huggingface-course/supervised-finetuning_quiz_student_responses
Viewer • Updated • 10 • 938 • 4
AI & ML interests
A central place for all models and datasets created in the HuggingFace course.
Recent Activity
View all activity
burtenshaw
updated a
dataset about 23 hours ago
sergiopaniego
posted an update 1 day ago
Post
111
Frontier agents are this good partly because the model was trained inside the very harness it ships with.
NVIDIA's new paper "Polar: Agentic RL on Any Harness at Scale" brings that recipe to the open: it turns coding harnesses like Codex, Claude Code, Qwen Code or Pi into RL training environments without touching their internals.
The core idea: every agent, however complex or closed, talks to a model through an API, so they put a proxy there. The harness runs exactly like in production while the proxy records prompts, sampled token ids and logprobs. Trajectories get rebuilt outside, token faithful, so gradients hit the exact tokens the policy sampled.
The gains are consistent across all four harnesses. Same Qwen3.5-4B, plain GRPO, evaluated on SWE-Bench Verified:
Codex 3.8 → 26.4 (+22.6)
Claude Code 29.8 → 34.6 (+4.8)
Qwen Code 34.6 → 35.2 (+0.6)
Pi 34.2 → 40.4 (+6.2)
The biggest gains appear on unfamiliar execution paths, Codex being the clearest case. The takeaway: you are not just training a model, you are training the model + harness system.
Two engineering pieces make it work at scale. Async worker pools isolate container boots (CPU), agent execution (GPU) and long tail test runs, so slow runtimes never block the GPUs. And prefix merging stitches hundreds of captured API calls back into contiguous traces: 5.4x faster trainer updates and rollout GPUs at 88% utilization.
It also doubles as an SFT data factory: 504 test verified agent traces from a 122B teacher, multi-turn conversations averaging 104 messages each, coming to the Hub under Apache 2.0 (release pending review).
Paper authors: Binfeng Xu, Hao Zhang, Shaokun Zhang, Songyang Han, Mingjie Liu, Jian Hu, Shizhe Diao, Zhenghui Jin, Yunheng Zou, Michael Demoret, Jan Kautz and Yi Dong.
> Paper: Polar: Agentic RL on Any Harness at Scale (2605.24220)
> Code: https://github.com/NVIDIA-NeMo/ProRL-Agent-Server
> Training data: NovaSky-AI/SkyRL-v0-293-data
NVIDIA's new paper "Polar: Agentic RL on Any Harness at Scale" brings that recipe to the open: it turns coding harnesses like Codex, Claude Code, Qwen Code or Pi into RL training environments without touching their internals.
The core idea: every agent, however complex or closed, talks to a model through an API, so they put a proxy there. The harness runs exactly like in production while the proxy records prompts, sampled token ids and logprobs. Trajectories get rebuilt outside, token faithful, so gradients hit the exact tokens the policy sampled.
The gains are consistent across all four harnesses. Same Qwen3.5-4B, plain GRPO, evaluated on SWE-Bench Verified:
Codex 3.8 → 26.4 (+22.6)
Claude Code 29.8 → 34.6 (+4.8)
Qwen Code 34.6 → 35.2 (+0.6)
Pi 34.2 → 40.4 (+6.2)
The biggest gains appear on unfamiliar execution paths, Codex being the clearest case. The takeaway: you are not just training a model, you are training the model + harness system.
Two engineering pieces make it work at scale. Async worker pools isolate container boots (CPU), agent execution (GPU) and long tail test runs, so slow runtimes never block the GPUs. And prefix merging stitches hundreds of captured API calls back into contiguous traces: 5.4x faster trainer updates and rollout GPUs at 88% utilization.
It also doubles as an SFT data factory: 504 test verified agent traces from a 122B teacher, multi-turn conversations averaging 104 messages each, coming to the Hub under Apache 2.0 (release pending review).
Paper authors: Binfeng Xu, Hao Zhang, Shaokun Zhang, Songyang Han, Mingjie Liu, Jian Hu, Shizhe Diao, Zhenghui Jin, Yunheng Zou, Michael Demoret, Jan Kautz and Yi Dong.
> Paper: Polar: Agentic RL on Any Harness at Scale (2605.24220)
> Code: https://github.com/NVIDIA-NeMo/ProRL-Agent-Server
> Training data: NovaSky-AI/SkyRL-v0-293-data
sergiopaniego
posted an update 3 days ago
Post
138
The recording from our talk: "From Responses To Trajectories: Multi-Turn and Multi-Environment RL" from PyTorch Conf Europe is live!
@kashif and I covered the latest advances in multi-turn GRPO in TRL: trajectories, tool use, envs, and agentic post-training at scale
https://www.youtube.com/watch?v=rPBeXFntJSU
@kashif and I covered the latest advances in multi-turn GRPO in TRL: trajectories, tool use, envs, and agentic post-training at scale
https://www.youtube.com/watch?v=rPBeXFntJSU
sergiopaniego
posted an update 4 days ago
Post
107
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
sergiopaniego
posted an update 5 days ago
Post
2277
most multi-turn RL loops have a silent bug: you decode the model's output to detect tool calls, then re-tokenize the conversation for the next turn. BPE isn't invertible, so decode then re-encode can land on different ids. gradient ends up on tokens the model never sampled. no crash, just quietly wrong math and broken training
@qgallouedec wrote a super educational blog on MITO (message-in, token-out) vs TITO (token-in, token-out) and how you might fix the problem above
go read it 🤓
https://qgallouedec-tito.hf.space/
@qgallouedec wrote a super educational blog on MITO (message-in, token-out) vs TITO (token-in, token-out) and how you might fix the problem above
go read it 🤓
https://qgallouedec-tito.hf.space/
sergiopaniego
posted an update 5 days ago
Post
6218
new banger blog alert 🚨
@ariG23498 is starting a blog series about profiling in pytorch and part 1 just dropped
takes you from the simplest scenario to actually knowing what your gpu is doing. if you have never opened a profiler trace this is where you start
covers
find it here: https://huggingface.co/blog/torch-profiler
@ariG23498 is starting a blog series about profiling in pytorch and part 1 just dropped
takes you from the simplest scenario to actually knowing what your gpu is doing. if you have never opened a profiler trace this is where you start
covers
torch.profiler from scratch. reading tables and traces, overhead bound vs compute bound, the full dispatch chain from python to gpu kernels, and what torch.compile is actually fusing under the hoodfind it here: https://huggingface.co/blog/torch-profiler
- 1 reply
sergiopaniego
posted an update 8 days ago
Post
161
If you have a github repo, you basically have an RL training environment
We're introducing Repo2RLEnv (built by @AdithyaSK ), a tool that mines PRs, commits, CVEs and turns them into verifiable sandboxed tasks with real reward signals, automatically
Outputs to Harbor spec so you can plug it straight into RL training or coding-agent eval
> repo: https://github.com/huggingface/Repo2RLEnv
> collection with envs: https://huggingface.co/collections/AdithyaSK/repo2rlenv-verifiable-rl-environments
We're introducing Repo2RLEnv (built by @AdithyaSK ), a tool that mines PRs, commits, CVEs and turns them into verifiable sandboxed tasks with real reward signals, automatically
Outputs to Harbor spec so you can plug it straight into RL training or coding-agent eval
> repo: https://github.com/huggingface/Repo2RLEnv
> collection with envs: https://huggingface.co/collections/AdithyaSK/repo2rlenv-verifiable-rl-environments
sergiopaniego
posted an update 9 days ago
Post
228
periodic reminder 🧐
some HF blog posts use a special template, long-form, animated, super deep
I keep them all in one collection that gets updated every time a new one drops so you don't lose track
https://hf.co/collections/sergiopaniego/research-and-long-form-blog-posts
spot one missing? let me know
some HF blog posts use a special template, long-form, animated, super deep
I keep them all in one collection that gets updated every time a new one drops so you don't lose track
https://hf.co/collections/sergiopaniego/research-and-long-form-blog-posts
spot one missing? let me know
sergiopaniego
posted an update 12 days ago
Post
9952
Harness, Scaffold, Context Engineering, Agent... do you actually know what they mean?
We wrote an AI agent glossary and tried to make sense of it all with simple definitions and real examples
↓ go read it ↓
https://huggingface.co/blog/agent-glossary
We wrote an AI agent glossary and tried to make sense of it all with simple definitions and real examples
↓ go read it ↓
https://huggingface.co/blog/agent-glossary
- 2 replies
sergiopaniego
posted an update 29 days ago
Post
1884
OpenEnv is growing fast in tutorials. If you're looking to get started with RL environments, check them out
> evaluate your agents using OpenEnv
> learn how rewards work via rubrics
> connect agents via MCP
> many moreeeee!
anything you think it's missing?
https://meta-pytorch.org/OpenEnv/tutorials/index.html
> evaluate your agents using OpenEnv
> learn how rewards work via rubrics
> connect agents via MCP
> many moreeeee!
anything you think it's missing?
https://meta-pytorch.org/OpenEnv/tutorials/index.html
sergiopaniego
posted an update about 1 month ago
Post
872
OpenEnv already ships 🚢 with a ready-to-deploy RLM environment on free HF Spaces
Drop "Attention Is All You Need", write code that spawns parallel LLM calls → ✅ correct answer, reward 1.0, in 4.2s
Run GRPO (TRL) → model learns to write that search strategy itself
test it yourself → sergiopaniego/repl-env
check out OpenEnv → https://github.com/meta-pytorch/OpenEnv
Drop "Attention Is All You Need", write code that spawns parallel LLM calls → ✅ correct answer, reward 1.0, in 4.2s
Run GRPO (TRL) → model learns to write that search strategy itself
test it yourself → sergiopaniego/repl-env
check out OpenEnv → https://github.com/meta-pytorch/OpenEnv
sergiopaniego
posted an update about 2 months ago
Post
1423
Earlier this month, Apple introduced Simple Self-Distillation: a fine-tuning method that improves models on coding tasks just by sampling from the model and training on its own outputs with plain cross-entropy
And… it's already supported in TRL, built by Kashif Rasul. you can really feel the pace of development in the team 🐎
Paper by Ruixiang ZHANG, He Bai, Huangjie Zheng, Navdeep Jaitly, Ronan Collobert, Yizhe Zhang at Apple 🍎
How it works: the model generates completions at a training-time temperature (T_train) with top_k/top_p truncation, then fine-tunes on them with plain cross-entropy. no labels or verifier needed
You can try it right away with this ready-to-run example (Qwen3-4B on rStar-Coder):
https://github.com/huggingface/trl/blob/main/trl/experimental/ssd/ssd.py
or benchmark a checkpoint with the eval script:
https://github.com/huggingface/trl/blob/main/trl/experimental/ssd/ssd_eval.py
One neat insight from the paper: T_train and T_eval compose into an effective T_eff = T_train × T_eval, so a broad band of configs works well. even very noisy samples still help
Want to dig deeper?
Paper: Embarrassingly Simple Self-Distillation Improves Code Generation (2604.01193)
Trainer docs: https://huggingface.co/docs/trl/main/en/ssd_trainer
And… it's already supported in TRL, built by Kashif Rasul. you can really feel the pace of development in the team 🐎
Paper by Ruixiang ZHANG, He Bai, Huangjie Zheng, Navdeep Jaitly, Ronan Collobert, Yizhe Zhang at Apple 🍎
How it works: the model generates completions at a training-time temperature (T_train) with top_k/top_p truncation, then fine-tunes on them with plain cross-entropy. no labels or verifier needed
You can try it right away with this ready-to-run example (Qwen3-4B on rStar-Coder):
https://github.com/huggingface/trl/blob/main/trl/experimental/ssd/ssd.py
or benchmark a checkpoint with the eval script:
https://github.com/huggingface/trl/blob/main/trl/experimental/ssd/ssd_eval.py
One neat insight from the paper: T_train and T_eval compose into an effective T_eff = T_train × T_eval, so a broad band of configs works well. even very noisy samples still help
Want to dig deeper?
Paper: Embarrassingly Simple Self-Distillation Improves Code Generation (2604.01193)
Trainer docs: https://huggingface.co/docs/trl/main/en/ssd_trainer
sergiopaniego
posted an update about 2 months ago
Post
505
Great experience yesterday at PyTorch Conf Europe in Paris 🇫🇷
We (w/ @kashif ) talked about training LLMs through interaction, using trajectories across games, browsers, or simulators
Room was packed, a clear sign of interest in where RL post-training is heading.
sharing the slides! 🤓
https://drive.google.com/file/d/16k7YRnf5EJEo0XjXGlRJ_hVeLoFWKyNP/view?usp=sharing
We (w/ @kashif ) talked about training LLMs through interaction, using trajectories across games, browsers, or simulators
Room was packed, a clear sign of interest in where RL post-training is heading.
sharing the slides! 🤓
https://drive.google.com/file/d/16k7YRnf5EJEo0XjXGlRJ_hVeLoFWKyNP/view?usp=sharing
sergiopaniego
posted an update 2 months ago
Post
2896
Gemma 4 💎 is here and it’s strong!
to celebrate, we’re rolling out in TRL:
> support for multimodal tool responses for environments (OpenEnv)
> an example to train it in CARLA for autonomous driving with image-based tool calls
go check it out 🏎️🏎️
blog: https://huggingface.co/blog/gemma4
script: https://github.com/huggingface/trl/blob/main/examples/scripts/openenv/carla_vlm_gemma.py
to celebrate, we’re rolling out in TRL:
> support for multimodal tool responses for environments (OpenEnv)
> an example to train it in CARLA for autonomous driving with image-based tool calls
go check it out 🏎️🏎️
blog: https://huggingface.co/blog/gemma4
script: https://github.com/huggingface/trl/blob/main/examples/scripts/openenv/carla_vlm_gemma.py
sergiopaniego
posted an update 2 months ago
Post
2106
TRL is officially an adult 🥳
excited to announce TRL v1.0❗️
head to the blog to see how we got here and what’s next for this post-training library, designed to keep pace with the field
https://huggingface.co/blog/trl-v1
excited to announce TRL v1.0❗️
head to the blog to see how we got here and what’s next for this post-training library, designed to keep pace with the field
https://huggingface.co/blog/trl-v1
- 2 replies
sergiopaniego
posted an update 3 months ago
Post
844
ICYMI, great blog by @kashif and @stas on Ulysses Sequence Parallelism: train with million-token contexts
on 4×H100s: 12x longer sequences, 3.7x throughput
learn how to integrate it with Accelerate, Transformers, and TRL ⤵️
https://huggingface.co/blog/ulysses-sp
on 4×H100s: 12x longer sequences, 3.7x throughput
learn how to integrate it with Accelerate, Transformers, and TRL ⤵️
https://huggingface.co/blog/ulysses-sp
sergiopaniego
posted an update 3 months ago
Post
504
We just released a big blog surveying 16 OSS frameworks for async RL training of LLMs!
We're building a new async GRPO trainer for TRL and as first step, we needed to understand how the ecosystem solves this problem today.
The problem: in synchronous RL training, generation dominates wall-clock time. 32K-token rollouts on a 32B model take hours while training GPUs sit completely idle. With reasoning models and agentic RL making rollouts longer and more variable, this only gets worse.
The ecosystem converged on the same fix: separate inference + training onto different GPU pools, rollout buffer, and async weight sync.
We compared 16 frameworks across 7 axes: orchestration, buffer design, weight sync, staleness management, partial rollouts, LoRA, and MoE support.
This survey is step one. The async GRPO trainer for TRL is next!
https://huggingface.co/blog/async-rl-training-landscape
We're building a new async GRPO trainer for TRL and as first step, we needed to understand how the ecosystem solves this problem today.
The problem: in synchronous RL training, generation dominates wall-clock time. 32K-token rollouts on a 32B model take hours while training GPUs sit completely idle. With reasoning models and agentic RL making rollouts longer and more variable, this only gets worse.
The ecosystem converged on the same fix: separate inference + training onto different GPU pools, rollout buffer, and async weight sync.
We compared 16 frameworks across 7 axes: orchestration, buffer design, weight sync, staleness management, partial rollouts, LoRA, and MoE support.
This survey is step one. The async GRPO trainer for TRL is next!
https://huggingface.co/blog/async-rl-training-landscape
sergiopaniego
posted an update 3 months ago
Post
466
Nemotron 3 Super by @nvidia is here! NVIDIA's hybrid Mamba2/Transformer models are now natively supported in transformers (no trust_remote_code needed)
Fine-tune them with TRL in just a few lines of code. Notebook + script included to get started right away. goooo!
- Notebook: https://colab.research.google.com/github/huggingface/trl/blob/main/examples/notebooks/sft_nemotron_3.ipynb
- Script: https://github.com/huggingface/trl/blob/main/examples/scripts/sft_nemotron_3.py
- Collection with all the models: https://huggingface.co/collections/nvidia/nvidia-nemotron-v3
Fine-tune them with TRL in just a few lines of code. Notebook + script included to get started right away. goooo!
- Notebook: https://colab.research.google.com/github/huggingface/trl/blob/main/examples/notebooks/sft_nemotron_3.ipynb
- Script: https://github.com/huggingface/trl/blob/main/examples/scripts/sft_nemotron_3.py
- Collection with all the models: https://huggingface.co/collections/nvidia/nvidia-nemotron-v3
sergiopaniego
posted an update 3 months ago
Post
686
did you know you can train agentic models with RL deploying the environments on HF Spaces? 🤗
with TRL + OpenEnv, your training script connects to remote environments hosted as Spaces
want to train faster? → just add more Spaces (TRL handles the parallelization natively)
we used this to train a model to solve the trolley problem in CARLA. 2 HF Spaces running a full driving simulator, each on a T4 GPU
full write-up with code and results → https://huggingface.co/blog/sergiopaniego/bringing-carla-to-openenv-trl
with TRL + OpenEnv, your training script connects to remote environments hosted as Spaces
want to train faster? → just add more Spaces (TRL handles the parallelization natively)
we used this to train a model to solve the trolley problem in CARLA. 2 HF Spaces running a full driving simulator, each on a T4 GPU
full write-up with code and results → https://huggingface.co/blog/sergiopaniego/bringing-carla-to-openenv-trl