Uploaded model

This gemma model was trained 2x faster with and 71% less Memory use. By using unsloth and Huggingface's TRL library.

GGUF

Model size

8.54B params

Architecture

gemma

Hardware compatibility

4-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for johnnietien/gemma-7b-bnb-4bit-jt-medical-vn-lora-gguf-q4_k_m

Base model

Quantized

(66)

this model