1 5 6

Hugo Larcher

hlarcher

AI & ML interests

None yet

Recent Activity

reacted to fdaudens's post with 🔥 2 days ago

🔥The Open R1 team just dropped OlympicCoder and it's wild: - 7B model outperforms Claude 3.7 Sonnet on IOI benchmark (yes, 7B!!) - 32B crushes all open-weight models tested, even those 100x larger 🤯 Open-sourcing the future of code reasoning! 🚀 Check it out https://huggingface.co/blog/open-r1/update-3

updated a model 21 days ago

hlarcher/opt-125m-lfs

published a model 21 days ago

hlarcher/opt-125m-lfs

View all activity

Organizations

hlarcher's activity

reacted to fdaudens's post with 🔥 2 days ago

Post

1669

🔥The Open R1 team just dropped OlympicCoder and it's wild:

- 7B model outperforms Claude 3.7 Sonnet on IOI benchmark (yes, 7B!!)
- 32B crushes all open-weight models tested, even those 100x larger 🤯

Open-sourcing the future of code reasoning! 🚀

Check it out https://huggingface.co/blog/open-r1/update-3

updated a model 21 days ago

hlarcher/opt-125m-lfs

Text Generation • Updated 21 days ago • 9

published a model 21 days ago

hlarcher/opt-125m-lfs

Text Generation • Updated 21 days ago • 9

updated a model 21 days ago

hlarcher/opt-125m

Text Generation • Updated 21 days ago • 117

published a model 21 days ago

hlarcher/opt-125m

Text Generation • Updated 21 days ago • 117

updated a dataset 28 days ago

hlarcher/inference-benchmarker-xet

Updated 28 days ago • 106

published a dataset 28 days ago

hlarcher/inference-benchmarker-xet

Updated 28 days ago • 106

upvoted an article 28 days ago

Article

From Chunks to Blocks: Accelerating Uploads and Downloads on the Hub

about 1 month ago

• 49

authored a paper about 1 month ago

SmolLM2: When Smol Goes Big -- Data-Centric Training of a Small Language Model

Paper • 2502.02737 • Published Feb 4 • 203

upvoted an article about 1 month ago

Article

Welcome to Inference Providers on the Hub 🔥

Jan 28

• 430

posted an update about 2 months ago

Post

1080

We are introducing multi-backend support in HF中国镜像站 Text Generation Inference!
With new TGI architecture we are now able to plug new modeling backends to get best performances according to selected model and available hardware. This first step will very soon be followed by the integration of new backends (TRT-LLM, llama.cpp, vLLM, Neuron and TPU).

We are polishing the TensorRT-LLM backend which achieves impressive performances on NVIDIA GPUs, stay tuned 🤗 !

Check out the details: https://huggingface.co/blog/tgi-multi-backend