Hugging Face's logo
Activity Feed Request to join this org

AI & ML interests

None defined yet.

Recent Activity
woojun-jungΒ  authored a paper 14 days ago
QEVA: A Reference-Free Evaluation Metric for Narrative Video Summarization with Multimodal Question Answering
parkneuralsΒ  authored a paper about 1 month ago
KV Cache Recycling to Expand Usable Context Capacity in Low Parameter LLMs
1aurentΒ  authored a paper about 1 month ago
Voxtral TTS
View all activity
danielhanchenΒ 
posted an update about 17 hours ago
view post
Post
1895
We’re excited to announce that Unsloth has joined the PyTorch Ecosystem! πŸ”₯πŸ¦₯

Unsloth is an open-source project that makes training & running models more accurate and faster with less compute. Our mission is to make local AI accessible to everyone. Thanks to all of you for making this possible! πŸ’•

Blog: https://unsloth.ai/blog/pytorch
GitHub: https://github.com/unslothai/unsloth
  • 1 reply
Β·
danielhanchenΒ 
posted an update 5 days ago
view post
Post
7451
We collaborated with NVIDIA to teach you how we made LLM training ~25% faster! πŸš€

Learn how 3 optimizations help your home GPU train models faster:
1. Packed-sequence metadata caching
2. Double-buffered checkpoint reloads
3. Faster MoE routing

Guide: https://unsloth.ai/blog/nvidia-collab
GitHub: https://github.com/unslothai/unsloth
Aurelien-MorganΒ 
posted an update 9 days ago
view post
Post
1007
@retrain-pipelines v0.2.0 is out !
I'm at Station F at My booth with GOSIM Paris 2026 today & tomorrow.
Come meet me for a live in-person demo and a chat !
  • 1 reply
Β·
danielhanchenΒ 
posted an update 9 days ago
view post
Post
8679
We made a guide on how to run open LLMs in Claude Code, Codex and OpenClaw.

Use Gemma 4 and Qwen3.6 GGUFs for local agentic coding on 24GB RAM

Run with self-healing tool calls, code execution, web search via the Unsloth API endpoint and llama.cpp

Guide: https://unsloth.ai/docs/basics/api
woojun-jungΒ 
authored a paper 14 days ago
danielhanchenΒ 
posted an update 15 days ago
view post
Post
10734
Unsloth is now one of the top 10 most followed organizations on Hugging Face. πŸ€—πŸ¦₯

Thanks so much for all the support!
Our HF page:
unsloth
  • 5 replies
Β·
danielhanchenΒ 
posted an update 22 days ago
danielhanchenΒ 
posted an update 28 days ago
Aurelien-MorganΒ 
posted an update about 1 month ago
view post
Post
217
Launching a workweek of @retrain-pipelines wheels.

Day #1 : Compose
  • 4 replies
Β·
danielhanchenΒ 
posted an update about 1 month ago
danielhanchenΒ 
posted an update about 1 month ago
danielhanchenΒ 
posted an update about 1 month ago
view post
Post
2770
A new way to use Unsloth.

Coming soon...
danielhanchenΒ 
posted an update about 2 months ago
view post
Post
935
You don’t need to set LLM parameters anymore! πŸš€

llama.cpp uses only the context length + compute your local setup needs. Unsloth also auto-applies the correct model settings

Try in Unsloth Studio - now with precompiled llama.cpp binaries.

GitHub: https://github.com/unslothai/unsloth
  • 2 replies
Β·
danielhanchenΒ 
posted an update about 2 months ago
view post
Post
3417
Introducing Unsloth Studio ✨
A new open-source web UI to train and run LLMs.

β€’ Run models locally on Mac, Windows, Linux
β€’ Train 500+ models 2x faster with 70% less VRAM
β€’ Supports GGUF, vision, audio, embedding models
β€’ Auto-create datasets from PDF, CSV, DOCX
β€’ Self-healing tool calling and code execution
β€’ Compare models side by side + export to GGUF

GitHub: https://github.com/unslothai/unsloth
Blog and Guide: https://unsloth.ai/docs/new/studio

Available now on Hugging Face, NVIDIA, Docker and Colab.
danielhanchenΒ 
posted an update 2 months ago
view post
Post
3934
We collaborated with NVIDIA to teach you about Reinforcement Learning and RL environments. πŸ’š Learn:

β€’ Why RL environments matter + how to build them
β€’ When RL is better than SFT
β€’ GRPO and RL best practices
β€’ How verifiable rewards and RLVR work

Blog: https://unsloth.ai/blog/rl-environments
  • 4 replies
Β·
danielhanchenΒ 
posted an update 3 months ago
view post
Post
3458
100,000+ models trained with Unsloth have now been open-sourced on πŸ€—Hugging Face! πŸ¦₯

Here are the most popular ones you can run local:
1. TeichAI - GLM-4.7-Flash distilled from Claude 4.5 Opus (high)
2. Zed - Qwen Coder 7B fine-tuned for stronger coding
3. DavidAU - Llama-3.3-8B distilled from Claude 4.5 Opus (high)
4. huihui - gpt-oss made β€œabliberated”

Links to models:
1. TeichAI: TeichAI/GLM-4.7-Flash-Claude-Opus-4.5-High-Reasoning-Distill-GGUF
2. Zed: zed-industries/zeta
3. DavidAU: DavidAU/Llama3.3-8B-Instruct-Thinking-Claude-4.5-Opus-High-Reasoning
4. huihui: huihui-ai/Huihui-gpt-oss-20b-BF16-abliterated

See all the 100K latest models fine-tuned with Unsloth here: https://huggingface.co/models?other=u
  • 2 replies
Β·
danielhanchenΒ 
posted an update 3 months ago
danielhanchenΒ 
posted an update 3 months ago
view post
Post
5226
We collaborated with Hugging Face to enable you to train MoE models 12Γ— faster with 35% less VRAM via our new Triton kernels (no accuracy loss). πŸ€—

Train gpt-oss locally on 12.8GB VRAM with our free notebooks: https://unsloth.ai/docs/new/faster-moe
  • 1 reply
Β·
julien-cΒ 
submitted a paper to Daily Papers 3 months ago
danielhanchenΒ 
posted an update 4 months ago