5
Exllama
😽
Chat: exllama v2
Pablo Carrera (パブロ)
pabloce
AI & ML interests
Hello, hello!
Recent Activity
updated
a Space
1 day ago
pabloce/exllama
reacted
to
nroggendorff's
post
with 🤗
6 days ago
hello, dev mode explorers!
updated
a Space
7 days ago
cognitivecomputations/chat
Organizations
pabloce's activity
updated
a
Space
1 day ago
reacted to
nroggendorff's
post with 🤗
6 days ago
Post
2736
hello, dev mode explorers!
- 2 replies
updated
a
Space
7 days ago
updated
a
Space
8 days ago
liked
a
Space
8 days ago
reacted to
victor's
post with ❤️
9 days ago
Post
3898
Hey everyone, we've given https://hf.co/spaces page a fresh update!
Smart Search: Now just type what you want to do—like "make a viral meme" or "generate music"—and our search gets it.
New Categories: Check out the cool new filter bar with icons to help you pick a category fast.
Redesigned Space Cards: Reworked a bit to really show off the app descriptions, so you know what each Space does at a glance.
Random Prompt: Need ideas? Hit the dice button for a burst of inspiration.
We’d love to hear what you think—drop us some feedback plz!
Smart Search: Now just type what you want to do—like "make a viral meme" or "generate music"—and our search gets it.
New Categories: Check out the cool new filter bar with icons to help you pick a category fast.
Redesigned Space Cards: Reworked a bit to really show off the app descriptions, so you know what each Space does at a glance.
Random Prompt: Need ideas? Hit the dice button for a burst of inspiration.
We’d love to hear what you think—drop us some feedback plz!
- 5 replies
liked
a
model
9 days ago
liked
a
Space
9 days ago
updated
a
Space
9 days ago
reacted to
lewtun's
post with 🚀❤️
9 days ago
Post
4447
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
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
Hi Charles (
@cbensimon
)
wish everything is okay.
I just wonder i don't know if I can ask this but what is the CUDA version HF Spaces use?
Do you know what nvidia-smi and nvcc --version output?
Sorry if this is out of the topic just wanna ask you this.
Is just for trying some CUDA packages that get a crazy error CUDA_ERROR_UNSUPPORTED_PTX_VERSION.
Have a great day Sir and thank u for your awesome work!
upvoted
an
article
10 days ago
Article
Open R1: Update #2
By
and 6 others
•
•
181
liked
a
Space
11 days ago
upvoted
a
collection
14 days ago
upvoted
2
collections
15 days ago
updated
a
Space
15 days ago
liked
a
model
15 days ago
updated
a
Space
15 days ago