Hugging Face's logo
Activity Feed

AI & ML interests

Aligning LLMs to be helpful, honest, harmless, and huggy (H4)

Recent Activity

lewtun  submitted a paper 6 days ago
Single-minus gluon tree amplitudes are nonzero
lewtun  submitted a paper 7 days ago
Reasoning Cache: Continual Improvement Over Long Horizons via Short-Horizon RL
cmpatino  updated a model 9 days ago
HuggingFaceH4/KD-Tinker
View all activity

qgallouedec 
posted an update about 2 hours ago
view post
Post
21
@CohereLabs just released 🌿 Tiny Aya: a fully open-source 3B parameter model that speaks 70+ languages 🌍! But there’s a catch:

Tiny Aya is just a language model. It doesn’t support tool calling, the key capability that turns frontier models into powerful *agents*.
So the real question is:

How hard is it to turn Tiny Aya into an agent?

Turns out… it’s simple, thanks to Hugging Face TRL.
We’re sharing a hands-on example showing how to train Tiny Aya to turn it into a tool-calling agent using TRL, unlocking what could become the first *massively multilingual open agent*.

Small model. Global reach. Agent capabilities.

👉 https://github.com/huggingface/trl/blob/main/examples/notebooks/sft_tool_calling.ipynb
sergiopaniego 
posted an update about 23 hours ago
lewtun 
submitted a paper to Daily Papers 6 days ago
sergiopaniego 
posted an update 6 days ago
lewtun 
submitted a paper to Daily Papers 7 days ago
albertvillanova 
posted an update 8 days ago
view post
Post
1551
5 years already working in democratizing AI 🤗
Grateful to be part of such an awesome team making it happen every day.
cmpatino 
updated a model 9 days ago
sergiopaniego 
posted an update 10 days ago
view post
Post
410
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
cmpatino 
in HuggingFaceH4/on-policy-distillation 14 days ago

How to reproduce the results in your blog?

4
#7 opened 20 days ago by
141forever
cmpatino 
published a model 16 days ago
sergiopaniego 
posted an update 21 days ago
view post
Post
471
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
alvarobartt 
posted an update 22 days ago
view post
Post
2997
💥 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 22 days ago
IlyasMoutawwakil 
posted an update 23 days ago
view post
Post
3016
Transformers v5 just landed! 🚀
It significantly unifies and reduces modeling code across architectures, while opening the door to a whole new class of performance optimizations.

My favorite new feature? 🤔
The new dynamic weight loader + converter. Here’s why 👇

Over the last few months, the core Transformers maintainers built an incredibly fast weight loader, capable of converting tensors on the fly while loading them in parallel threads. This means we’re no longer constrained by how parameters are laid out inside the safetensors weight files.

In practice, this unlocks two big things:
- Much more modular modeling code. You can now clearly see how architectures build on top of each other (DeepSeek v2 → v3, Qwen v2 → v3 → MoE, etc.). This makes shared bottlenecks obvious and lets us optimize the right building blocks once, for all model families.
- Performance optimizations beyond what torch.compile can do alone. torch.compile operates on the computation graph, but it can’t change parameter layouts. With the new loader, we can restructure weights at load time: fusing MoE expert projections, merging attention QKV projections, and enabling more compute-dense kernels that simply weren’t possible before.

Personally, I'm honored to have contributed in this direction, including the work on optimizing MoE implementations and making modeling code more torch-exportable, so these optimizations can be ported cleanly across runtimes.

Overall, Transformers v5 is a strong signal of where the community and industry are converging: Modularity and Performance, without sacrificing Flexibility.

Transformers v5 makes its signature from_pretrained an entrypoint where you can mix and match:
- Parallelism
- Quantization
- Custom kernels
- Flash/Paged attention
- Continuous batching
- ...

Kudos to everyone involved! I highly recommend the:
Release notes: https://github.com/huggingface/transformers/releases/tag/v5.0.0
Blog post: https://huggingface.co/blog/transformers-v5
·
sergiopaniego 
posted an update 24 days ago
yjernite 
authored a paper 24 days ago
cmpatino 
in HuggingFaceH4/on-policy-distillation 24 days ago

About lr and evaluation

2
#6 opened 28 days ago by
141forever
IlyasMoutawwakil 
posted an update 28 days ago
view post
Post
2369
After 2 months of refinement, I'm happy to announce that a lot of Transformers' modeling code is now significantly more torch-compile & export-friendly 🔥

Why it had to be done 👇
PyTorch's Dynamo compiler is increasingly becoming the default interoperability layer for ML systems. Anything that relies on torch.export or torch.compile, from model optimization to cross-framework integrations, benefits directly when models can be captured as a single dynamo-traced graph !

Transformers models are now easier to:
⚙️ Compile end-to-end with torch.compile backends
📦 Export reliably via torch.export and torch.onnx.export
🚀 Deploy to ONNX / ONNX Runtime, Intel Corporation's OpenVINO, NVIDIA AutoDeploy (TRT-LLM), AMD's Quark, Meta's Executorch and more hardware-specific runtimes.

This work aims at unblocking entire TorchDynamo-based toolchains that rely on exporting Transformers across runtimes and accelerators.

We are doubling down on Transformers commitment to be a first-class citizen of the PyTorch ecosystem, more exportable, more optimizable, and easier to deploy everywhere.

There are definitely some edge-cases that we still haven't addressed so don't hesitate to try compiling / exporting your favorite transformers and to open issues / PRs.

PR in the comments ! More updates coming coming soon !
  • 1 reply
·
sergiopaniego 
posted an update about 1 month ago
view post
Post
1625
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
  • 1 reply
·
sergiopaniego 
posted an update about 1 month ago