Mert Erbak PRO
merterbak
AI & ML interests
NLP and Image Processing
Recent Activity
liked
a Space
about 6 hours ago
nvidia/describe-anything-model-demo
updated
a model
about 12 hours ago
merterbak/Mistral-Small-3.1-24B-Instruct-2503-GGUF
reacted
to
their
post
with 🔥
about 22 hours ago
FlowReasoner is a new system that builds a custom set of small AI agents for every user question. Unlike search based methods it uses reasoning driven optimization with external execution feedback.
✅ First, it distills reasoning data using DeepSeek R1-671B to build multi agent systems. 🤖
✅ Then, reasoning data used for DeepSeek-R1-Distill-Qwen-7B via supervised fine tuning for basic reasoning skills. 💡
✅ Finally, RL with GRPO (optimizes by comparing response groups from queries/tasks) to improve reasoning.
https://huggingface.co/papers/2504.15257
Code: https://github.com/sail-sg/flowreasoner
Organizations
