GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
ChikenBoy
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
ChikenBoy
Model Tree
Qwen/Qwen3-VL-8B-Instruct
Input Modalities
Output Modalities
Supported Functionality
Qwen3-vl-8B-Kowalski-v5 — это дообученная Qwen3 8B на ~140 тысячах примеров. Я прокачал её в логике, математике, а также в коде. В неё добавлен блок с CoT. Модель была обучена методом Full Supervised Fine-Tuning (SFT). В данной вресии было добавлено зрение.
Qwen3-vl-8B-Kowalski-v5 is a fine-tuned Qwen3 8B trained on ~140k examples. I upgraded its logic, math, and coding skills. It features a block with CoT. The model was trained using Full Supervised Fine-Tuning (SFT). This version adds vision capabilities.