sergiopaniego/c3-pathological-static-fda5bc-bucket
0 Bytes
Sergio Paniego PRO
sergiopaniego
AI & ML interests
None yet
Recent Activity
updated a dataset 9 minutes ago
huggingface-projects/Deep-RL-Course-Certification updated a Space about 20 hours ago
sergiopaniego/c3-pathological-static-fda5bc published a Space about 20 hours ago
sergiopaniego/c3-pathological-static-fda5bcOrganizations
Posts 103
Post
45
you can now train your own coding agents with trl + openenv, starting with opencode
we just added end-to-end support for training agent harnesses:
> TRL: a loop-owning training path (AsyncGRPOTrainer + HarnessRolloutWorker) that launches the agent in an OpenEnv session, reads back its trace, reconstructs the training samples, and trains with AsyncGRPO
> OpenEnv: the OpenCode harness environment plus a transparent proxy that forwards the agent's model calls and records each turn's token ids and logprobs
you train the actual opencode agent as is, it runs its own loop and tools and the policy learns from the exact tokens it produced
we're shipping a self-contained example: local subprocess sandbox, DeepCoder problems, validated on Qwen3-8B.
> example: https://github.com/huggingface/trl/blob/main/examples/scripts/openenv/opencode.py
> docs: https://huggingface.co/docs/trl/main/openenv
and we're working actively on both sides so expect more 🤓
we just added end-to-end support for training agent harnesses:
> TRL: a loop-owning training path (AsyncGRPOTrainer + HarnessRolloutWorker) that launches the agent in an OpenEnv session, reads back its trace, reconstructs the training samples, and trains with AsyncGRPO
> OpenEnv: the OpenCode harness environment plus a transparent proxy that forwards the agent's model calls and records each turn's token ids and logprobs
you train the actual opencode agent as is, it runs its own loop and tools and the policy learns from the exact tokens it produced
we're shipping a self-contained example: local subprocess sandbox, DeepCoder problems, validated on Qwen3-8B.
> example: https://github.com/huggingface/trl/blob/main/examples/scripts/openenv/opencode.py
> docs: https://huggingface.co/docs/trl/main/openenv
and we're working actively on both sides so expect more 🤓
Articles 26
Article
38
Profiling in PyTorch (Part 3): Attention is all you profile
spaces 173
pinned
Running on Zero
Agents
Featured
120
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
C3 Pathological Static Fda5bc
🎯
Monitor your projects with an interactive dashboard
Running
C3 Grpo Static Ce85df
🎯
Track and visualize your data with an interactive dashboard
models 143
sergiopaniego/qwen3-0.6b-mbpp-grpo-k2
Text Generation • 0.6B • Updated • 40
sergiopaniego/qwen3-0.6b-mbpp-grpo-k16
Text Generation • 0.6B • Updated • 47
sergiopaniego/qwen3-0.6b-mbpp-grpo-k8
Text Generation • 0.6B • Updated • 47
sergiopaniego/Qwen3.5-4B-sdpo-math-hints
Updated • 1
sergiopaniego/Qwen3.5-4B-sdpo-math-gold
Updated
sergiopaniego/Qwen3.5-4B-sdpo-math-baseline
Updated
sergiopaniego/sdpo-hints
Updated
sergiopaniego/pi-mono-youtube-livestream-2-scripts
Updated • 2
sergiopaniego/gemma-4-E2B-offpolicy-kd-lr1e4
Updated
sergiopaniego/gemma-4-E2B-offpolicy-kd-lr2e4
Updated
datasets 14
sergiopaniego/math-sdpo-hints-plain
Viewer • Updated • 600 • 37
sergiopaniego/math-sdpo-hints
Viewer • Updated • 600 • 43
sergiopaniego/gsm8k-sdpo-plain
Viewer • Updated • 700 • 46
sergiopaniego/gsm8k-sdpo-hints
Viewer • Updated • 700 • 49
sergiopaniego/pi-mono-chat
Viewer • Updated • 886 • 120
sergiopaniego/requests-pr-diff
Viewer • Updated • 1 • 23
sergiopaniego/trl-r2e-test
Viewer • Updated • 1 • 37
sergiopaniego/chain-sum-rollouts
Viewer • Updated • 50 • 13
sergiopaniego/ttt-scripted-smoke
Viewer • Updated • 20 • 17
sergiopaniego/sample_videos
Viewer • Updated • 2 • 32