30 lines
866 B
Plaintext
30 lines
866 B
Plaintext
---
|
|
title: "Jan supports NVIDIA NIM"
|
|
version: 0.5.1
|
|
description: "Jan has integrated NVIDIA NIM and supports Qwen 2 7B"
|
|
date: 2024-06-21
|
|
ogImage: "https://catalog.jan.ai/docs/jan_nvidia_nim_support.gif"
|
|
---
|
|
|
|
import ChangelogHeader from "@/components/Changelog/ChangelogHeader"
|
|
|
|
<ChangelogHeader title= "Jan supports NVIDIA NIM" date= '2024-06-21' ogImage= "https://catalog.jan.ai/docs/jan_nvidia_nim_support.gif"/>
|
|
|
|
## NVIDIA NIM
|
|
|
|
We've integrated NVIDIA NIM support.
|
|
|
|
## Qwen 2 7B
|
|
|
|
You can now access Qwen 2 7B directly in the Jan Hub.
|
|
|
|
We've updated to llama.cpp b3088 for better performance - thanks to [GG](https://github.com/ggerganov)
|
|
|
|
## Fixes
|
|
|
|
- Fixed Anthropic API error
|
|
- Reduced chat font weight (back to normal!)
|
|
- Restored the maximize button
|
|
|
|
For more details, see the [GitHub release notes](https://github.com/menloresearch/jan/releases/tag/v0.5.1).
|