Hugging Face's logo
Activity Feed

AI & ML interests

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

Recent Activity

cmpatino  updated a model 1 day ago
HuggingFaceH4/Tinker-Thinky-SFT-r32
cmpatino  published a model 1 day ago
HuggingFaceH4/Tinker-Thinky-SFT-r32
yjernite  authored a paper 3 days ago
INTIMA: A Benchmark for Human-AI Companionship Behavior
View all activity

sergiopaniego 
posted an update about 6 hours ago
view post
Post
55
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 1 day ago
view post
Post
1408
💥 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 1 day ago
cmpatino 
updated a model 1 day ago
cmpatino 
published a model 1 day ago
IlyasMoutawwakil 
posted an update 2 days ago
view post
Post
2682
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 3 days ago
yjernite 
authored a paper 3 days ago
cmpatino 
in HuggingFaceH4/on-policy-distillation 3 days ago

About lr and evaluation

1
#6 opened 8 days ago by
141forever
IlyasMoutawwakil 
posted an update 7 days ago
view post
Post
2287
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
·
cmpatino 
in HuggingFaceH4/on-policy-distillation 8 days ago

Rephrase dataset description
#5 opened 8 days ago by
cmpatino
kashif 
in HuggingFaceH4/on-policy-distillation 8 days ago

fix token merging

1
#3 opened 8 days ago by
kashif
cmpatino 
in HuggingFaceH4/on-policy-distillation 8 days ago

Experiments setup for reproduction

1
#2 opened about 1 month ago by
charosen

fix token merging

1
#3 opened 8 days ago by
kashif
kashif 
updated a Space 8 days ago
sergiopaniego 
posted an update 10 days ago
view post
Post
1548
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 13 days ago
sergiopaniego 
posted an update 16 days ago
view post
Post
2965
New REPL environment in OpenEnv available! ✨
Used in the Recursive Language Models (RLM) paper by Alex Zhang.

Ready for inference & post-training using trajectories. Handles long contexts:

> Run Python code in a sandbox
> Make recursive calls to LMs
> Explore data programmatically
> Return final result

Docs: https://meta-pytorch.org/OpenEnv/environments/repl/
Inference script: https://github.com/meta-pytorch/OpenEnv/blob/main/examples/repl_oolong_simple.py
sergiopaniego 
posted an update 17 days ago
view post
Post
429
Recursive Language Models (RLM) is a new interface for LLMs with cool ideas by Alex Zhang!

⚠️ LLMs struggle with long prompts → attention overload & lost info
🔄 RLMs inspect, split & call themselves on chunks, then aggregate results
✅ Handles millions of tokens, reduces noise, improves reasoning
💡 System prompt guides recursion
🎯 RLM trajectories can be used for RL training or distillation (OpenEnv+TRL!!)

We're adding it to OpenEnv (with Kashif Rasul): https://github.com/meta-pytorch/OpenEnv/pull/282

More resources:

> Paper: Recursive Language Models (2512.24601)
> Paper blog: https://alexzhang13.github.io/blog/2025/rlm/
> RLM repo: https://github.com/alexzhang13/rlm
  • 2 replies
·
sergiopaniego 
posted an update 21 days ago