UnstableLlama's picture

3 16

UnstableLlama

UnstableLlama

·

AI & ML interests

Local AI

Recent Activity

reacted to chansung's post with 👍 4 days ago

Simple Summarization on DeepSeek-R1 from DeepSeek AI The RL stage is very important. ↳ However, it is difficult to create a truly helpful AI for people solely through RL. ↳ So, we applied a learning pipeline consisting of four stages: providing a good starting point, reasoning RL, SFT, and safety RL, and achieved performance comparable to o1. ↳ Simply fine-tuning other open models with the data generated by R1-Zero (distillation) resulted in performance comparable to o1-mini. Of course, this is just a brief overview and may not be of much help. All models are accessible on Hugging Face, and the paper can be read through the GitHub repository. Model: https://huggingface.co./deepseek-ai Paper: https://github.com/deepseek-ai/DeepSeek-R1

liked a model 6 days ago

deepseek-ai/DeepSeek-R1

updated a model 2 months ago

UnstableLlama/Marco-o1-exl2

View all activity

Organizations

None yet

UnstableLlama's activity

New activity in UnstableLlama/Xwin-LM-13B-V0.1-4bpw-exl2 over 1 year ago

Thanks!

#1 opened over 1 year ago by

New activity in UnstableLlama/Xwin-LM-7B-V0.1-8bpw-exl2 over 1 year ago

test

#1 opened over 1 year ago by

test

#1 opened over 1 year ago by

test

#1 opened over 1 year ago by