Hugging Face's logo
Activity Feed Request to join this org

AI & ML interests

None defined yet.

Recent Activity
migurski-wmf  published a dataset 18 days ago
wikimedia/linked-openstreetmap-wikidata-wikipedia-wikivoyage
migurski-wmf  updated a dataset 25 days ago
wikimedia/linked-openstreetmap-wikidata-wikipedia-wikivoyage
migurski-wmf  updated a dataset 29 days ago
wikimedia/linked-openstreetmap-wikidata-wikipedia-wikivoyage
View all activity
albertvillanova 
posted an update 1 day ago
view post
Post
82
Day-0 Mistral Large 4 support in TRL 🚀

- LoRA SFT of the 1T-A52B model on one 8xB300 node, on top of the FP8 checkpoint
- Experts split 8 ways with expert parallelism, everything else sharded with FSDP, all set at load time
- Assistant-only loss out of the box with its training chat template
- ~32.7k tokens per step in ~8 s

Script + Slurm launcher 👇
https://github.com/huggingface/trl/tree/main/examples/sft_mistral_large_4
https://huggingface.co/posts/sergiopaniego/408182860646834
migurski-wmf 
published a dataset 18 days ago
migurski-wmf 
updated a dataset 25 days ago
santhosh 
updated a Space 3 months ago
santhosh 
published a Space 3 months ago
santhosh 
updated a dataset 3 months ago
albertvillanova 
posted an update 4 months ago
view post
Post
4,577
🎉 KTO is now part of the stable TRL API

As of Promote KTO to stable API, KTOTrainer and KTOConfig have graduated from trl.experimental to the stable trl API. https://github.com/huggingface/trl/pull/6175

This one closes out a long road. Over the past 6+ months, the "Align KTO with DPO" effort landed ~90 PRs methodically bringing KTO up to the standard we hold for stable trainers, one carefully-scoped change at a time:
- Feature parity with DPO: full VLM support (incl. multi-image), sync_ref_model, PEFT + Liger, ZeRO-3 + PEFT dtype fix, pad_to_multiple_of, activation offloading, IterableDataset and dict eval_dataset, remove_unused_columns, and reference-logprob precomputation at init.
- Consistency with DPO: aligned method order and signatures, tokenization, _prepare_dataset, PEFT handling, ref-model preparation for distributed training, and config layout — plus a new DataCollatorForKTO and output format. Metrics moved into _compute_loss and simplified to direct averages via the shared _metrics attribute.
- Removing legacy baggage: dropped encoder-decoder support, BOS/EOS handling, null_ref_context, generate_during_eval, model_init, preprocess_logits_for_metrics, model/ref adapter names, and several dead config knobs.
- Coverage: a full test suite mirroring DPO, text collator tests, VLM tests, and slow tests.
- The promotion itself: the experimental → stable move (#6175) and shim cleanup (#6287), handled so downstream users get a clean deprecation path.

Honestly, this has been one of the more complex tasks I've taken on since joining the team, not because any single change was hard, but because it demanded sustained consistency across a ~2,000-line trainer, with every branch, comment, and edge case kept in lockstep with DPO.

Huge thanks to everyone who reviewed along the way (especially @qgallouedec ), the incremental review cadence is exactly what kept this maintainable.

KTO now sits on equal footing with our other flagship trainers. 🚀
  • 2 replies
·
KingNish 
posted an update 5 months ago
view post
Post
5,278
We trained an open-source Mythos like cybersecurity LLM for the Build Small Hackathon meet OpenMythos

Trained in two stages: SFT on ~1.84K filtered ArXiv cs.CR papers + real CVE data, then RLVR using paired with past vulnerabilities GitHub repos with a verifier model checking outputs against ground truth.

Trained on: H100s from Modal

The RLVR stage made the biggest difference responses got more precise and less prone to confusing similar vulnerability classes.

Everything is open:
🤖 Demo → build-small-hackathon/OpenMythos
🧠 Model → build-small-hackathon/OpenMythos
📦 CVE Dataset → build-small-hackathon/CVE_Vulnerailities_Detailed
📄 ArXiv Dataset → himanshu17HF/ArvixImport-Filtered-Final

Try it out and let us know where it breaks 🙏
  • 2 replies
·
sdelbecque 
in wikimedia/structured-wikipedia 5 months ago

test
#22 opened 5 months ago by
john0falltrades
sdelbecque 
updated a dataset 5 months ago
isaranto 
in wikimedia/structured-wikipedia 5 months ago

Upload folder using huggingface_hub
#19 opened 5 months ago by
renilthomas82
renilthomas82 
in wikimedia/structured-wikipedia 5 months ago

Upload folder using huggingface_hub
#19 opened 5 months ago by
renilthomas82

Upload hf-permission-test.txt with huggingface_hub
#18 opened 5 months ago by
renilthomas82
santhosh 
updated a dataset 6 months ago
albertvillanova 
posted an update 8 months ago
view post
Post
3,125
🚀 TRL v0.29.0 introduces trl-training: an agent-native training skill.

This makes the TRL CLI a structured, agent-readable capability, allowing AI agents to reliably execute training workflows such as:
- Supervised Fine-Tuning (SFT)
- Direct Preference Optimization (DPO)
- Group Relative Policy Optimization (GRPO)

We’re excited to see what the community builds on top of this.

If you’re working on AI agents, alignment research, or scalable RL training infrastructure: give TRL v0.29.0 a try! 🤗

The future of ML tooling is agent-native.
🔗 https://github.com/huggingface/trl/releases/tag/v0.29.0
albertvillanova 
posted an update 9 months ago
view post
Post
2,082
5 years already working in democratizing AI 🤗
Grateful to be part of such an awesome team making it happen every day.
KingNish 
posted an update 11 months ago
view post
Post
3,866
Muon vs MuonClip vs Muon+Adamw

Muon has gone from an experiment to a mainstream optimizer, but does it hold up for fine‑tuning? We ran head‑to‑head tests on Qwen3‑4B (10k+ high‑quality instruction rows) to find out.

Short story: Pure Muon converged fastest at the start, but its gradient‑norm spikes made training unstable. MuonClip (Kimi K2’s clipping) stabilizes long pretraining runs, yet in our small‑scale fine‑tune it underperformed, lower token accuracy and slower convergence. The winner was the hybrid: Muon for 2D layers + AdamW for 1D layers. It delivered the best balance of stability and final performance and even beat vanilla AdamW.

Takeaway: for small-scale fine-tuning, hybrid = practical and reliable.

Next Step: scale to larger models/datasets to see if Muon’s spikes become catastrophic or if clipping wins out.

Full Blog Link: https://huggingface.co/blog/KingNish/optimizer-part1
KingNish 
posted an update 11 months ago
frimelle 
authored 2 papers about 1 year ago