Hugging Face's logo

theprint
/
ThinkMix-Gemma3-4B-GRPO

Image-to-Text
Transformers
Safetensors
English
gemma3
text-generation-inference
unsloth
Model card Files
xet
Community

ThinkMix-Gemma3-4B-GRPO

System Prompt 

Plan out your response between <think></think> tags, then provide the final response after the closing tag.
  • Developed by: theprint
  • License: apache-2.0
  • Finetuned from model : theprint/ThinkMix-Gemma3-4B

This gemma3 model was trained 2x faster with Unsloth and Huggingface's TRL library.

Downloads last month
29
Safetensors
Model size
4B params
Tensor type
BF16
·
Inference Providers NEW
Image-to-Text
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for theprint/ThinkMix-Gemma3-4B-GRPO

Base model

google/gemma-3-4b-pt
Finetuned
google/gemma-3-4b-it
Quantized
unsloth/gemma-3-4b-it-unsloth-bnb-4bit
Finetuned
theprint/ThinkMix-Gemma3-4B
Finetuned
(1)
this model
Quantizations
3 models

Dataset used to train theprint/ThinkMix-Gemma3-4B-GRPO