sergiopaniego/browsergym-grpo-functiongemma-270m-it-bucket
15.4 MB
Sergio Paniego PRO
sergiopaniego
AI & ML interests
None yet
Recent Activity
posted an update about 1 hour ago
how do you sync a trillion parameter model every RL step without a shared cluster? we just wrote a blog about it, led by @aminediroHF
what I like the most is the way it proves you can use the Hub for basically everything 🧐 → trainer on one machine, vLLM in a HF Space, the wordle env in another HF Space and weights going through a Hub Bucket. no shared cluster, just HTTPS
it works because ~99% of bf16 weights don't change between RL steps so you only sync the diff. 1.2 GB to 25 MB of payload per step
https://huggingface.co/blog/delta-weight-sync liked a Space about 1 hour ago
huggingface-projects/rf-detr-realtime-webcam updated a dataset about 10 hours ago
agents-course/final-certificatesOrganizations
Posts 93
Post
6
how do you sync a trillion parameter model every RL step without a shared cluster? we just wrote a blog about it, led by @aminediroHF
what I like the most is the way it proves you can use the Hub for basically everything 🧐 → trainer on one machine, vLLM in a HF Space, the wordle env in another HF Space and weights going through a Hub Bucket. no shared cluster, just HTTPS
it works because ~99% of bf16 weights don't change between RL steps so you only sync the diff. 1.2 GB to 25 MB of payload per step
https://huggingface.co/blog/delta-weight-sync
what I like the most is the way it proves you can use the Hub for basically everything 🧐 → trainer on one machine, vLLM in a HF Space, the wordle env in another HF Space and weights going through a Hub Bucket. no shared cluster, just HTTPS
it works because ~99% of bf16 weights don't change between RL steps so you only sync the diff. 1.2 GB to 25 MB of payload per step
https://huggingface.co/blog/delta-weight-sync
Articles 19
Article
71
Profiling in PyTorch (Part 1): A Beginner's Guide to torch.profiler
In-depth technical articles and research pieces published by Hugging Face
-
The Ultra-Scale Playbook
🌌3.87kThe ultimate guide to training LLM on large GPU Clusters
-
The Smol Training Playbook
📚3.2kThe secrets to building world-class LLMs
-
Evaluation Guidebook
📝325Explore LLM benchmark scores over time
-
FineVision: Open Data is All You Need
📝225A new open-source dataset for training VLMs
Blog: https://huggingface.co/blog/sergiopaniego/bringing-carla-to-openenv-trl/
In-depth technical articles and research pieces published by Hugging Face
-
The Ultra-Scale Playbook
🌌3.87kThe ultimate guide to training LLM on large GPU Clusters
-
The Smol Training Playbook
📚3.2kThe secrets to building world-class LLMs
-
Evaluation Guidebook
📝325Explore LLM benchmark scores over time
-
FineVision: Open Data is All You Need
📝225A new open-source dataset for training VLMs
spaces 139
pinned
Running on Zero
Agents
Featured
115
VLM Object Understanding
🦀
Explore object detection, visual grounding, keypoint Detecti
pinned
Runtime error
Agents
11
Qwen2-VL-7B
🔥
Ask questions about charts in images
pinned
Running on Zero
Agents
SmolVLM-trl-dpo-rlaif-v
🔥
Generate text from an image and question
pinned
Runtime error
Agents
SmolVLM-trl-sft-ChartQA
🔥
Ask questions about charts in images
Running
Huggingface Static C3b61b
🎯
View and manage your tracking data in an interactive dashboard
Running
Huggingface Static A08598
🎯
View project metrics on an interactive dashboard
models 125
sergiopaniego/browsergym-grpo-functiongemma-270m-it
Text Generation • 0.3B • Updated • 32 • 2
sergiopaniego/qwen3-grpo-requests
Updated
sergiopaniego/reasoning-gym-chain-sum-Qwen3-1.7B-sft
Text Generation • 2B • Updated • 10
sergiopaniego/reasoning-gym-chain-sum-Qwen3-1.7B
Text Generation • 2B • Updated • 221 •
sergiopaniego/carla-vlm-gemma-test
Updated
sergiopaniego/carla-vlm-qwen35-test
Updated
sergiopaniego/carla-vlm-gemma
Updated
sergiopaniego/carla-vlm-qwen35
Updated
sergiopaniego/nemotron-3-sft
Updated
sergiopaniego/Qwen3-0.6B-carla-trolley-escape
0.8B • Updated • 7
datasets 9
sergiopaniego/requests-pr-diff
Viewer • Updated • 1 • 350
sergiopaniego/trl-r2e-test
Viewer • Updated • 1 • 68
sergiopaniego/chain-sum-rollouts
Viewer • Updated • 50 • 31
sergiopaniego/ttt-scripted-smoke
Viewer • Updated • 20 • 24
sergiopaniego/sample_videos
Viewer • Updated • 2 • 22
sergiopaniego/difficult_prompts
Viewer • Updated • 38 • 27
sergiopaniego/ourworldindata_example
Viewer • Updated • 13 • 36 • 1
sergiopaniego/faiss_embeddings
Updated • 24
sergiopaniego/CarlaFollowLanePreviousV
Viewer • Updated • 59.6k • 21