Olivier's picture

6 1 18

Olivier

oliviermills

·

https://oliviermills.com

AI & ML interests

LLMs, Data, AI for non-profits

Recent Activity

reacted to lewtun's post with 🔥 16 days 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

replied to lewtun's post 16 days 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

liked a dataset 7 months ago

Salesforce/xlam-function-calling-60k

View all activity

Organizations

oliviermills's activity

upvoted a paper 9 months ago

LoRA Land: 310 Fine-tuned LLMs that Rival GPT-4, A Technical Report

Paper • 2405.00732 • Published Apr 29, 2024 • 120