf_legacy_loss": false, | |
| "tie_encoder_decoder": false, | |
| "tie_word_embeddings": true, | |
| "tokenizer_class": null, | |
| "top_k": 50, | |
| "top_p": 1.0, | |
| "torch_dtype": "bfloat16", | |
| "torchscript": false, | |
| "transformers_version": "4.39.0", | |
| "typical_p": 1.0, | |
| "use_bfloat16": true, | |
| "use_flash_attn": true | |
| } | |
| } | |