OpenGVLab
/

InternVL-Chat-V1-2

@@ -10,13 +10,19 @@ datasets:
 pipeline_tag: visual-question-answering
 ---
-# Model Card for InternVL-Chat-Chinese-V1.2
-## What is InternVL?
-\[[Paper](https://arxiv.org/abs/2312.14238)\]  \[[GitHub](https://github.com/OpenGVLab/InternVL)\] \[[Chat Demo](https://internvl.opengvlab.com/)\]
-InternVL scales up the ViT to _**6B parameters**_ and aligns it with LLM.
 ## InternVL-Chat-V1.2 Blog
@@ -42,20 +48,20 @@ For more details about data preparation, please see [here](https://github.com/Op
 \* Proprietary Model
 | name               | image size | MMMU<br>(val) | MMMU<br>(test) | MathVista<br>(testmini) | MMB<br>(test) | MMB−CN<br>(test) | MMVP | MME      | ScienceQA<br>(image) | POPE | TextVQA<br>(val) | SEEDv1<br>(image) | VizWiz<br>(test) | GQA<br>(test) |
-| ------------------ | ---------- | ------------- | -------------- | ----------------------- | ------------- | ---------------- | ---- | -------- | -------------------- | ---- | ------- | ----------------- | ---------------- | ------------- |
-| GPT−4V\*           | unknown    | 56.8          | 55.7           | 49.9                    | 77.0          | 74.4             | 38.7 | 1409/517 | -                    | -    | 78.0    | 71.6              | -                | -             |
-| Gemini Ultra\*     | unknown    | 59.4          | -              | 53.0                    | -             | -                | -    | -        | -                    | -    | 82.3    | -                 | -                | -             |
-| Gemini Pro\*       | unknown    | 47.9          | -              | 45.2                    | 73.6          | 74.3             | 40.7 | 1497/437 | -                    | -    | 74.6    | 70.7              | -                | -             |
-| Qwen−VL−Plus\*     | unknown    | 45.2          | 40.8           | 43.3                    | 67.0          | 70.7             | -    | 1681/502 | -                    | -    | 78.9    | 65.7              | -                | -             |
-| Qwen−VL−Max\*      | unknown    | 51.4          | 46.8           | 51.0                    | 77.6          | 75.7             | -    | -        | -                    | -    | 79.5    | -                 | -                | -             |
-|                    |            |               |                |                         |               |                  |      |          |                      |      |         |                   |                  |               |
-| LLaVA−NEXT−34B     | 672x672    | 51.1          | 44.7           | 46.5                    | 79.3          | 79.0             | -    | 1631/397 | 81.8                 | 87.7 | 69.5    | 75.9              | 63.8             | 67.1          |
-| InternVL−Chat−V1.2 | 448x448    | 51.6          | 46.2           | 47.7                    | 82.2          | 81.2             | 56.7 | 1672/509 | 83.3                 | 88.0 | 69.7    | 75.6              | 60.0             | 64.0          |
-- MMBench results are collected from the [leaderboard](https://mmbench.opencompass.org.cn/leaderboard).
 - In most benchmarks, InternVL-Chat-V1.2 achieves better performance than LLaVA-NeXT-34B.
-### Training (SFT)
 We provide [slurm scripts](https://github.com/OpenGVLab/InternVL/tree/main/internvl_chat/shell/hermes2_yi34b/internvl_chat_v1_2_hermes2_yi34b_448_finetune.sh) for multi-node multi-GPU training. You can use either 32 or 64 GPUs to train this model. If you use 64 GPUs, training will take approximately 18 hours.
@@ -69,32 +75,28 @@ The hyperparameters used for finetuning are listed in the following table.
 ## Model Details
-- **Model Type:** vision large language model, multimodal chatbot
 - **Model Stats:**
   - Architecture: [InternViT-6B-448px-V1-2](https://huggingface.co/OpenGVLab/InternViT-6B-448px-V1-2) + MLP + [Nous-Hermes-2-Yi-34B](https://huggingface.co/NousResearch/Nous-Hermes-2-Yi-34B)
   - Params: 40B
-  - Image size: 448 x 448
-  - Number of visual tokens: 256
 - **Training Strategy:**
   - Pretraining Stage
     - Learnable Component: MLP
     - Data: Trained on 8192x4800=39.3M samples, including COYO, LAION, CC12M, CC3M, SBU, Wukong, GRIT, Objects365, OpenImages, and OCR data.
     - Note: In this stage, we load the pretrained weights of [InternViT-6B-448px-V1-2](https://huggingface.co/OpenGVLab/InternViT-6B-448px-V1-2). Moreover, in order to reduce the number of visual tokens, we use a pixel shuffle to reduce 1024 tokens to 256 tokens.
-  - SFT Stage
     - Learnable Component: ViT + MLP + LLM
-    - Data: A simplified, fully open-source dataset, containing approximately 1 million samples.
 ## Model Usage
-We provide a minimum code example to run InternVL-Chat using only the `transformers` library.
 You also can use our [online demo](https://internvl.opengvlab.com/) for a quick experience of this model.
-Note: If you meet this error `ImportError: This modeling file requires the following packages that were not found in your environment: fastchat`, please run `pip install fschat`.
 ```python
 import torch
 from PIL import Image
@@ -145,7 +147,6 @@ response, history = model.chat(tokenizer, pixel_values, question, generation_con
 print(question, response)
 ```
 ## Citation
 If you find this project useful in your research, please consider citing:

 pipeline_tag: visual-question-answering
 ---
+# Model Card for InternVL-Chat-V1.2
+<img src="https://cdn-uploads.huggingface.co/production/uploads/64119264f0f81eb569e0d569/Sx8dq7ReqSLOgvA_oTmXL.webp" alt="Image Description" width="300" height="300">
+\[[Paper](https://arxiv.org/abs/2312.14238)\]  \[[GitHub](https://github.com/OpenGVLab/InternVL)\] \[[Chat Demo](https://internvl.opengvlab.com/)\] \[[中文解读](https://zhuanlan.zhihu.com/p/675877376)]
+| Model                   | Date       | Download                                                                             | Note                               |
+| ----------------------- | ---------- | ------------------------------------------------------------------------------------ | ---------------------------------- |
+| InternVL-Chat-V1.5      | 2024.04.18 | 🤗 [HF link](https://huggingface.co/OpenGVLab/InternVL-Chat-V1-5)                    | support 4K image; super strong OCR; Approaching the performance of GPT-4V and Gemini Pro on various benchmarks like MMMU, DocVQA, ChartQA, MathVista, etc. (🔥new)|
+| InternVL-Chat-V1.2-Plus | 2024.02.21 | 🤗 [HF link](https://huggingface.co/OpenGVLab/InternVL-Chat-Chinese-V1-2-Plus)       | more SFT data and stronger  |
+| InternVL-Chat-V1.2      | 2024.02.11 | 🤗 [HF link](https://huggingface.co/OpenGVLab/InternVL-Chat-Chinese-V1-2)            | scaling up LLM to 34B       |
+| InternVL-Chat-V1.1      | 2024.01.24 | 🤗 [HF link](https://huggingface.co/OpenGVLab/InternVL-Chat-Chinese-V1-1)            | support Chinese and stronger OCR   |
 ## InternVL-Chat-V1.2 Blog
 \* Proprietary Model
 | name               | image size | MMMU<br>(val) | MMMU<br>(test) | MathVista<br>(testmini) | MMB<br>(test) | MMB−CN<br>(test) | MMVP | MME      | ScienceQA<br>(image) | POPE | TextVQA<br>(val) | SEEDv1<br>(image) | VizWiz<br>(test) | GQA<br>(test) |
+| ------------------ | ---------- | ------------- | -------------- | ----------------------- | ------------- | ---------------- | ---- | -------- | -------------------- | ---- | ---------------- | ----------------- | ---------------- | ------------- |
+| GPT−4V\*           | unknown    | 56.8          | 55.7           | 49.9                    | 77.0          | 74.4             | 38.7 | 1409/517 | -                    | -    | 78.0             | 71.6              | -                | -             |
+| Gemini Ultra\*     | unknown    | 59.4          | -              | 53.0                    | -             | -                | -    | -        | -                    | -    | 82.3             | -                 | -                | -             |
+| Gemini Pro\*       | unknown    | 47.9          | -              | 45.2                    | 73.6          | 74.3             | 40.7 | 1497/437 | -                    | -    | 74.6             | 70.7              | -                | -             |
+| Qwen−VL−Plus\*     | unknown    | 45.2          | 40.8           | 43.3                    | 67.0          | 70.7             | -    | 1681/502 | -                    | -    | 78.9             | 65.7              | -                | -             |
+| Qwen−VL−Max\*      | unknown    | 51.4          | 46.8           | 51.0                    | 77.6          | 75.7             | -    | -        | -                    | -    | 79.5             | -                 | -                | -             |
+|                    |            |               |                |                         |               |                  |      |          |                      |      |                  |                   |                  |               |
+| LLaVA−NEXT−34B     | 672x672    | 51.1          | 44.7           | 46.5                    | 79.3          | 79.0             | -    | 1631/397 | 81.8                 | 87.7 | 69.5             | 75.9              | 63.8             | 67.1          |
+| InternVL−Chat−V1.2 | 448x448    | 51.6          | 46.2           | 47.7                    | 82.2          | 81.2             | 56.7 | 1687/489 | 83.3                 | 88.0 | 72.5             | 75.6              | 60.0             | 64.0          |
 - In most benchmarks, InternVL-Chat-V1.2 achieves better performance than LLaVA-NeXT-34B.
+- Update (2024-04-21): We have fixed a bug in the evaluation code, and the TextVQA result has been corrected to 72.5.
+### Training (Supervised Finetuning)
 We provide [slurm scripts](https://github.com/OpenGVLab/InternVL/tree/main/internvl_chat/shell/hermes2_yi34b/internvl_chat_v1_2_hermes2_yi34b_448_finetune.sh) for multi-node multi-GPU training. You can use either 32 or 64 GPUs to train this model. If you use 64 GPUs, training will take approximately 18 hours.
 ## Model Details
+- **Model Type:** multimodal large language model (MLLM)
 - **Model Stats:**
   - Architecture: [InternViT-6B-448px-V1-2](https://huggingface.co/OpenGVLab/InternViT-6B-448px-V1-2) + MLP + [Nous-Hermes-2-Yi-34B](https://huggingface.co/NousResearch/Nous-Hermes-2-Yi-34B)
+  - Image size: 448 x 448 (256 tokens)
   - Params: 40B
 - **Training Strategy:**
   - Pretraining Stage
     - Learnable Component: MLP
     - Data: Trained on 8192x4800=39.3M samples, including COYO, LAION, CC12M, CC3M, SBU, Wukong, GRIT, Objects365, OpenImages, and OCR data.
     - Note: In this stage, we load the pretrained weights of [InternViT-6B-448px-V1-2](https://huggingface.co/OpenGVLab/InternViT-6B-448px-V1-2). Moreover, in order to reduce the number of visual tokens, we use a pixel shuffle to reduce 1024 tokens to 256 tokens.
+  - Supervised Finetuning Stage
     - Learnable Component: ViT + MLP + LLM
+    - Data: A simplified, fully open-source dataset, containing approximately 1.2 million samples.
 ## Model Usage
+We provide an example code to run InternVL-Chat-V1.2 using `transformers`.
 You also can use our [online demo](https://internvl.opengvlab.com/) for a quick experience of this model.
 ```python
 import torch
 from PIL import Image
 print(question, response)
 ```
 ## Citation
 If you find this project useful in your research, please consider citing: