ValueFX9507/Tifa-DeepsexV2-7b-MGRPO-GGUF-Q4
Reinforcement Learning
β’
Updated
β’
34k
β’
190
Play with all the pix2struct variants in this d
Interact with images and texts using Qwen-VL-Max
Qwen2.5-VL-7B-Instruct
Generate images and insights from text and images
Self-Supervised Prompt Optimization