Hugging Face's logo

wut?
Team
Activity Feed

AI & ML interests

None defined yet.
ariG23498 
posted an update about 1 month ago
ariG23498 
posted an update 3 months ago
view post
Post
1707
🚨 Implement KV Cache from scratch in pure PyTorch. 🚨

We have documented all of our learning while implementing KV Cache to nanoVLM. Joint work with @kashif @lusxvr @andito @pcuenq

Blog: hf.co/blog/kv-cache
  • 1 reply
·
lewtun 
authored a paper 4 months ago
betodepaola 
in meta-llama/Llama-Guard-4-12B 4 months ago

Removing new lines
#9 opened 4 months ago by
betodepaola

Updating chat template

1
#8 opened 4 months ago by
betodepaola

Delete chat_template.json
#6 opened 4 months ago by
pcuenq

Updating chat template
#7 opened 4 months ago by
betodepaola
betodepaola 
updated a model 4 months ago
pcuenq 
in meta-llama/Llama-Guard-4-12B 4 months ago

Delete chat_template.json
#6 opened 4 months ago by
pcuenq
betodepaola 
updated a model 4 months ago
betodepaola 
in meta-llama/Llama-Guard-4-12B 4 months ago

Adding images
#5 opened 4 months ago by
betodepaola

Adding readme, license and use policy
#4 opened 4 months ago by
betodepaola

Adding readme, license and use policy
#3 opened 4 months ago by
betodepaola

Adding readme, license and use policy
#2 opened 4 months ago by
betodepaola
lewtun 
authored a paper 5 months ago
pcuenq 
authored a paper 5 months ago
lewtun 
authored a paper 6 months ago
lewtun 
posted an update 6 months ago
view post
Post
3338
Introducing OlympicCoder: a series of open reasoning models that can solve olympiad-level programming problems 🧑‍💻

- 7B open-r1/OlympicCoder-7B
- 32B open-r1/OlympicCoder-32B

We find that OlympicCoder models outperform Claude 3.7 Sonnet, as well as others over 100x larger 💪

Together with the models, we are releasing:

📊CodeForces-CoTs: new dataset of code problems from the most popular competitive coding platform, with R1 traces in C++ and Python open-r1/codeforces-cots

🏆 IOI'2024: a new benchmark of VERY hard programming problems where even frontier models struggle to match human performance open-r1/ioi

For links to the models and datasets, check out our latest progress report from Open R1: https://huggingface.co/blog/open-r1/update-3
  • 1 reply
·
lysandre 
posted an update 6 months ago
view post
Post
7947
SmolVLM-2 and SigLIP-2 are now part of transformers in dedicated releases!

They're added on top of the v4.49.0 release, and can be installed from the following tags: v4.49.0-SmolVLM-2 and v4.49.0-SigLIP-2.

This marks a new beginning for the release process of transformers. For the past five years, we've been doing monthly releases featuring many models (v4.49.0, the latest release, features 9 new architectures).

Starting with SmolVLM-2 & SigLIP2, we'll now additionally release tags supporting new models on a stable branch. These models are therefore directly available for use by installing from the tag itself. These tags will continue to be updated with fixes applied to these models.

Going forward, continue expecting software releases following semantic versioning: v4.50.0 will have ~10 new architectures compared to v4.49.0, as well as a myriad of new features, improvements and bug fixes. Accompanying these software releases, we'll release tags offering brand new models as fast as possible, to make them accessible to all immediately.
  • 1 reply
·
lewtun 
posted an update 7 months ago
view post
Post
5425
Introducing OpenR1-Math-220k!

open-r1/OpenR1-Math-220k

The community has been busy distilling DeepSeek-R1 from inference providers, but we decided to have a go at doing it ourselves from scratch 💪

What’s new compared to existing reasoning datasets?

♾ Based on AI-MO/NuminaMath-1.5: we focus on math reasoning traces and generate answers for problems in NuminaMath 1.5, an improved version of the popular NuminaMath-CoT dataset.

🐳 800k R1 reasoning traces: We generate two answers for 400k problems using DeepSeek R1. The filtered dataset contains 220k problems with correct reasoning traces.

📀 512 H100s running locally: Instead of relying on an API, we leverage vLLM and SGLang to run generations locally on our science cluster, generating 180k reasoning traces per day.

⏳ Automated filtering: We apply Math Verify to only retain problems with at least one correct answer. We also leverage Llama3.3-70B-Instruct as a judge to retrieve more correct examples (e.g for cases with malformed answers that can’t be verified with a rules-based parser)

📊 We match the performance of DeepSeek-Distill-Qwen-7B by finetuning Qwen-7B-Math-Instruct on our dataset.

🔎 Read our blog post for all the nitty gritty details: https://huggingface.co/blog/open-r1/update-2