[GH-ISSUE #5463] InternLM2.5 - 7 billion parameter with 1M context length #65456

Closed
opened 2026-05-03 21:20:12 -05:00 by GiteaMirror · 3 comments
Owner

Originally created by @Qualzz on GitHub (Jul 3, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/5463

Link to the collection

Introduction
InternLM2.5 has open-sourced a 7 billion parameter base model and a chat model tailored for practical scenarios. The model has the following characteristics:

Outstanding reasoning capability: State-of-the-art performance on Math reasoning, surpassing models like Llama3 and Gemma2-9B.

1M Context window: Nearly perfect at finding needles in the haystack with 1M-long context, with leading performance on long-context tasks like LongBench. Try it with LMDeploy for 1M-context inference.

Stronger tool use: InternLM2.5 supports gathering information from more than 100 web pages, corresponding implementation will be released in Lagent soon. InternLM2.5 has better tool utilization-related capabilities in instruction following, tool selection and reflection. See examples.

Originally created by @Qualzz on GitHub (Jul 3, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/5463 [Link to the collection](https://huggingface.co/collections/internlm/internlm25-66853f32717072d17581bc13) Introduction InternLM2.5 has open-sourced a 7 billion parameter base model and a chat model tailored for practical scenarios. The model has the following characteristics: Outstanding reasoning capability: State-of-the-art performance on Math reasoning, surpassing models like Llama3 and Gemma2-9B. 1M Context window: Nearly perfect at finding needles in the haystack with 1M-long context, with leading performance on long-context tasks like LongBench. Try it with [LMDeploy](https://huggingface.co/internlm/internlm2_5-7b-chat-1m/blob/main/chat/lmdeploy.md) for 1M-context inference. Stronger tool use: InternLM2.5 supports gathering information from more than 100 web pages, corresponding implementation will be released in [Lagent](https://github.com/InternLM/lagent/tree/main) soon. InternLM2.5 has better tool utilization-related capabilities in instruction following, tool selection and reflection. See [examples](https://huggingface.co/internlm/internlm2_5-7b-chat-1m/blob/main/agent/).
GiteaMirror added the model label 2026-05-03 21:20:12 -05:00
Author
Owner

@jthack commented on GitHub (Jul 3, 2024):

1m token length 👀

<!-- gh-comment-id:2206756794 --> @jthack commented on GitHub (Jul 3, 2024): 1m token length 👀
Author
Owner

@jvmx commented on GitHub (Jul 3, 2024):

Seconded, this would be a fantastic addition.

<!-- gh-comment-id:2206860901 --> @jvmx commented on GitHub (Jul 3, 2024): Seconded, this would be a fantastic addition.
Author
Owner

@Qualzz commented on GitHub (Jul 3, 2024):

Online
👍

<!-- gh-comment-id:2207389340 --> @Qualzz commented on GitHub (Jul 3, 2024): [Online](https://ollama.com/library/internlm2) 👍
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#65456