
qingy2024/GRMR-V3-G4B
Image-Text-to-Text
•
Updated
•
72
•
13
An improved set of models for grammar correction. (Chat template should work, no "responding as an LLM" anymore, that kind of stuff).
Note Models with "G" mean fine-tuned off of Gemma 3 PT models
Note Models with "Q" mean fine-tuned off of Qwen 3 Base models
Note Models with "L" mean fine-tuned off of Llama 3.2 Base models