Edit model card

Uploaded model

  • Developed by: Sakayo16
  • License: apache-2.0
  • Finetuned from model : unsloth/llama-3-8b-Instruct-bnb-4bit

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

Downloads last month
43
Safetensors
Model size
4.65B params
Tensor type
FP16
F32
U8
Inference API
Input a message to start chatting with Batazia/llama3-instruct-4bit.
This model can be loaded on Inference API (serverless).

Quantized from