Hugging Face's logo

gg-hf-gm
community
Activity Feed

AI & ML interests

None defined yet.

Recent Activity

RyanMullins  updated a model 5 days ago
google/embeddinggemma-300m-qat-q8_0-unquantized
RyanMullins  updated a model 5 days ago
google/embeddinggemma-300m-qat-q4_0-unquantized
RyanMullins  updated a model 5 days ago
google/embeddinggemma-300m
View all activity

sergiopaniego 
posted an update 4 days ago
view post
Post
3782
You can now supercharge your TRL training pipelines with kernels

👷 kernels is new library to load optimized compute kernels directly from the Hub

Combined with TRL, it makes you developer experience smoother & faster.

Check out the new guide to learn more! 🕺

Learn ➡️ https://huggingface.co/docs/trl/main/en/kernels_hub
RyanMullins 
updated 3 models 5 days ago
RyanMullins 
updated a model 5 days ago
Xenova 
updated a model 6 days ago
osanseviero 
updated 2 models 6 days ago
sergiopaniego 
posted an update 12 days ago
view post
Post
406
It's now posible to do end-2-end ML without leaving the @huggingface Hub, by combining TRL + HF jobs + Trackio!!

🐡We just released a full guide explaining the process.

Go check it out!

📖 Guide: https://huggingface.co/docs/trl/main/en/jobs_training

💡 Reminder: HF Jobs is only available for Pro, Team, or Enterprise plans. Yet another reason to upgrade
mlabonne 
posted an update 26 days ago
view post
Post
5551
Liquid just released two 450M and 1.6B param VLMs!

They're super fast and leverage SigLIP2 NaFlex encoders to handle native resolutions without distortion. It's ideal for on-device deployment in constrained environments like phones.

It's available today on Hugging Face, with an inference and a fine-tuning Colab notebooks.

LiquidAI/LFM2-VL-450M
LiquidAI/LFM2-VL-1.6B
sergiopaniego 
posted an update 27 days ago
sergiopaniego 
posted an update 28 days ago
view post
Post
405
New Zero-Shot Object Detectors in transformers! 🥽

We’ve added LLMDet and MM GroundingDINO, plus a demo Space to compare them with others 🖼️

Play with it: ariG23498/zero-shot-od
sergiopaniego 
posted an update 28 days ago
sergiopaniego 
posted an update about 1 month ago
view post
Post
456
Latest TRL release brings major upgrades for multimodal alignment!

We dive into 3 new techniques to improve VLM post-training in our new blog:

🌋 GRPO
🎞️ GSPO
🐙 MPO
➕ vLLM integration for online training w/ transformers backend\

🐡 Blog: https://huggingface.co/blog/trl-vlm-alignment
tomaarsen 
posted an update about 1 month ago
view post
Post
4244
😎 I just published Sentence Transformers v5.1.0, and it's a big one. 2x-3x speedups of SparseEncoder models via ONNX and/or OpenVINO backends, easier distillation data preparation with hard negatives mining, and more:

1️⃣ Faster ONNX and OpenVINO backends for SparseEncoder models
Usage is as simple as backend="onnx" or backend="openvino" when initializing a SparseEncoder to get started, but I also included utility functions for optimization, dynamic quantization, and static quantization, plus benchmarks.

2️⃣ New n-tuple-scores output format from mine_hard_negatives
This new output format is immediately compatible with the MarginMSELoss and SparseMarginMSELoss for training SentenceTransformer, CrossEncoder, and SparseEncoder losses.

3️⃣ Gathering across devices
When doing multi-GPU training using a loss that has in-batch negatives (e.g. MultipleNegativesRankingLoss), you can now use gather_across_devices=True to load in-batch negatives from the other devices too! Essentially a free lunch, pretty big impact potential in my evals.

4️⃣ Trackio support
If you also upgrade transformers, and you install trackio with pip install trackio, then your experiments will also automatically be tracked locally with trackio. Just open up localhost and have a look at your losses/evals, no logins, no metric uploading.

5️⃣ MTEB Documentation
We've added some documentation on evaluating SentenceTransformer models properly with MTEB. It's rudimentary as the documentation on the MTEB side is already great, but it should get you started.

Plus many more smaller features & fixes (crash fixes, compatibility with datasets v4, FIPS compatibility, etc.).

See the full release notes here: https://github.com/UKPLab/sentence-transformers/releases/tag/v5.1.0

Big thanks to all of the contributors for helping with the release, many of the features from this release were proposed by others. I have a big list of future potential features that I'd love to add, but I'm
sergiopaniego 
posted an update about 1 month ago
sergiopaniego 
posted an update about 1 month ago
view post
Post
3417
Want to learn how to align a Vision Language Model (VLM) for reasoning using GRPO and TRL? 🌋

🧑‍🍳 We've got you covered!!

NEW multimodal post training recipe to align a VLM using TRL in @HuggingFace 's Cookbook.

Go to the recipe 👉https://huggingface.co/learn/cookbook/fine_tuning_vlm_grpo_trl

Powered by the latest TRL v0.20 release, this recipe shows how to teach Qwen2.5-VL-3B-Instruct to reason over images 🌋
sergiopaniego 
posted an update about 1 month ago
view post
Post
4515
Just included example scripts for aligning models using GSPO (including VLM example) 🙆‍♂️🙆‍♂️

GSPO is the latest RL alignment algo by @Alibaba_Qwen and it's already supported in the latest TRL v0.20 release.

Super-easy-to-get-started example scripts below, GO run them!👩‍💻👩‍💻

🧑‍🎨 Script: https://github.com/huggingface/trl/blob/main/examples/scripts/gspo.py
🦄 VLM script: https://github.com/huggingface/trl/blob/main/examples/scripts/gspo_vlm.py
🧩 More TRL examples: https://huggingface.co/docs/trl/main/en/example_overview
🧙‍♂️ GSPO paper: Group Sequence Policy Optimization (2507.18071)
sergiopaniego 
posted an update about 1 month ago
view post
Post
346
Did you miss this? 👓

🧙‍♂️vLLM + transformers integration just got upgraded with direct VLM support.

Select a VLM + model_impl=transformers and play via vLLM!
sergiopaniego 
posted an update about 1 month ago
view post
Post
2687
We just released TRL v0.20 with major multimodal upgrades!

👁️ VLM support for GRPO (highly requested by the community!)
🎞️ New GSPO trainer (from @Qwen , released last week, VLM-ready)
🐙 New MPO trainer (multimodal by design, as in the paper)

📝 Full release notes here: https://github.com/huggingface/trl/releases/tag/v0.20.0