alibidaran/Qwen_COG_Thinker_Merged
Text Generation • 3B • Updated • 336 • 1
Ali Bidaran PRO
alibidaran
AI & ML interests
AI resercher, LLMs, Computer Vision, Generative AI, NLP, Machine /Deep learning, Reinforcement Learning
Recent Activity
new activity 1 day ago
alibidaran/Qwen_COG_Thinker_Merged:Benchmark updated a model 1 day ago
alibidaran/Qwen_COG_Thinker_Merged updated a model 7 days ago
alibidaran/Qwen_COG_ThinkerOrganizations
None yet
Benchmark
5
#1 opened 12 days ago
by 
pirola
updated a
model 1 day ago
updated a
model 7 days ago
repliedto their post 9 days ago
I haven't done evaluation benchmarks on the Gemma 4 yet, this space is here for comparison.
posted an update 11 days ago
Post
4047
With the release of Gemma 4, I launched a new Space called MEDPAI — a medical imaging analysis tool that combines object detection with multimodal AI.
Here's how it works:
Upload a CT scan or X-ray
Computer vision models detect and annotate findings
Gemma 4 33B generates a report or answers your questions about the image
Currently available detectors: dental analysis and bone fracture detection.
More models are in the pipeline — follow the Space to stay updated!
alibidaran/MEDPAI
Here's how it works:
Upload a CT scan or X-ray
Computer vision models detect and annotate findings
Gemma 4 33B generates a report or answers your questions about the image
Currently available detectors: dental analysis and bone fracture detection.
More models are in the pipeline — follow the Space to stay updated!
alibidaran/MEDPAI
- 3 replies
updated a
Space 11 days ago
published a
Space 11 days ago
repliedto their post 12 days ago
Why GPT-4o?
posted an update 14 days ago
Post
2051
🧠 Introducing Qwen2.5 — 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 👇
alibidaran/Qwen_COG_Thinker_Merged
#AI #LLM #Qwen #ReasoningModels #GRPO #OpenSource
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 👇
alibidaran/Qwen_COG_Thinker_Merged
#AI #LLM #Qwen #ReasoningModels #GRPO #OpenSource
- 2 replies
published a
model 14 days ago
published a
model 21 days ago
updated 2
models about 1 month ago
published a
model about 1 month ago
updated a
model about 1 month ago
published a
model about 1 month ago
updated a
model about 1 month ago
published a
model about 1 month ago
liked a
dataset about 2 months ago
updated a
model about 2 months ago