InternLM

InternLM


HOT

[](./LICENSE)
[](https://github.com/internLM/OpenCompass/)

<!--  -->

[📘Commercial Application](#license) |
🤗HuggingFace |
[🆕Update News](#news) |
🤔Reporting Issues |
📜Technical Report
💬Chat Web |
🔗API |
🧩Modelers

[English](./README.md) |
[简体中文](./README_zh-CN.md)

👋 join us on Discord and WeChat

Introduction

InternLM3 has open-sourced an 8-billion parameter instruction model, InternLM3-8B-Instruct, designed for general-purpose usage and advanced reasoning. This model has the following characteristics:

• Enhanced performance at reduced cost:

State-of-the-art performance on reasoning and knowledge-intensive tasks surpass models like Llama3.1-8B and Qwen2.5-7B. Remarkably, InternLM3 is trained on only 4 trillion high-quality tokens, saving more than 75% of the training cost compared to other LLMs of similar scale.

• Deep thinking capability:

InternLM3 supports both the deep thinking mode for solving complicated reasoning tasks via the long chain-of-thought and the normal response mode for fluent user interactions.

News

\[2025.01.15\] We release InternLM3-8B-Instruct, See [model zoo below](#model-zoo) for download or [model cards](./model_cards/) for more details.

\[2024.08.01\] 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.

\[2024.03.26\] We release InternLM2 technical report. See arXiv for details.

\[2024.01.31\] We release InternLM2-1.8B, along with the associated chat model. They provide a cheaper deployment option while maintaining leading performance.

\[2024.01.23\] We release InternLM2-Math-7B and InternLM2-Math-20B with pretraining and SFT checkpoints. They surpass ChatGPT with small sizes. See InternLM-Math for details and download.

\[2024.01.17\] We release InternLM2-7B and InternLM2-20B and their corresponding chat models with stronger capabilities in all dimensions. See [model zoo below](#model-zoo) for download or [model cards](./model_cards/) for more details.

\[2023.12.13\] InternLM-7B-Chat and InternLM-20B-Chat checkpoints are updated. With an improved finetuning strategy, the new chat models can generate higher quality responses with greater stylistic diversity.

\[2023.09.20\] InternLM-20B is released with base and chat versions.

Model Zoo

InternLM3

| Model | Transformers | ModelScope | Modelers | Release Date |
| ------------------------- | -------------------------------------------------------- | ------------------------------------------------------ | ----------------------------------------------------- | ------------ |
| InternLM3-8B-Instruct | 🤗internlm3_8B_instruct | internlm3_8b_instruct |  | 2025-01-15 |

InternLM2.5

(click to expand)

| Model | Transformers(HF) | ModelScope(HF) | OpenXLab(HF) | OpenXLab(Origin) | Release Date |
| -------------------------- | ------------------------------------------ | ---------------------------------------- | -------------------------------------- | ------------------------------------------ | ------------ |
| InternLM2.5-1.8B | 🤗internlm2_5-1_8b | internlm2_5-1_8b |  |  | 2024-08-05 |
| InternLM2.5-1.8B-Chat | 🤗internlm2_5-1_8b-chat | internlm2_5-1_8b-chat |  |  | 2024-08-05 |
| InternLM2.5-7B | 🤗internlm2_5-7b | internlm2_5-7b |  |  | 2024-07-03 |
| InternLM2.5-7B-Chat | 🤗internlm2_5-7b-chat | internlm2_5-7b-chat |  |  | 2024-07-03 |
| InternLM2.5-7B-Chat-1M | 🤗internlm2_5-7b-chat-1m | internlm2_5-7b-chat-1m |  |  | 2024-07-03 |
| InternLM2.5-20B | 🤗internlm2_5-20b | internlm2_5-20b |  |  | 2024-08-05 |
| InternLM2.5-20B-Chat | 🤗internlm2_5-20b-chat | internlm2_5-20b-chat |  |  | 2024-08-05 |

Notes:

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.
3. InternLM2.5-Chat-1M: InternLM2.5-Chat-1M supports 1M long-context with compatible performance as InternLM2.5-Chat.

Limitations: Although we have made efforts to ensure the safety of the model during the training process and to encourage the model to generate text that complies with ethical and legal requirements, the model may still produce unexpected outputs due to its size and probabilistic generation paradigm. For example, the generated responses may contain biases, discrimination, or other harmful content. Please do not propagate such content. We are not responsible for any consequences resulting from the dissemination of harmful information.

Supplements: HF refers to the format used by HuggingFace in transformers, whereas Origin denotes the format adopted by the InternLM team in InternEvo.

InternLM2-Reward

(click to expand)

InternLM2-Reward is a series of reward models, trained on 2.4 million preference samples, available in 1.8B, 7B, and 20B sizes. These model were applied to the PPO training process of our chat models. See [model cards](./model_cards/internlm2_reward.md) for more details.

| Model | RewardBench Score | Transformers(HF) | ModelScope(HF) | OpenXLab(HF) | Release Date |
| ------------------------- | ----------------- | -------------------------------------------------- | ------------------------------------------------- | ----------------------------------------------- | ------------ |
| InternLM2-1.8B-Reward | 80.6 | 🤗internlm2-1_8b-reward | internlm2-1_8b-reward |  | 2024-07-19 |
| InternLM2-7B-Reward | 86.6 | 🤗internlm2-7b-reward | internlm2-7b-reward |  | 2024-07-19 |
| InternLM2-20B-Reward | 89.5 | 🤗internlm2-20b-reward | internlm2-20b-reward |  | 2024-07-19 |

InternLM2

(click to expand)

Our previous generation models with advanced capabilities in long-context processing, reasoning, and coding. See [model cards](./model_cards/) for more details.

| Model | Transformers(HF) | ModelScope(HF) | OpenXLab(HF) | OpenXLab(Origin) | Release Date |
| --------------------------- | ----------------------------------------- | ---------------------------------------- | -------------------------------------- | ------------------------------------------ | ------------ |
| InternLM2-1.8B | 🤗internlm2-1.8b | internlm2-1.8b |  |  | 2024-01-31 |
| InternLM2-Chat-1.8B-SFT | 🤗internlm2-chat-1.8b-sft | internlm2-chat-1.8b-sft |  |  | 2024-01-31 |
| InternLM2-Chat-1.8B | 🤗internlm2-chat-1.8b | internlm2-chat-1.8b |  |  | 2024-02-19 |
| InternLM2-Base-7B | 🤗internlm2-base-7b | [<img src="./assets/modelscope_logo.

…

Collapse