kyatham Karthik

Karthik64

1

·

AI & ML interests

None yet

Recent Activity

liked a model 27 days ago

harshatheg/Qwen-2.5-1B-RLCD

repliedto anakin87's post over 1 year ago

𝗜 𝘁𝗿𝗮𝗶𝗻𝗲𝗱 𝗮 𝗟𝗮𝗻𝗴𝘂𝗮𝗴𝗲 𝗠𝗼𝗱𝗲𝗹 𝘁𝗼 𝘀𝗰𝗵𝗲𝗱𝘂𝗹𝗲 𝗲𝘃𝗲𝗻𝘁𝘀 𝘄𝗶𝘁𝗵 𝗚𝗥𝗣𝗢! 👑 🗓️ ✍️ Blog post: https://huggingface.co/blog/anakin87/qwen-scheduler-grpo I experimented with GRPO lately. I am fascinated by models learning from prompts and rewards - no example answers needed like in Supervised Fine-Tuning. After the DeepSeek boom, everyone is trying GRPO with GSM8K or the Countdown Game... I wanted a different challenge, like 𝘁𝗲𝗮𝗰𝗵𝗶𝗻𝗴 𝗮 𝗺𝗼𝗱𝗲𝗹 𝘁𝗼 𝗰𝗿𝗲𝗮𝘁𝗲 𝗮 𝘀𝗰𝗵𝗲𝗱𝘂𝗹𝗲 𝗳𝗿𝗼𝗺 𝗮 𝗹𝗶𝘀𝘁 𝗼𝗳 𝗲𝘃𝗲𝗻𝘁𝘀 𝗮𝗻𝗱 𝗽𝗿𝗶𝗼𝗿𝗶𝘁𝗶𝗲𝘀. Choosing an original problem forced me to: 🤔 Think about the problem setting 🧬 Generate data 🤏 Choose the right base model 🏆 Design reward functions (and experiencing reward hacking) 🔄 Run multiple rounds of training, hoping that my model would learn something. A fun and rewarding 😄 experience. I learned a lot of things, that I want to share with you. 👇 ✍️ Blog post: https://huggingface.co/blog/anakin87/qwen-scheduler-grpo 💻 Code: https://github.com/anakin87/qwen-scheduler-grpo 🤗 Hugging Face collection (dataset and model): https://huggingface.co/collections/anakin87/qwen-scheduler-grpo-680bcc583e817390525a8837

View all activity

Organizations

None yet

liked a model 27 days ago

harshatheg/Qwen-2.5-1B-RLCD

Text Generation • Updated Sep 16 • 592

replied to anakin87's post over 1 year ago

you have done because DeepSeek boom ??but you can try with GSMK8
,but it can take time to do Original Problem ....but with GRPO using GSMK8,more effective in large problems(Like Large LLM's )....GRPO is really shines in these setups where reward design becomes very artful..But very Great work for what you did !nice work