Maharsh's picture

1 1 5

Maharsh

maharshpatelx

·

AI & ML interests

None yet

Recent Activity

reacted to lewtun's post with 🔥 about 10 hours ago

We are reproducing the full DeepSeek R1 data and training pipeline so everybody can use their recipe. Instead of doing it in secret we can do it together in the open! 🧪 Step 1: replicate the R1-Distill models by distilling a high-quality reasoning corpus from DeepSeek-R1. 🧠 Step 2: replicate the pure RL pipeline that DeepSeek used to create R1-Zero. This will involve curating new, large-scale datasets for math, reasoning, and code. 🔥 Step 3: show we can go from base model -> SFT -> RL via multi-stage training. Follow along: https://github.com/huggingface/open-r1

commented on an article 8 days ago

The Large Language Model Course

upvoted an article 8 days ago

The Large Language Model Course

View all activity

Organizations

None yet

maharshpatelx's activity

liked 2 models 3 months ago

Qwen/Qwen2.5-Coder-32B-Instruct

Text Generation • Updated 16 days ago • 173k • • 1.52k

microsoft/OmniParser

Image-Text-to-Text • Updated Dec 2, 2024 • 1.32k • 1.54k

liked a dataset 3 months ago

user22451002/Windows-11-x64

Updated Aug 13, 2024 • 2 • 1

liked 2 datasets 4 months ago

codeparrot/github-code

Updated Oct 20, 2022 • 12.3k • 303

bigcode/the-stack

Viewer • Updated Apr 13, 2023 • 546M • 6.13k • 760