Baris Parlan
bparlan
·
AI & ML interests
Storytelling, social graph, mythology, data analysis and vis
Recent Activity
reacted to alibidaran's post with 🔥 about 8 hours ago
🧠 Introducing Qwen3.5 — Cognitive Reasoning Mode
I fine-tuned Qwen2.5 with GRPO to actually think before it answers — not just pattern-match.
Most LLMs mimic reasoning. This one builds a real cognitive path:
📌 Plan → understand the task
🔍 Monitor → reason step by step
✅ Evaluate → verify before answering
Every response follows a strict structured protocol:
<think> <planning> ... <monitoring> ... <evaluation> ... </think>
Then a clean, reasoning-free <output>.
The model self-checks its own structure. If a section is missing or malformed → the response is invalid.
This isn't chain-of-thought slapped on top. The reasoning protocol is baked in via RL.
🔗 Full README + inference code below 👇
https://huggingface.co/alibidaran/Qwen_COG_Thinker_Merged
#AI #LLM #Qwen #ReasoningModels #GRPO #OpenSource liked a model 3 months ago
Lykon/dreamshaper-8 liked a model 3 months ago
wangfuyun/AnimateLCMOrganizations
