trl-lib/trackio-dataset
Updated
•
3.75k
AI & ML interests
None defined yet.
Recent Activity
View all activity
Upload text_arena_evals.png
#2 opened about 19 hours ago
by
burtenshaw
qgallouedec
updated
a
dataset
3 days ago
qgallouedec
published
a
dataset
5 days ago
sergiopaniego
posted
an
update
5 days ago
Post
2621
Meet OpenEnv 👋, an open ecosystem of environments for intelligent agents. Build, share, and test agents safely and consistently.
Ideal for training with TRL (we include examples🤓), deployment, and community collaboration via the HF Hub
Blog: https://huggingface.co/blog/openenv
Hub for Environments:
openenv
OpenEnv repo: https://github.com/meta-pytorch/OpenEnv
Try it out using TRL: https://huggingface.co/docs/trl/main/en/openenv
Ideal for training with TRL (we include examples🤓), deployment, and community collaboration via the HF Hub
Blog: https://huggingface.co/blog/openenv
Hub for Environments:
openenv
OpenEnv repo: https://github.com/meta-pytorch/OpenEnv
Try it out using TRL: https://huggingface.co/docs/trl/main/en/openenv
qgallouedec
updated
a
Space
6 days ago
sergiopaniego
posted
an
update
12 days ago
Post
1867
New drop! 💥 The VLM Object Understanding Comparison Space now runs with Qwen3-VL-4B and moondream3.
You can compare how models reason about images 🧠
Bonus: thanks to @ariG23498 , you now get auto-suggested prompts to explore faster.
Let’s gooo
sergiopaniego/vlm_object_understanding
You can compare how models reason about images 🧠
Bonus: thanks to @ariG23498 , you now get auto-suggested prompts to explore faster.
Let’s gooo
sergiopaniego/vlm_object_understanding
sergiopaniego
posted
an
update
12 days ago
Post
836
New drop! 💥 The VLM Object Understanding Comparison Space now runs with Qwen3-VL-4B and moondream3.
You can compare how models reason about images 🧠
Bonus: thanks to @ariG23498 , you now get auto-suggested prompts to explore faster.
Let’s gooo
sergiopaniego/vlm_object_understanding
You can compare how models reason about images 🧠
Bonus: thanks to @ariG23498 , you now get auto-suggested prompts to explore faster.
Let’s gooo
sergiopaniego/vlm_object_understanding
sergiopaniego
updated
a
dataset
13 days ago
sergiopaniego
posted
an
update
14 days ago
Post
2265
@Qwen
released their new small and dense VLMs (Qwen3-VL).
They're incredibly capable and one of my all-time favourite VLMs.
🤗 We’ve prepared some resources to help you get started.
> Fine-tune Qwen3-VL-4B with SFT or GRPO (free Colab notebooks):
> SFT: https://colab.research.google.com/github/huggingface/trl/blob/main/examples/notebooks/sft_qwen_vl.ipynb
> GRPO: https://colab.research.google.com/github/huggingface/trl/blob/main/examples/notebooks/grpo_qwen3_vl.ipynb
> Compare object detection vs. Moondream3:
sergiopaniego/vlm_object_understanding
> Fine-tune from the CLI using TRL:
https://github.com/kashif/Qwen3-VL/blob/trl-sft/qwen-vl-finetune/README.md#trl-based-training-single-gpu
They're incredibly capable and one of my all-time favourite VLMs.
🤗 We’ve prepared some resources to help you get started.
> Fine-tune Qwen3-VL-4B with SFT or GRPO (free Colab notebooks):
> SFT: https://colab.research.google.com/github/huggingface/trl/blob/main/examples/notebooks/sft_qwen_vl.ipynb
> GRPO: https://colab.research.google.com/github/huggingface/trl/blob/main/examples/notebooks/grpo_qwen3_vl.ipynb
> Compare object detection vs. Moondream3:
sergiopaniego/vlm_object_understanding
> Fine-tune from the CLI using TRL:
https://github.com/kashif/Qwen3-VL/blob/trl-sft/qwen-vl-finetune/README.md#trl-based-training-single-gpu
lvwerra
authored
a
paper
15 days ago
sergiopaniego
posted
an
update
19 days ago
Post
1446
Super nice intro to fine-tuning with TRL, just dropped by
@google
(runs free on Colab)!
They use SFT + QLoRA to fine-tune the tiny Gemma 3 270M model for emoji generation
Here’s what the fine-tuned model generates for the prompt: “I'm learning to tweet” → 🐦🗣💻
Colab: https://colab.research.google.com/github/google-gemini/gemma-cookbook/blob/main/Demos/Emoji-Gemma-on-Web/resources/Fine_tune_Gemma_3_270M_for_emoji_generation.ipynb
Try it out: google/emoji-gemma
Learn more: https://developers.googleblog.com/en/own-your-ai-fine-tune-gemma-3-270m-for-on-device/
They use SFT + QLoRA to fine-tune the tiny Gemma 3 270M model for emoji generation
Here’s what the fine-tuned model generates for the prompt: “I'm learning to tweet” → 🐦🗣💻
Colab: https://colab.research.google.com/github/google-gemini/gemma-cookbook/blob/main/Demos/Emoji-Gemma-on-Web/resources/Fine_tune_Gemma_3_270M_for_emoji_generation.ipynb
Try it out: google/emoji-gemma
Learn more: https://developers.googleblog.com/en/own-your-ai-fine-tune-gemma-3-270m-for-on-device/
sergiopaniego
posted
an
update
22 days ago
Post
2396
Online training methods (e.g., GRPO) require real-time generation, a compute- and memory-heavy bottleneck.
TRL has built-in vLLM support and in this new recipe, we show how to leverage it for efficient online training. Run on Colab ⚡, scale to multi-GPU/multi-node!
🧑🍳 recipe: https://huggingface.co/learn/cookbook/grpo_vllm_online_training
TRL has built-in vLLM support and in this new recipe, we show how to leverage it for efficient online training. Run on Colab ⚡, scale to multi-GPU/multi-node!
🧑🍳 recipe: https://huggingface.co/learn/cookbook/grpo_vllm_online_training
- 1 reply
sergiopaniego
posted
an
update
23 days ago
Post
2883
A few days ago, Thinking Machines Lab released “LoRA Without Regret”, showing that LoRA can match full fine-tuning performance when configured right.
Naturally, we decided to reproduce the results with TRL and release a guide!
https://huggingface.co/docs/trl/main/en/lora_without_regret
Naturally, we decided to reproduce the results with TRL and release a guide!
https://huggingface.co/docs/trl/main/en/lora_without_regret
sergiopaniego
posted
an
update
28 days ago
Post
583
Want to deploy open models using vLLM as the inference engine?
We just released a step-by-step guide on how to do it with @huggingface Inference Endpoints, now available in the vLLM docs.
let the gpus go brrr
https://docs.vllm.ai/en/latest/deployment/frameworks/hf_inference_endpoints.html
We just released a step-by-step guide on how to do it with @huggingface Inference Endpoints, now available in the vLLM docs.
let the gpus go brrr
https://docs.vllm.ai/en/latest/deployment/frameworks/hf_inference_endpoints.html
sergiopaniego
posted
an
update
about 1 month ago
Post
485
You need to try this tool! 🫡
My colleague @Molbap built an interactive HF Space to explore the modular support of open models in transformers over time
👀 You’ll spot things like 🦙 llama defining many models or which ones could be modular next
Try it: Molbap/transformers-modular-refactor
My colleague @Molbap built an interactive HF Space to explore the modular support of open models in transformers over time
👀 You’ll spot things like 🦙 llama defining many models or which ones could be modular next
Try it: Molbap/transformers-modular-refactor
sergiopaniego
posted
an
update
about 1 month ago
Post
475
How fast can you create an endpoint in Hugging Face Inference Endpoints with a new model + vLLM to deploy a state-of-the-art OCR model?
Let’s break it down step by step.
1️⃣ Create your endpoint
Go to Hugging Face Endpoints → + NEW
Select Deploy from Hub → rednote-hilab/dots.ocr → Configure 🛠️
2️⃣ Configure hardware & container
Pick hardware: AWS/GPU/L4 ⚡
Set container: vLLM 🐇
Click Create ✅
3️⃣ Update endpoint settings
Container: Container URI: vllm/vllm-openai:nightly → Update
Advanced: add flag --trust-remote-code → Update ⚠️
4️⃣ Run inference
Download the script 📝: ariG23498/useful-scripts
Set your HF_TOKEN and update base_url in the script.
Run it. ✅
Your OCR model is now live via HF Inference Endpoints!
Let’s break it down step by step.
1️⃣ Create your endpoint
Go to Hugging Face Endpoints → + NEW
Select Deploy from Hub → rednote-hilab/dots.ocr → Configure 🛠️
2️⃣ Configure hardware & container
Pick hardware: AWS/GPU/L4 ⚡
Set container: vLLM 🐇
Click Create ✅
3️⃣ Update endpoint settings
Container: Container URI: vllm/vllm-openai:nightly → Update
Advanced: add flag --trust-remote-code → Update ⚠️
4️⃣ Run inference
Download the script 📝: ariG23498/useful-scripts
Set your HF_TOKEN and update base_url in the script.
Run it. ✅
Your OCR model is now live via HF Inference Endpoints!
sergiopaniego
posted
an
update
about 1 month ago
Post
3454
💥 Tons of new material just landed in the smol-course! 🧑💻
> evaluation
> alignment
> VLMs
> quizzes
> assignments!
> certificates!👩🎓
go learn! 👉 https://huggingface.co/learn/smol-course/unit0/1
> evaluation
> alignment
> VLMs
> quizzes
> assignments!
> certificates!👩🎓
go learn! 👉 https://huggingface.co/learn/smol-course/unit0/1
- 1 reply
sergiopaniego
posted
an
update
about 1 month ago
Post
1393
This summer TRL leveled up for multimodal alignment 🌞
✅ New VLM alignment methods (MPO, GRPO, GSPO)
✅ Extended RLOO & Online DPO for VLMs
✅ Native SFT support
✅ Ready-to-use training scripts
🔗 https://huggingface.co/blog/trl-vlm-alignment
✅ New VLM alignment methods (MPO, GRPO, GSPO)
✅ Extended RLOO & Online DPO for VLMs
✅ Native SFT support
✅ Ready-to-use training scripts
🔗 https://huggingface.co/blog/trl-vlm-alignment
sergiopaniego
posted
an
update
about 1 month ago
Post
561
You can now use any open LLM as your coding assistant in VS Code with the
@huggingface
Provider for GitHub Copilot Chat.
Just pick your fav open model and start building!
Vibe-coding is all you need!?
learn more: https://huggingface.co/docs/inference-providers/en/guides/vscode
Just pick your fav open model and start building!
Vibe-coding is all you need!?
learn more: https://huggingface.co/docs/inference-providers/en/guides/vscode
- 1 reply
sergiopaniego
posted
an
update
about 1 month ago
Post
449
Training long-context LLMs is getting easier!
TRL now supports Context Parallelism (CP), letting you scale sequences across multiple GPUs, even multi-node setups, seamlessly 💆
Combine TRL and accelerate, and you can run it effortlessly!
With 8 GPUs, CP enables 300k+ token sequences while keeping throughput reasonable.
Works for both full fine-tuning and LoRA, unlocking contexts that used to hit OOM 📈
Check out the full guide here 👉 https://huggingface.co/docs/trl/main/en/distributing_training#context-parallelism
If you want to learn more about Context Parallelism, check out the Ultrascale Playbook 👉 nanotron/ultrascale-playbook
TRL now supports Context Parallelism (CP), letting you scale sequences across multiple GPUs, even multi-node setups, seamlessly 💆
Combine TRL and accelerate, and you can run it effortlessly!
With 8 GPUs, CP enables 300k+ token sequences while keeping throughput reasonable.
Works for both full fine-tuning and LoRA, unlocking contexts that used to hit OOM 📈
Check out the full guide here 👉 https://huggingface.co/docs/trl/main/en/distributing_training#context-parallelism
If you want to learn more about Context Parallelism, check out the Ultrascale Playbook 👉 nanotron/ultrascale-playbook