ML Intern
š¤
287
Ask ML questions and get instant helpful answers
smolagents
Team
community
AI & ML interests
None defined yet.
Recent Activity
View all activity
lewtunĀ
updated a
Space 3 days ago
Post
176
Hugging Face MCP Server v0.3.10
~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Reverted
~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Reverted
mcp bucket in favour of upcoming MCP App integration. 
akseljoonasĀ
updated a
Space 6 days ago
Fix: Pro users with OAuth tokens incorrectly classified as free
3
#21 opened 7 days ago
by 
Marco333
Post
887
Hugging Face MCP Server v0.3.9
~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Users with a bucket named
~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Users with a bucket named
mcp will get an additional list_files tool that returns the public URL of contained files. This is primarily intended for use with Gradio Spaces that need URLs as inputs.fix(bedrock): force tool cachePoint via cache_control_injection_points
1
#24 opened 7 days ago
by 
GuillaumeSalouHF
fix(session-uploader): forward user_id + total_cost_usd to dataset row
#23 opened 7 days ago
by GuillaumeSalouHF
Post
5288
Want to share my enthusiasm for zai-org/GLM-5.1 here too š„
I think we have it: our open source Claude Code = GLM-5.1 + Pi (https://pi.dev/) - Built a Three.js racing game to eval and it's extremely impressive. Thoughts:
- One-shot car physics with real drift mechanics (this is hard)
- My fav part: Awesome at self iterating (with no vision!) created 20+ Bun.WebView debugging tools to drive the car programmatically and read game state. Proved a winding bug with vector math without ever seeing the screen
- 531-line racing AI in a single write: 4 personalities, curvature map, racing lines, tactical drifting. Built telemetry tools to compare player vs AI speed curves and data-tuned parameters
- All assets from scratch: 3D models, procedural textures, sky shader, engine sounds, spatial AI audio!
- Can do hard math: proved road normals pointed DOWN via vector cross products, computed track curvature normalized by arc length to tune AI cornering speed
You are going to hear about this model a lot in the next months - open source let's go - and thanks z-aišš
I think we have it: our open source Claude Code = GLM-5.1 + Pi (https://pi.dev/) - Built a Three.js racing game to eval and it's extremely impressive. Thoughts:
- One-shot car physics with real drift mechanics (this is hard)
- My fav part: Awesome at self iterating (with no vision!) created 20+ Bun.WebView debugging tools to drive the car programmatically and read game state. Proved a winding bug with vector math without ever seeing the screen
- 531-line racing AI in a single write: 4 personalities, curvature map, racing lines, tactical drifting. Built telemetry tools to compare player vs AI speed curves and data-tuned parameters
- All assets from scratch: 3D models, procedural textures, sky shader, engine sounds, spatial AI audio!
- Can do hard math: proved road normals pointed DOWN via vector cross products, computed track curvature normalized by arc length to tune AI cornering speed
You are going to hear about this model a lot in the next months - open source let's go - and thanks z-aišš
- 4 replies
Post
974
The experimental MCP
hub_query tool now supports Paper Searching and Details as well as Daily Papers. 
clefourrierĀ
authored a
paper about 2 months ago
albertvillanovaĀ
posted an update 2 months ago
Post
2538
š TRL v0.29.0 introduces trl-training: an agent-native training skill.
This makes the TRL CLI a structured, agent-readable capability, allowing AI agents to reliably execute training workflows such as:
- Supervised Fine-Tuning (SFT)
- Direct Preference Optimization (DPO)
- Group Relative Policy Optimization (GRPO)
Weāre excited to see what the community builds on top of this.
If youāre working on AI agents, alignment research, or scalable RL training infrastructure: give TRL v0.29.0 a try! š¤
The future of ML tooling is agent-native.
š https://github.com/huggingface/trl/releases/tag/v0.29.0
This makes the TRL CLI a structured, agent-readable capability, allowing AI agents to reliably execute training workflows such as:
- Supervised Fine-Tuning (SFT)
- Direct Preference Optimization (DPO)
- Group Relative Policy Optimization (GRPO)
Weāre excited to see what the community builds on top of this.
If youāre working on AI agents, alignment research, or scalable RL training infrastructure: give TRL v0.29.0 a try! š¤
The future of ML tooling is agent-native.
š https://github.com/huggingface/trl/releases/tag/v0.29.0
victorĀ
submitted a
paper to Daily Papers 2 months ago
Post
3728
Hugging Face MCP Server v0.3.2
~~~~~~~~~~~~~~~~~~~~~~~~~~~~
- Replace model_search and dataset_search with combined hub_repo_search tool.
- Less distracting description for hf_doc_search
- model_search and dataset_search tool calls will still function (plan to remove next release).
~~~~~~~~~~~~~~~~~~~~~~~~~~~~
- Replace model_search and dataset_search with combined hub_repo_search tool.
- Less distracting description for hf_doc_search
- model_search and dataset_search tool calls will still function (plan to remove next release).
- 4 replies
lewtunĀ
submitted 2
papers to Daily Papers 3 months ago
albertvillanovaĀ
posted an update 3 months ago
Post
1896
5 years already working in democratizing AI š¤
Grateful to be part of such an awesome team making it happen every day.
Grateful to be part of such an awesome team making it happen every day.
Post
2759
Interesting article: use Claude Code to help open models write CUDA kernels (for eg) by turning CC traces into Skills. They made a library out of it š
https://huggingface.co/blog/upskill
https://huggingface.co/blog/upskill
Post
327
Hugging Face MCP Server v0.3.1
~~~~~~~~~~~~~~~~~~~~~~~~~~~~
- Streamable HTTP used for Gradio Connectivity
- SSE Transport (as Server) removed
- Proxy Configuration added for launch of sub-agent tools
~~~~~~~~~~~~~~~~~~~~~~~~~~~~
- Streamable HTTP used for Gradio Connectivity
- SSE Transport (as Server) removed
- Proxy Configuration added for launch of sub-agent tools
Post
3508
Nvidia is on a roll lately. Nemotron 3 Nano is my new fav local model, but here's the real flex: they published the entire evaluation setup. Configs, prompts, logs, all of it. This is how you do open models š„
https://huggingface.co/blog/nvidia/nemotron-3-nano-evaluation-recipe
https://huggingface.co/blog/nvidia/nemotron-3-nano-evaluation-recipe
Post
2559
Hugging Face MCP Server v0.2.46
~~~~~~~~~~~~~~~~~~~~~~~~~~~~
- Add "discover" to Dynamic Space tool. Recommend deselecting "space_search" if using dynamic spaces.
~~~~~~~~~~~~~~~~~~~~~~~~~~~~
- Add "discover" to Dynamic Space tool. Recommend deselecting "space_search" if using dynamic spaces.