How does this compare to other "1M context"-s UloRL and Unsloth?
#5
by
ljupco
- opened
Thanks for OSS-ing this - you are making life so much fun! I got only 88gb vram (share of 96gb ram) to play with this on a macbook. Curious to see what transpires... But before that, what's similar what's different between this, and -
- "An Ultra-Long Output Reinforcement Learning Approach for Advancing Large Language Models' Reasoning Abilities" at https://huggingface.co/forestliutc/UloRL; or
- This by the Unsloth guys https://huggingface.co/unsloth/Qwen3-Coder-30B-A3B-Instruct-1M-GGUF
? Thanks for your help - LJ