doriankim
/

gemma3_4b_skin_r32_b8_1000steps_merged_16bit

Image-Text-to-Text

text-generation-inference

Model card Files Files and versions

Uploaded finetuned model

Developed by: doriankim
License: apache-2.0
Finetuned from model : unsloth/gemma-3-4b-it-unsloth-bnb-4bit

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

Downloads last month: 11

Safetensors

Model size

4.3B params

Tensor type

BF16

·

Model tree for doriankim/gemma3_4b_skin_r32_b8_1000steps_merged_16bit

Base model

google/gemma-3-4b-pt

Finetuned

google/gemma-3-4b-it

Quantized

unsloth/gemma-3-4b-it-unsloth-bnb-4bit

Finetuned

(771)

this model