MathLLMs/MathCoder-VL-2B

1{2  "_commit_hash": null,3  "_name_or_path": "./pretrained/Mini-InternVL-Chat-2B-V1-5",4  "architectures": [5    "InternVLChatModel"6  ],7  "auto_map": {8    "AutoConfig": "configuration_internvl_chat.InternVLChatConfig",9    "AutoModel": "modeling_internvl_chat.InternVLChatModel",10    "AutoModelForCausalLM": "modeling_internvl_chat.InternVLChatModel"11  },12  "downsample_ratio": 0.5,13  "dynamic_image_size": true,14  "force_image_size": 448,15  "llm_config": {16    "_name_or_path": "pretrained/internlm2-chat-1_8b",17    "add_cross_attention": false,18    "architectures": [19      "InternLM2ForCausalLM"20    ],21    "attn_implementation": "flash_attention_2",22    "auto_map": {23      "AutoConfig": "configuration_internlm2.InternLM2Config",24      "AutoModel": "modeling_internlm2.InternLM2ForCausalLM",25      "AutoModelForCausalLM": "modeling_internlm2.InternLM2ForCausalLM"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": 2048,45    "id2label": {46      "0": "LABEL_0",47      "1": "LABEL_1"48    },49    "initializer_range": 0.02,50    "intermediate_size": 8192,51    "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": 16,64    "num_beam_groups": 1,65    "num_beams": 1,66    "num_hidden_layers": 24,67    "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    "problem_type": null,75    "pruned_heads": {},76    "remove_invalid_values": false,77    "repetition_penalty": 1.0,78    "return_dict": true,79    "return_dict_in_generate": false,80    "rms_norm_eps": 1e-05,81    "rope_scaling": {82      "factor": 3.0,83      "type": "dynamic"84    },85    "rope_theta": 1000000,86    "sep_token_id": 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": "4.39.0",99    "typical_p": 1.0,100    "use_bfloat16": false,101    "use_cache": false,102    "vocab_size": 92557103  },104  "max_dynamic_patch": 12,105  "min_dynamic_patch": 1,106  "model_type": "internvl_chat",107  "pad2square": false,108  "ps_version": "v2",109  "select_layer": -1,110  "template": "internlm2-chat",111  "torch_dtype": "bfloat16",112  "transformers_version": null,113  "use_backbone_lora": 0,114  "use_llm_lora": 0,115  "use_thumbnail": true,116  "vision_config": {117    "_name_or_path": "OpenGVLab/InternViT-300M-448px",118    "add_cross_attention": false,119    "architectures": [120      "InternVisionModel"121    ],122    "attention_dropout": 0.0,123    "auto_map": {124      "AutoConfig": "configuration_intern_vit.InternVisionConfig",125      "AutoModel": "modeling_intern_vit.InternVisionModel"126    },127    "bad_words_ids": null,128    "begin_suppress_tokens": null,129    "bos_token_id": null,130    "chunk_size_feed_forward": 0,131    "cross_attention_hidden_size": null,132    "decoder_start_token_id": null,133    "diversity_penalty": 0.0,134    "do_sample": false,135    "drop_path_rate": 0.1,136    "dropout": 0.0,137    "early_stopping": false,138    "encoder_no_repeat_ngram_size": 0,139    "eos_token_id": null,140    "exponential_decay_length_penalty": null,141    "finetuning_task": null,142    "forced_bos_token_id": null,143    "forced_eos_token_id": null,144    "hidden_act": "gelu",145    "hidden_size": 1024,146    "id2label": {147      "0": "LABEL_0",148      "1": "LABEL_1"149    },150    "image_size": 448,151    "initializer_factor": 1.0,152    "initializer_range": 0.02,153    "intermediate_size": 4096,154    "is_decoder": false,155    "is_encoder_decoder": false,156    "label2id": {157      "LABEL_0": 0,158      "LABEL_1": 1159    },160    "layer_norm_eps": 1e-06,161    "length_penalty": 1.0,162    "max_length": 20,163    "min_length": 0,164    "model_type": "intern_vit_6b",165    "no_repeat_ngram_size": 0,166    "norm_type": "layer_norm",167    "num_attention_heads": 16,168    "num_beam_groups": 1,169    "num_beams": 1,170    "num_channels": 3,171    "num_hidden_layers": 24,172    "num_return_sequences": 1,173    "output_attentions": false,174    "output_hidden_states": false,175    "output_scores": false,176    "pad_token_id": null,177    "patch_size": 14,178    "prefix": null,179    "problem_type": null,180    "pruned_heads": {},181    "qk_normalization": false,182    "qkv_bias": true,183    "remove_invalid_values": false,184    "repetition_penalty": 1.0,185    "return_dict": true,186    "return_dict_in_generate": false,187    "sep_token_id": null,188    "suppress_tokens": null,189    "task_specific_params": null,190    "temperature": 1.0,191    "tf_legacy_loss": false,192    "tie_encoder_decoder": false,193    "tie_word_embeddings": true,194    "tokenizer_class": null,195    "top_k": 50,196    "top_p": 1.0,197    "torch_dtype": "bfloat16",198    "torchscript": false,199    "transformers_version": "4.39.0",200    "typical_p": 1.0,201    "use_bfloat16": true,202    "use_flash_attn": true203  }204}205