[docs]: release InternLM2.5 1.8B and 20B (#780)

2024-08-05 16:45:23 +08:00 · 2024-08-05 16:45:23 +08:00 · ef74b41aca
parent feef5023b3
commit ef74b41aca
4 changed files with 120 additions and 2 deletions
--- a/README.md
+++ b/README.md
@ -46,6 +46,8 @@ InternLM2.5 series are released with the following features:

 ## News

+\[2024.08.01\] We release InternLM2.5-1.8B, InternLM2.5-1.8B-Chat, InternLM2.5-20B and InternLM2.5-20B-Chat. See [model zoo below](#model-zoo) for download or [model cards](./model_cards/) for more details.
+
 \[2024.07.19\] We release the InternLM2-Reward series of reward models in 1.8B, 7B and 20B sizes. See [model zoo below](#model-zoo) for download or [model cards](./model_cards/internlm2_reward.md) for more details.

 \[2024.07.03\] We release InternLM2.5-7B, InternLM2.5-7B-Chat and InternLM2.5-7B-Chat-1M. See [model zoo below](#model-zoo) for download or [model cards](./model_cards/) for more details.
@ -68,13 +70,17 @@ InternLM2.5 series are released with the following features:

 | Model                      | Transformers(HF)                           | ModelScope(HF)                           | OpenXLab(HF)                           | OpenXLab(Origin)                           | Release Date |
 | -------------------------- | ------------------------------------------ | ---------------------------------------- | -------------------------------------- | ------------------------------------------ | ------------ |
+| **InternLM2.5-1.8B**       | [🤗internlm2_5-1_8b](https://huggingface.co/internlm/internlm2_5-1_8b) | [<img src="./assets/modelscope_logo.png" width="20px" /> internlm2_5-1_8b](https://modelscope.cn/models/Shanghai_AI_Laboratory/internlm2_5-1_8b/summary) | [![Open in OpenXLab](https://cdn-static.openxlab.org.cn/header/openxlab_models.svg)](https://openxlab.org.cn/models/detail/OpenLMLab/internlm2_5-1_8b) | [![Open in OpenXLab](https://cdn-static.openxlab.org.cn/header/openxlab_models.svg)](https://openxlab.org.cn/models/detail/OpenLMLab/internlm2_5-1_8b-original) | 2024-08-05   |
+| **InternLM2.5-1.8B-Chat**  | [🤗internlm2_5-1_8b-chat](https://huggingface.co/internlm/internlm2_5-1_8b-chat) | [<img src="./assets/modelscope_logo.png" width="20px" /> internlm2_5-1_8b-chat](https://modelscope.cn/models/Shanghai_AI_Laboratory/internlm2_5-1_8b-chat/summary) | [![Open in OpenXLab](https://cdn-static.openxlab.org.cn/header/openxlab_models.svg)](https://openxlab.org.cn/models/detail/OpenLMLab/internlm2_5-1_8b-chat) | [![Open in OpenXLab](https://cdn-static.openxlab.org.cn/header/openxlab_models.svg)](https://openxlab.org.cn/models/detail/OpenLMLab/internlm2_5-1_8b-chat-original) | 2024-08-05   |
 | **InternLM2.5-7B**         | [🤗internlm2_5-7b](https://huggingface.co/internlm/internlm2_5-7b) | [<img src="./assets/modelscope_logo.png" width="20px" /> internlm2_5-7b](https://modelscope.cn/models/Shanghai_AI_Laboratory/internlm2_5-7b/summary) | [![Open in OpenXLab](https://cdn-static.openxlab.org.cn/header/openxlab_models.svg)](https://openxlab.org.cn/models/detail/OpenLMLab/internlm2_5-7b) | [![Open in OpenXLab](https://cdn-static.openxlab.org.cn/header/openxlab_models.svg)](https://openxlab.org.cn/models/detail/OpenLMLab/internlm2_5-7b-original) | 2024-07-03   |
 | **InternLM2.5-7B-Chat**    | [🤗internlm2_5-7b-chat](https://huggingface.co/internlm/internlm2_5-7b-chat) | [<img src="./assets/modelscope_logo.png" width="20px" /> internlm2_5-7b-chat](https://modelscope.cn/models/Shanghai_AI_Laboratory/internlm2_5-7b-chat/summary) | [![Open in OpenXLab](https://cdn-static.openxlab.org.cn/header/openxlab_models.svg)](https://openxlab.org.cn/models/detail/OpenLMLab/internlm2_5-7b-chat) | [![Open in OpenXLab](https://cdn-static.openxlab.org.cn/header/openxlab_models.svg)](https://openxlab.org.cn/models/detail/OpenLMLab/internlm2_5-7b-chat-original) | 2024-07-03   |
 | **InternLM2.5-7B-Chat-1M** | [🤗internlm2_5-7b-chat-1m](https://huggingface.co/internlm/internlm2_5-7b-chat-1m) | [<img src="./assets/modelscope_logo.png" width="20px" /> internlm2_5-7b-chat-1m](https://modelscope.cn/models/Shanghai_AI_Laboratory/internlm2_5-7b-chat-1m/summary) | [![Open in OpenXLab](https://cdn-static.openxlab.org.cn/header/openxlab_models.svg)](https://openxlab.org.cn/models/detail/OpenLMLab/internlm2_5-7b-chat-1m) | [![Open in OpenXLab](https://cdn-static.openxlab.org.cn/header/openxlab_models.svg)](https://openxlab.org.cn/models/detail/OpenLMLab/internlm2_5-7b-chat-1m-original) | 2024-07-03   |
+| **InternLM2.5-20B**        | [🤗internlm2_5-20b](https://huggingface.co/internlm/internlm2_5-20b) | [<img src="./assets/modelscope_logo.png" width="20px" /> internlm2_5-20b](https://modelscope.cn/models/Shanghai_AI_Laboratory/internlm2_5-20b/summary) | [![Open in OpenXLab](https://cdn-static.openxlab.org.cn/header/openxlab_models.svg)](https://openxlab.org.cn/models/detail/OpenLMLab/internlm2_5-20b) | [![Open in OpenXLab](https://cdn-static.openxlab.org.cn/header/openxlab_models.svg)](https://openxlab.org.cn/models/detail/OpenLMLab/internlm2_5-20b-original) | 2024-08-05   |
+| **InternLM2.5-20B-Chat**   | [🤗internlm2_5-20b-chat](https://huggingface.co/internlm/internlm2_5-20b-chat) | [<img src="./assets/modelscope_logo.png" width="20px" /> internlm2_5-20b-chat](https://modelscope.cn/models/Shanghai_AI_Laboratory/internlm2_5-20b-chat/summary) | [![Open in OpenXLab](https://cdn-static.openxlab.org.cn/header/openxlab_models.svg)](https://openxlab.org.cn/models/detail/OpenLMLab/internlm2_5-20b-chat) | [![Open in OpenXLab](https://cdn-static.openxlab.org.cn/header/openxlab_models.svg)](https://openxlab.org.cn/models/detail/OpenLMLab/internlm2_5-20b-chat-original) | 2024-08-05   |

 **Notes:**

-The release of InternLM2.5 series contains 7B model size for now and we are going to release the 1.8B and 20B versions soon. 7B models are efficient for research and application and 20B models are more powerful and can support more complex scenarios. The relation of these models are shown as follows.
+The release of InternLM2.5 series contains 1.8B, 7B, and 20B versions. 7B models are efficient for research and application and 20B models are more powerful and can support more complex scenarios. The relation of these models are shown as follows.

 1. **InternLM2.5**: Foundation models pre-trained on large-scale corpus. InternLM2.5 models are recommended for consideration in most applications.
 2. **InternLM2.5-Chat**: The Chat model that undergoes supervised fine-tuning (SFT) and reinforcement learning from human feedback (RLHF), based on the InternLM2.5 model. InternLM2.5-Chat is optimized for instruction following, chat experience, and function call, which is recommended for downstream applications.
--- a/README_zh-CN.md
+++ b/README_zh-CN.md
@ -44,6 +44,8 @@ InternLM2.5 系列模型在本仓库正式发布，具有如下特性：

 ## 更新

+\[2024.08.01\] 我们发布了 InternLM2.5-1.8B、InternLM2.5-1.8B-Chat、InternLM2.5-20B 和 InternLM2.5-20B-Chat。可以在下方的 [模型库](#model-zoo) 进行下载，或者在 [model cards](./model_cards/) 中了解更多细节。
+
 \[2024.07.19\] 我们发布了 1.8B、7B 和 20B 大小的 InternLM2-Reward 系列奖励模型。可以在下方的 [模型库](#model-zoo) 进行下载，或者在 [model cards](./model_cards/internlm2_reward.md) 中了解更多细节。

 \[2024.06.30\] 我们发布了 InternLM2.5-7B、InternLM2.5-7B-Chat 和 InternLM2.5-7B-Chat-1M。可以在下方的 [模型库](#model-zoo) 进行下载，或者在 [model cards](./model_cards/) 中了解更多细节。
@ -66,13 +68,17 @@ InternLM2.5 系列模型在本仓库正式发布，具有如下特性：

 | Model                      | Transformers(HF)                           | ModelScope(HF)                           | OpenXLab(HF)                           | OpenXLab(Origin)                           | Release Date |
 | -------------------------- | ------------------------------------------ | ---------------------------------------- | -------------------------------------- | ------------------------------------------ | ------------ |
+| **InternLM2.5-1.8B**       | [🤗internlm2_5-1_8b](https://huggingface.co/internlm/internlm2_5-1_8b) | [<img src="./assets/modelscope_logo.png" width="20px" /> internlm2_5-1_8b](https://modelscope.cn/models/Shanghai_AI_Laboratory/internlm2_5-1_8b/summary) | [![Open in OpenXLab](https://cdn-static.openxlab.org.cn/header/openxlab_models.svg)](https://openxlab.org.cn/models/detail/OpenLMLab/internlm2_5-1_8b) | [![Open in OpenXLab](https://cdn-static.openxlab.org.cn/header/openxlab_models.svg)](https://openxlab.org.cn/models/detail/OpenLMLab/internlm2_5-1_8b-original) | 2024-08-05   |
+| **InternLM2.5-1.8B-Chat**  | [🤗internlm2_5-1_8b-chat](https://huggingface.co/internlm/internlm2_5-1_8b-chat) | [<img src="./assets/modelscope_logo.png" width="20px" /> internlm2_5-1_8b](https://modelscope.cn/models/Shanghai_AI_Laboratory/internlm2_5-1_8b-chat/summary) | [![Open in OpenXLab](https://cdn-static.openxlab.org.cn/header/openxlab_models.svg)](https://openxlab.org.cn/models/detail/OpenLMLab/internlm2_5-1_8b-chat) | [![Open in OpenXLab](https://cdn-static.openxlab.org.cn/header/openxlab_models.svg)](https://openxlab.org.cn/models/detail/OpenLMLab/internlm2_5-1_8b-chat-original) | 2024-08-05   |
 | **InternLM2.5-7B**         | [🤗internlm2_5-7b](https://huggingface.co/internlm/internlm2_5-7b) | [<img src="./assets/modelscope_logo.png" width="20px" /> internlm2_5-7b](https://modelscope.cn/models/Shanghai_AI_Laboratory/internlm2_5-7b/summary) | [![Open in OpenXLab](https://cdn-static.openxlab.org.cn/header/openxlab_models.svg)](https://openxlab.org.cn/models/detail/OpenLMLab/internlm2_5-7b) | [![Open in OpenXLab](https://cdn-static.openxlab.org.cn/header/openxlab_models.svg)](https://openxlab.org.cn/models/detail/OpenLMLab/internlm2_5-7b-original) | 2024-07-03   |
 | **InternLM2.5-7B-Chat**    | [🤗internlm2_5-7b-chat](https://huggingface.co/internlm/internlm2_5-7b-chat) | [<img src="./assets/modelscope_logo.png" width="20px" /> internlm2_5-7b-chat](https://modelscope.cn/models/Shanghai_AI_Laboratory/internlm2_5-7b-chat/summary) | [![Open in OpenXLab](https://cdn-static.openxlab.org.cn/header/openxlab_models.svg)](https://openxlab.org.cn/models/detail/OpenLMLab/internlm2_5-7b-chat) | [![Open in OpenXLab](https://cdn-static.openxlab.org.cn/header/openxlab_models.svg)](https://openxlab.org.cn/models/detail/OpenLMLab/internlm2_5-7b-chat-original) | 2024-07-03   |
 | **InternLM2.5-7B-Chat-1M** | [🤗internlm2_5-7b-chat-1m](https://huggingface.co/internlm/internlm2_5-7b-chat-1m) | [<img src="./assets/modelscope_logo.png" width="20px" /> internlm2_5-7b-chat-1m](https://modelscope.cn/models/Shanghai_AI_Laboratory/internlm2_5-7b-chat-1m/summary) | [![Open in OpenXLab](https://cdn-static.openxlab.org.cn/header/openxlab_models.svg)](https://openxlab.org.cn/models/detail/OpenLMLab/internlm2_5-7b-chat-1m) | [![Open in OpenXLab](https://cdn-static.openxlab.org.cn/header/openxlab_models.svg)](https://openxlab.org.cn/models/detail/OpenLMLab/internlm2_5-7b-chat-1m-original) | 2024-07-03   |
+| **InternLM2.5-20B**        | [🤗internlm2_5-20b](https://huggingface.co/internlm/internlm2_5-20b) | [<img src="./assets/modelscope_logo.png" width="20px" /> internlm2_5-20b](https://modelscope.cn/models/Shanghai_AI_Laboratory/internlm2_5-20b/summary) | [![Open in OpenXLab](https://cdn-static.openxlab.org.cn/header/openxlab_models.svg)](https://openxlab.org.cn/models/detail/OpenLMLab/internlm2_5-20b) | [![Open in OpenXLab](https://cdn-static.openxlab.org.cn/header/openxlab_models.svg)](https://openxlab.org.cn/models/detail/OpenLMLab/internlm2_5-20b-original) | 2024-08-05   |
+| **InternLM2.5-20B-Chat**   | [🤗internlm2_5-20b-chat](https://huggingface.co/internlm/internlm2_5-20b-chat) | [<img src="./assets/modelscope_logo.png" width="20px" /> internlm2_5-20b](https://modelscope.cn/models/Shanghai_AI_Laboratory/internlm2_5-20b-chat/summary) | [![Open in OpenXLab](https://cdn-static.openxlab.org.cn/header/openxlab_models.svg)](https://openxlab.org.cn/models/detail/OpenLMLab/internlm2_5-20b-chat) | [![Open in OpenXLab](https://cdn-static.openxlab.org.cn/header/openxlab_models.svg)](https://openxlab.org.cn/models/detail/OpenLMLab/internlm2_5-20b-chat-original) | 2024-08-05   |

 **模型说明：**

-目前 InternLM 2.5 系列只发布了 7B 大小的模型，我们接下来将开源 1.8B 和 20B 的版本。7B 为轻量级的研究和应用提供了一个轻便但性能不俗的模型，20B 模型的综合性能更为强劲，可以有效支持更加复杂的实用场景。每个规格不同模型关系如下所示：
+目前 InternLM 2.5 系列发布了 1.8B、7B 和 20B 大小的模型。7B 为轻量级的研究和应用提供了一个轻便但性能不俗的模型，20B 模型的综合性能更为强劲，可以有效支持更加复杂的实用场景。每个规格不同模型关系如下所示：

 1. **InternLM2.5**：经历了大规模预训练的基座模型，是我们推荐的在大部分应用中考虑选用的优秀基座。
 2. **InternLM2.5-Chat**: 对话模型，在 InternLM2.5 基座上经历了有监督微调和 online RLHF。InternLM2.5-Chat 面向对话交互进行了优化，具有较好的指令遵循、共情聊天和调用工具等的能力，是我们推荐直接用于下游应用的模型。
--- a/model_cards/internlm2.5_1.8b.md
+++ b/model_cards/internlm2.5_1.8b.md
@ -0,0 +1,53 @@
+# InternLM2.5-1.8B Model Card
+
+## Introduction
+
+InternLM2.5, the 2.5th generation InternLM, has open-sourced a 1.8 billion parameter base model and a chat model tailored for practical scenarios. For the convenience of users and researchers, we have open-sourced two versions of each scale of the model, which are:
+
+- InternLM2.5-1.8B: Further pretrain with general domain data and domain-enhanced corpus, obtaining state-of-the-art performance in evaluation with good language capability. InternLM2.5 models are recommended for consideration in most applications.
+- InternLM2.5-chat-1.8B: Further aligned on top of InternLM2.5 through supervised fine-tuning (SFT) and online RLHF. InternLM2.5-Chat exhibits better instruction following, chat experience, and function calling, which is recommended for downstream applications.
+
+The model has the following characteristics:
+
+- **Outstanding reasoning capability**: State-of-the-art performance on Math reasoning, surpassing models like MiniCPM-2 and Qwen2-1.5B.
+
+- **Stronger tool use**: InternLM2.5 supports gathering information from more than 100 web pages, corresponding implementation has be released in [MindSearch](https://github.com/InternLM/MindSearch). InternLM2.5 has better tool utilization-related capabilities in instruction following, tool selection and reflection. See [examples](https://github.com/InternLM/InternLM/blob/main/agent/lagent.md).
+
+## Model Zoo
+
+| Model                     | Transformers(HF)                           | ModelScope(HF)                           | OpenXLab(HF)                           | OpenXLab(Origin)                            | Release Date |
+| ------------------------- | ------------------------------------------ | ---------------------------------------- | -------------------------------------- | ------------------------------------------- | ------------ |
+| **InternLM2.5-1.8B**      | [🤗internlm2_5-1_8b](https://huggingface.co/internlm/internlm2_5-1_8b) | [<img src="../assets/modelscope_logo.png" width="20px" /> internlm2_5-1_8b](https://modelscope.cn/models/Shanghai_AI_Laboratory/internlm2_5-1_8b/summary) | [![Open in OpenXLab](https://cdn-static.openxlab.org.cn/header/openxlab_models.svg)](https://openxlab.org.cn/models/detail/OpenLMLab/internlm2_5-1_8b) | [![Open in OpenXLab](https://cdn-static.openxlab.org.cn/header/openxlab_models.svg)](https://openxlab.org.cn/models/detail/OpenLMLab/internlm2_5-1_8b-original) | 2024-08-05   |
+| **InternLM2.5-1.8B-Chat** | [🤗internlm2_5-1_8b-chat](https://huggingface.co/internlm/internlm2_5-1_8b-chat) | [<img src="../assets/modelscope_logo.png" width="20px" /> internlm2_5-1_8b-chat](https://modelscope.cn/models/Shanghai_AI_Laboratory/internlm2_5-1_8b-chat/summary) | [![Open in OpenXLab](https://cdn-static.openxlab.org.cn/header/openxlab_models.svg)](https://openxlab.org.cn/models/detail/OpenLMLab/internlm2_5-1_8b-chat) | [![Open in OpenXLab](https://cdn-static.openxlab.org.cn/header/openxlab_models.svg)](https://openxlab.org.cn/models/detail/OpenLMLab/internlm2_5-1_8b-chat-original) | 2024-08-05   |
+
+- `HF` refers to the format used by HuggingFace in [transformers](https://github.com/huggingface/transformers), whereas `Origin` denotes the format adopted by the InternLM team in [InternEvo](https://github.com/InternLM/InternEvo).
+
+## Performance Evaluation
+
+We have evaluated InternLM2.5 on several important benchmarks using the open-source evaluation tool [OpenCompass](https://github.com/open-compass/opencompass). Some of the evaluation results are shown in the table below. You are welcome to visit the [OpenCompass Leaderboard](https://opencompass.org.cn/rank) for more evaluation results.
+
+### Base Model
+
+| Benchmark | InternLM2.5-1.8B | InternLM2-1.8B | Qwen2-1.5B |
+| --------- | ---------------- | -------------- | ---------- |
+| MMLU      | 53.52            | 45.99          | 57.45      |
+| CMMLU     | 65.44            | 45.27          | 70.58      |
+| BBH       | 41.16            | 36.03          | 35.75      |
+| MATH      | 27.28            | 9.42           | 24.38      |
+| HUMANEVAL | 35.98            | 30.49          | 34.15      |
+| GPQA      | 24.24            | 24.24          | 31.82      |
+
+### Chat Model
+
+| Benchmark         | InternLM2.5-1.8B-Chat | MiniCPM-2 | Qwen2-1.5B-Instruct |
+| ----------------- | --------------------- | --------- | ------------------- |
+| MMLU (5-shot)     | 50.7                  | 54.2      | 55.7                |
+| CMMLU (5-shot)    | 62.2                  | 50.6      | 65.2                |
+| BBH (3-shot CoT)  | **41.9**              | 41.5      | 36.5                |
+| MATH (0-shot CoT) | **40.2**              | 15.5      | 21.4                |
+| GPQA (0-shot)     | **27.8**              | 23.7      | 27.3                |
+
+- We use `ppl` for the MCQ evaluation on base model.
+- The evaluation results were obtained from [OpenCompass](https://github.com/open-compass/opencompass) , and evaluation configuration can be found in the configuration files provided by [OpenCompass](https://github.com/open-compass/opencompass).
+- The evaluation data may have numerical differences due to the version iteration of [OpenCompass](https://github.com/open-compass/opencompass), so please refer to the latest evaluation results of [OpenCompass](https://github.com/open-compass/opencompass).
+- \* means the result is copied from the original paper.
--- a/model_cards/internlm2.5_20b.md
+++ b/model_cards/internlm2.5_20b.md
@ -0,0 +1,53 @@
+# InternLM2.5-20B Model Card
+
+## Introduction
+
+InternLM2.5, the 2.5th generation InternLM, has open-sourced a 20 billion parameter base model and a chat model tailored for practical scenarios. For the convenience of users and researchers, we have open-sourced two versions of each scale of the model, which are:
+
+- InternLM2.5-20B: Further pretrain with general domain data and domain-enhanced corpus, obtaining state-of-the-art performance in evaluation with good language capability. InternLM2.5 models are recommended for consideration in most applications.
+- InternLM2.5-chat-20B: Further aligned on top of InternLM2.5 through supervised fine-tuning (SFT) and online RLHF. InternLM2.5-Chat exhibits better instruction following, chat experience, and function calling, which is recommended for downstream applications.
+
+The model has the following characteristics:
+
+- **Outstanding reasoning capability**: State-of-the-art performance on Math reasoning, surpassing models like Llama3 and Gemma2-27B.
+
+- **Stronger tool use**: InternLM2.5 supports gathering information from more than 100 web pages, corresponding implementation has be released in [MindSearch](https://github.com/InternLM/MindSearch). InternLM2.5 has better tool utilization-related capabilities in instruction following, tool selection and reflection. See [examples](https://github.com/InternLM/InternLM/blob/main/agent/lagent.md).
+
+## Model Zoo
+
+| Model                    | Transformers(HF)                           | ModelScope(HF)                           | OpenXLab(HF)                            | OpenXLab(Origin)                            | Release Date |
+| ------------------------ | ------------------------------------------ | ---------------------------------------- | --------------------------------------- | ------------------------------------------- | ------------ |
+| **InternLM2.5-20B**      | [🤗internlm2_5-20b](https://huggingface.co/internlm/internlm2_5-20b) | [<img src="../assets/modelscope_logo.png" width="20px" /> internlm2_5-20b](https://modelscope.cn/models/Shanghai_AI_Laboratory/internlm2_5-20b/summary) | [![Open in OpenXLab](https://cdn-static.openxlab.org.cn/header/openxlab_models.svg)](https://openxlab.org.cn/models/detail/OpenLMLab/internlm2_5-20b) | [![Open in OpenXLab](https://cdn-static.openxlab.org.cn/header/openxlab_models.svg)](https://openxlab.org.cn/models/detail/OpenLMLab/internlm2_5-20b-original) | 2024-08-05   |
+| **InternLM2.5-20B-Chat** | [🤗internlm2_5-20b-chat](https://huggingface.co/internlm/internlm2_5-20b-chat) | [<img src="../assets/modelscope_logo.png" width="20px" /> internlm2_5-20b-chat](https://modelscope.cn/models/Shanghai_AI_Laboratory/internlm2_5-20b-chat/summary) | [![Open in OpenXLab](https://cdn-static.openxlab.org.cn/header/openxlab_models.svg)](https://openxlab.org.cn/models/detail/OpenLMLab/internlm2_5-20b-chat) | [![Open in OpenXLab](https://cdn-static.openxlab.org.cn/header/openxlab_models.svg)](https://openxlab.org.cn/models/detail/OpenLMLab/internlm2_5-20b-chat-original) | 2024-08-05   |
+
+- `HF` refers to the format used by HuggingFace in [transformers](https://github.com/huggingface/transformers), whereas `Origin` denotes the format adopted by the InternLM team in [InternEvo](https://github.com/InternLM/InternEvo).
+
+## Performance Evaluation
+
+We have evaluated InternLM2.5 on several important benchmarks using the open-source evaluation tool [OpenCompass](https://github.com/open-compass/opencompass). Some of the evaluation results are shown in the table below. You are welcome to visit the [OpenCompass Leaderboard](https://opencompass.org.cn/rank) for more evaluation results.
+
+### Base Model
+
+| Benchmark | InternLM2.5-20B | InternLM2-20B |
+| --------- | --------------- | ------------- |
+| MMLU      | 74.25           | 67.58         |
+| CMMLU     | 82.22           | 68.29         |
+| BBH       | 77.82           | 71.36         |
+| MATH      | 48              | 32.66         |
+| HUMANEVAL | 71.95           | 51.22         |
+| GPQA      | 37.88           | 31.31         |
+
+### Chat Model
+
+| Benchmark         | InternLM2.5-20B-Chat | Gemma2-27B-IT |
+| ----------------- | -------------------- | ------------- |
+| MMLU (5-shot)     | 73.5                 | 75.0          |
+| CMMLU (5-shot)    | **79.7**             | 63.3          |
+| BBH (3-shot CoT)  | **76.3**             | 71.5          |
+| MATH (0-shot CoT) | **64.7**             | 50.1          |
+| GPQA (0-shot)     | **33.3**             | 29.3          |
+
+- We use `ppl` for the MCQ evaluation on base model.
+- The evaluation results were obtained from [OpenCompass](https://github.com/open-compass/opencompass) , and evaluation configuration can be found in the configuration files provided by [OpenCompass](https://github.com/open-compass/opencompass).
+- The evaluation data may have numerical differences due to the version iteration of [OpenCompass](https://github.com/open-compass/opencompass), so please refer to the latest evaluation results of [OpenCompass](https://github.com/open-compass/opencompass).
+- \* means the result is copied from the original paper.