GRMR V3 Models - a qingy2024 Collection

qingy2024 's Collections

UwU

Fusion

Qwen 2.5 Math 14B Iter 2

Qwen 2.5 Math 14B Iter 1

Chemistry LLM Data

GRMR V3 Models

updated Jun 4

An improved set of models for grammar correction. (Chat template should work, no "responding as an LLM" anymore, that kind of stuff).

qingy2024/GRMR-V3-G4B

Image-Text-to-Text • 4B • Updated Jun 6 • 24 • 16

Note Models with "G" mean fine-tuned off of Gemma 3 PT models
qingy2024/GRMR-V3-Q4B

Text Generation • 4B • Updated Jun 4 • 6 • 7

Note Models with "Q" mean fine-tuned off of Qwen 3 Base models
qingy2024/GRMR-V3-L3B

Text Generation • 3B • Updated Jun 3 • 11 • 2

Note Models with "L" mean fine-tuned off of Llama 3.2 Base models
qingy2024/GRMR-V3-Q1.7B

Text Generation • 2B • Updated Jun 3 • 4 • 2
qingy2024/GRMR-V3-L1B

Text Generation • 1B • Updated Jun 3 • 8 • 2
qingy2024/GRMR-V3-G1B

Text Generation • 1.0B • Updated Jun 6 • 5