Update README with latest features and Unsloth Start - #7258
Conversation
![gemini-code-assist[bot]](https://avatars.githubusercontent.com/in/956858?s=60&v=4){kind=small}
There was a problem hiding this comment.
Code Review
This pull request updates the README.md file to reflect the latest features, hardware support, and news for Unsloth. Key updates include the addition of the 'Unsloth Start' command for connecting various AI agents to local models, expanded AMD and Vulkan hardware support details, and an updated list of features and supported models (such as GLM-5.2, DeepSeek-V4, and Gemma 4). No review comments were provided, so there is no additional feedback to address.
Important
The consumer version of Gemini Code Assist on GitHub is being sunset. Starting June 18, 2026, new organization installations will be blocked, and all code review activity will officially cease on July 17, 2026.
For more details on the timeline and next steps, please review the Help Documentation.
![chatgpt-codex-connector[bot]](https://avatars.githubusercontent.com/in/1144995?s=60&v=4){kind=small}
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: 78cf958ca0
ℹ️ About Codex in GitHub
Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".
Imagineer99
changed the title
Imagineer99
changed the title
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: 43e8c404f8
ℹ️ About Codex in GitHub
Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".
|
|
||
| | Agent | Command | | ||
| | --- | --- | | ||
| | Claude Code | `unsloth start claude` | |
There was a problem hiding this comment.
In the safetensors/transformers case described earlier in the README, this command launches Claude against the Anthropic-compatible endpoint, but that endpoint is backed only by get_llama_cpp_backend() and returns No GGUF model loaded. Load a GGUF model first. when no GGUF/llama-server model is loaded (studio/backend/routes/inference.py:12530-12540). Users who load a non-GGUF Studio model will therefore get a Claude session whose turns fail; this row should call out the GGUF requirement or point those users to an agent/API path that uses /v1/chat/completions.
Useful? React with 👍 / 👎.
* Document local agent connections * Refresh README features and news * Tighten README feature copy * Restore selective README emphasis * Add Unsloth Start quickstart * Update * Mention * Update README.md * Reduce * Restore-inference-order * Split-agent-API-features
2 participants
No description provided.