Post
2277
We collabed with HF on showing how you can use HF Jobs and Unsloth! https://huggingface.co/blog/unsloth-jobs
AI & ML interests
None defined yet.
Recent Activity
View all activity
danielhanchen
posted
an
update
3 days ago
sergiopaniego
posted
an
update
4 days ago
Post
1253
Tiny Aya 🌿 just dropped from
@CohereLabs
, a really powerful multilingual small model!
To celebrate, we cooked up fresh resources to train it for tool calling 🔧
> Free Google Colab guide: https://colab.research.google.com/github/huggingface/trl/blob/main/examples/notebooks/sft_tool_calling.ipynb
> Standalone training script: https://github.com/huggingface/trl/blob/main/examples/scripts/sft_tiny_aya_tool_calling.py
To celebrate, we cooked up fresh resources to train it for tool calling 🔧
> Free Google Colab guide: https://colab.research.google.com/github/huggingface/trl/blob/main/examples/notebooks/sft_tool_calling.ipynb
> Standalone training script: https://github.com/huggingface/trl/blob/main/examples/scripts/sft_tiny_aya_tool_calling.py
danielhanchen
posted
an
update
6 days ago
Post
5535
You can now run Qwen3.5 locally! 💜
Qwen3.5-397B-A17B is an open MoE vision reasoning LLM for agentic coding & chat. It performs on par with Gemini 3 Pro, Claude Opus 4.5 & GPT-5.2.
GGUF: unsloth/Qwen3.5-397B-A17B-GGUF
Run Dynamic 3-bit on a 192GB Mac for 20 tokens/s.
Guide: https://unsloth.ai/docs/models/qwen3.5
Qwen3.5-397B-A17B is an open MoE vision reasoning LLM for agentic coding & chat. It performs on par with Gemini 3 Pro, Claude Opus 4.5 & GPT-5.2.
GGUF: unsloth/Qwen3.5-397B-A17B-GGUF
Run Dynamic 3-bit on a 192GB Mac for 20 tokens/s.
Guide: https://unsloth.ai/docs/models/qwen3.5
- 9 replies
danielhanchen
posted
an
update
7 days ago
Post
8363
You can now run MiniMax-2.5 locally! 🚀
At 230B parameters, MiniMax-2.5 is the strongest LLM under 700B params, delivering SOTA agentic coding & chat.
Run Dynamic 3/4-bit on a 128GB Mac for 20 tokens/s.
Guide: https://unsloth.ai/docs/models/minimax-2.5
GGUF: unsloth/MiniMax-M2.5-GGUF
At 230B parameters, MiniMax-2.5 is the strongest LLM under 700B params, delivering SOTA agentic coding & chat.
Run Dynamic 3/4-bit on a 128GB Mac for 20 tokens/s.
Guide: https://unsloth.ai/docs/models/minimax-2.5
GGUF: unsloth/MiniMax-M2.5-GGUF
- 1 reply
sergiopaniego
posted
an
update
9 days ago
Post
432
The latest piece by
@MiniMax-AI
is a must-read.
It tries to break the impossible triangle of agent RL: throughput × stability × flexibility.
A lot to learn here, go read it 🫵
https://huggingface.co/blog/MiniMax-AI/forge-scalable-agent-rl-framework-and-algorithm
It tries to break the impossible triangle of agent RL: throughput × stability × flexibility.
A lot to learn here, go read it 🫵
https://huggingface.co/blog/MiniMax-AI/forge-scalable-agent-rl-framework-and-algorithm
danielhanchen
posted
an
update
12 days ago
Post
5124
We collaborated with Hugging Face to enable you to train MoE models 12× faster with 35% less VRAM via our new Triton kernels (no accuracy loss). 🤗
Train gpt-oss locally on 12.8GB VRAM with our free notebooks: https://unsloth.ai/docs/new/faster-moe
Train gpt-oss locally on 12.8GB VRAM with our free notebooks: https://unsloth.ai/docs/new/faster-moe
- 1 reply
sergiopaniego
posted
an
update
13 days ago
Post
430
if you're looking for a good first issue to get your open-source journey started, you could contribute to this TRL issue by documenting one impactful paper in the docs
we have a broad list to cover!! 🧐
https://github.com/huggingface/trl/issues/4407
we have a broad list to cover!! 🧐
https://github.com/huggingface/trl/issues/4407
danielhanchen
posted
an
update
17 days ago
Post
3669
We created a tool-calling guide for local LLMs!
Learn how to use any open model like Qwen3-Coder-Next and GLM-4.7-Flash for function calling.
Guide: https://unsloth.ai/docs/basics/tool-calling-guide-for-local-llms
We provide hands-on examples for: story writing, Python execution, terminal tool calls, maths and more.
Learn how to use any open model like Qwen3-Coder-Next and GLM-4.7-Flash for function calling.
Guide: https://unsloth.ai/docs/basics/tool-calling-guide-for-local-llms
We provide hands-on examples for: story writing, Python execution, terminal tool calls, maths and more.
-
- 7 replies
danielhanchen
posted
an
update
19 days ago
Post
3742
Qwen releases Qwen3-Coder-Next! 💜 Run the locally on 46GB RAM or less.
Thhe model excels at agentic coding & local use. With 256K context, it delivers similar performance to models with 10-20× more active parameters.
GGUF: unsloth/Qwen3-Coder-Next-GGUF
Guide: https://unsloth.ai/docs/models/qwen3-coder-next
Thhe model excels at agentic coding & local use. With 256K context, it delivers similar performance to models with 10-20× more active parameters.
GGUF: unsloth/Qwen3-Coder-Next-GGUF
Guide: https://unsloth.ai/docs/models/qwen3-coder-next
-
-
- 10 replies
sergiopaniego
posted
an
update
24 days ago
Post
479
Meet the Post-Training Toolkit (PTT), which easily integrates with TRL via a single callback, by Aditya Challapally (
@microsoft
):
🔍 Detects training issues early
🛠 Lets you intervene safely
📊 Keeps long training runs stable, auditable & efficient
Microsoft blog: https://devblogs.microsoft.com/engineering-at-microsoft/diagnosing-instability-in-production-scale-agent-rl/
Integration guide: https://huggingface.co/docs/trl/main/en/ptt_integration
Code: https://github.com/microsoft/post-training-toolkit
🔍 Detects training issues early
🛠 Lets you intervene safely
📊 Keeps long training runs stable, auditable & efficient
Microsoft blog: https://devblogs.microsoft.com/engineering-at-microsoft/diagnosing-instability-in-production-scale-agent-rl/
Integration guide: https://huggingface.co/docs/trl/main/en/ptt_integration
Code: https://github.com/microsoft/post-training-toolkit
alvarobartt
posted
an
update
25 days ago
Post
3027
💥
💡 Alternatively, you can also set the
hf-mem v0.4.1 now also estimates KV cache memory requirements for any context length and batch size with the --experimental flag!uvx hf-mem --model-id ... --experimental will automatically pull the required information from the Hugging Face Hub to include the KV cache estimation, when applicable.💡 Alternatively, you can also set the
--max-model-len, --batch-size and --kv-cache-dtype arguments (à la vLLM) manually if preferred.
-
- 1 reply
sergiopaniego
posted
an
update
25 days ago
Post
2564
New TRL + OpenEnv example! 💥
Fine tune an LLM for playing Sudoku using an RL env via OpenEnv
Includes a script that runs on 1 or multiple GPUs with vLLM, plus a Colab-ready notebook.
Enjoy!
Notebook: https://colab.research.google.com/github/huggingface/trl/blob/main/examples/notebooks/openenv_sudoku_grpo.ipynb
Script: https://github.com/huggingface/trl/blob/main/examples/scripts/openenv/sudoku.py
Fine tune an LLM for playing Sudoku using an RL env via OpenEnv
Includes a script that runs on 1 or multiple GPUs with vLLM, plus a Colab-ready notebook.
Enjoy!
Notebook: https://colab.research.google.com/github/huggingface/trl/blob/main/examples/notebooks/openenv_sudoku_grpo.ipynb
Script: https://github.com/huggingface/trl/blob/main/examples/scripts/openenv/sudoku.py
- 1 reply
danielhanchen
posted
an
update
25 days ago
Post
3423
You can now run Kimi K2.5 locally! 🔥
We shrank the 1T model to 240GB (-60%) via Dynamic 1-bit.
Get >40 tok/s on 242GB or 622GB VRAM/RAM for near full precision.
GGUF: unsloth/Kimi-K2.5-GGUF
Guide: https://unsloth.ai/docs/models/kimi-k2.5
We shrank the 1T model to 240GB (-60%) via Dynamic 1-bit.
Get >40 tok/s on 242GB or 622GB VRAM/RAM for near full precision.
GGUF: unsloth/Kimi-K2.5-GGUF
Guide: https://unsloth.ai/docs/models/kimi-k2.5
-
- 7 replies
sergiopaniego
posted
an
update
27 days ago
Post
2170
Date idea: read the entire Transformers v5.0.0 release notes
Officially stable now: https://github.com/huggingface/transformers/releases/tag/v5.0.0
Officially stable now: https://github.com/huggingface/transformers/releases/tag/v5.0.0
- 1 reply
mlabonne
authored
2
papers
about 1 month ago
danielhanchen
posted
an
update
about 1 month ago
Post
2615
You can now fine-tune embedding models in our free Unsloth notebook! 🤗
Fine-tuning embedding models improves retrieval & RAG by aligning vectors to your domain-specific notion of similarity, improving search, clustering, and recommendations on your data.
⭐ Blog + Notebooks: https://unsloth.ai/docs/new/embedding-finetuning
Unsloth trains embedding models 1.8-3.3x faster with 20% less VRAM, 2x longer context & no accuracy loss vs. FA2 setups.
We'd like to thank Hugging Face and Unsloth contributor: electroglyph for making this possible!
Fine-tuning embedding models improves retrieval & RAG by aligning vectors to your domain-specific notion of similarity, improving search, clustering, and recommendations on your data.
⭐ Blog + Notebooks: https://unsloth.ai/docs/new/embedding-finetuning
Unsloth trains embedding models 1.8-3.3x faster with 20% less VRAM, 2x longer context & no accuracy loss vs. FA2 setups.
We'd like to thank Hugging Face and Unsloth contributor: electroglyph for making this possible!
-
- 3 replies
danielhanchen
posted
an
update
about 1 month ago
Post
2626
Run GLM-4.7-Flash locally on your device with 24GB RAM!🔥
It's the best performing 30B model on SWE-Bench and GPQA. With 200K context, it excels at coding, agents, chat & reasoning.
GGUF: unsloth/GLM-4.7-Flash-GGUF
Guide: https://unsloth.ai/docs/models/glm-4.7-flash
It's the best performing 30B model on SWE-Bench and GPQA. With 200K context, it excels at coding, agents, chat & reasoning.
GGUF: unsloth/GLM-4.7-Flash-GGUF
Guide: https://unsloth.ai/docs/models/glm-4.7-flash
sergiopaniego
posted
an
update
about 1 month ago
Post
1632
FunctionGemma Tuning Lab is a new no-code tool by
@google
that lets you fine-tune a model directly from the browser, with no coding knowledge required, using TRL behind the scenes.
blog: https://developers.googleblog.com/a-guide-to-fine-tuning-functiongemma/
try it out: google/functiongemma-tuning-lab
This example builds on a more advanced one for learning fine-tuning with SFT using TRL: https://ai.google.dev/gemma/docs/functiongemma/finetuning-with-functiongemma
blog: https://developers.googleblog.com/a-guide-to-fine-tuning-functiongemma/
try it out: google/functiongemma-tuning-lab
This example builds on a more advanced one for learning fine-tuning with SFT using TRL: https://ai.google.dev/gemma/docs/functiongemma/finetuning-with-functiongemma
-
- 1 reply
sergiopaniego
posted
an
update
about 1 month ago
Post
841
TRL v0.27.0 is out!! 🥳
It includes GDPO, the latest variant of GRPO for multi-reward RL ✨
GDPO decouples reward normalization to avoid reward collapse and improve per-reward convergence — developed by
@sliuau @SimonX et al.
Explore the paper: GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization (2601.05242)
Explore the full set of changes here:
https://github.com/huggingface/trl/releases/tag/v0.27.0
It includes GDPO, the latest variant of GRPO for multi-reward RL ✨
GDPO decouples reward normalization to avoid reward collapse and improve per-reward convergence — developed by
@sliuau @SimonX et al.
Explore the paper: GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization (2601.05242)
Explore the full set of changes here:
https://github.com/huggingface/trl/releases/tag/v0.27.0