Dennis's picture

4 3 10

Dennis PRO

doubledsbv

·

ddickmann

AI & ML interests

None yet

Recent Activity

liked a dataset about 11 hours ago

facebook/natural_reasoning

reacted to lewtun's post with ❤️ 10 days ago

Introducing OpenR1-Math-220k! https://huggingface.co/datasets/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 https://huggingface.co/datasets/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

updated a model about 1 month ago

seedboxai/sparse_llama_3.1-8b-sft-distilled

View all activity

Organizations

doubledsbv's activity

New activity in occiglot/euro-llm-leaderboard 9 months ago

A few model submissions that didn't work

#2 opened 9 months ago by

KnutJaegersberg

New activity in seedboxai/KafkaLM-8x7B-German-V0.1 11 months ago

Is this based on 8x7B instruct? and if so on which version v0.1 or v0.2?

#1 opened 11 months ago by

New activity in seedboxai/KafkaLM-7B-DARE_TIES-LaserRMT-QLoRA-DPO-v0.5 12 months ago

"torch_dtype": "float32"

#1 opened 12 months ago by

New activity in seedboxai/KafkaLM-8x7b-German-V0.1-DPO 12 months ago

Great work!

#2 opened 12 months ago by