Upload folder using huggingface_hub

README.md

@@ -9,7 +9,44 @@ pipeline_tag: visual-question-answering
 
 [\[🤗 HF Demo\]](https://huggingface.co/spaces/OpenGVLab/InternVL)  [\[🚀 Quick Start\]](#model-usage)  [\[📖 中文解读\]](https://zhuanlan.zhihu.com/p/675877376)
 
-## Model Usage
+## Introduction
+
+We are excited to announce the release of InternVL 2.0, the latest addition to the InternVL series of multimodal large language models. InternVL 2.0 features a variety of instruction-tuned models, ranging from 2 billion to 108 billion parameters. This repository contains the instruction-tuned InternVL2-2B model.
+
+Compared to the state-of-the-art open-source multimodal large language models, InternVL 2.0 surpasses most open-source models. It demonstrates competitive performance on par with proprietary commercial models across various capabilities, including document and chart comprehension, infographics QA, scene text understanding and OCR tasks, scientific and mathematical problem solving, as well as cultural understanding and integrated multimodal capabilities.
+
+InternVL 2.0 is trained with an 8k context window and utilizes training data consisting of long texts, multiple images, and videos, significantly improving its ability to handle these types of inputs compared to InternVL 1.5. For more details, please refer to our blog and GitHub.
+
+## Performance
+
+|         Benchmark         | PaliGemma-3B | Phi-3-Vision | Mini-InternVL-2B-1.5 | InternVL2-2B |
+| :-----------------------: | :----------: | :----------: | :------------------: | :----------: |
+|        Model Size         |     2.9B     |     4.2B     |         2.2B         |     2.2B     |
+|                           |              |              |                      |              |
+|   DocVQA<sub>test</sub>   |      -       |      -       |         85.0         |     TODO     |
+|  ChartQA<sub>test</sub>   |      -       |     81.4     |         74.8         |     76.2     |
+|  InfoVQA<sub>test</sub>   |      -       |      -       |         55.4         |     TODO     |
+|   TextVQA<sub>val</sub>   |     68.1     |     70.9     |         70.5         |     73.4     |
+|         OCRBench          |     614      |     639      |         654          |     784      |
+|     MME<sub>sum</sub>     |    1686.1    |    1508.0    |        1901.5        |    1876.8    |
+|        RealWorldQA        |     55.2     |     58.8     |         57.9         |     57.3     |
+|    AI2D<sub>test</sub>    |     68.3     |     76.7     |         69.8         |     74.1     |
+|    MMMU<sub>val</sub>     |     34.9     |     40.4     |         34.6         |     34.3     |
+| MMBench-EN<sub>test</sub> |     71.0     |     73.6     |         70.9         |     73.2     |
+| MMBench-CN<sub>test</sub> |     63.6     |      -       |         66.2         |     70.9     |
+|   CCBench<sub>dev</sub>   |     29.6     |     24.1     |         63.5         |     74.7     |
+| MMVet<sub>GPT4-0613</sub> |     33.1     |      -       |         39.3         |     44.6     |
+|        SEED-Image         |     69.6     |     70.9     |         69.8         |     71.6     |
+| HallBench<sub>avg.</sub>  |     32.2     |     39.0     |         37.5         |     37.9     |
+| MathVista<sub>mini</sub>  |     28.7     |     44.5     |         41.1         |     46.3     |
+
+- We simultaneously use InternVL and VLMEvalKit repositories for model evaluation. Specifically, the results reported for DocVQA, ChartQA, InfoVQA, TextVQA, MME, AI2D, MMBench, CCBench, MMVet, and SEED-Image were tested using the InternVL repository. MMMU, OCRBench, RealWorldQA, HallBench, and MathVista were evaluated using the VLMEvalKit.
+
+- Please note that evaluating the same model using different testing toolkits like InternVL and VLMEvalKit can result in slight differences, which is normal. Updates to code versions and variations in environment and hardware can also cause minor discrepancies in results.
+
+- It is important to mention that the MMVet scores we report are evaluated using GPT-4-0613 as the judge model. Different versions of GPT-4 can lead to significant variations in the scores for this dataset. For instance, using GPT-4-Turbo would result in significantly lower scores.
+
+## Quick Start
 
 We provide an example code to run InternVL2-2B using `transformers`.
 
@@ -203,4 +240,4 @@ If you find this project useful in your research, please consider citing:
   journal={arXiv preprint arXiv:2404.16821},
   year={2024}
 }
-```
+```

config.json

@@ -77,7 +77,10 @@
     "return_dict": true,
     "return_dict_in_generate": false,
     "rms_norm_eps": 1e-05,
-    "rope_scaling": null,
+    "rope_scaling": {
+      "factor": 2.0,
+      "type": "dynamic"
+    },
     "rope_theta": 1000000,
     "sep_token_id": null,
     "suppress_tokens": null,
@@ -88,7 +91,7 @@
     "tie_word_embeddings": false,
     "tokenizer_class": null,
     "top_k": 50,
-    "top_p": 1.0,
+    "top_p": null,
     "torch_dtype": "bfloat16",
     "torchscript": false,
     "transformers_version": "4.37.2",
@@ -183,7 +186,7 @@
     "tie_word_embeddings": true,
     "tokenizer_class": null,
     "top_k": 50,
-    "top_p": 1.0,
+    "top_p": null,
     "torch_dtype": "bfloat16",
     "torchscript": false,
     "transformers_version": "4.37.2",