Edit model card

Uploaded model

  • Developed by: Deeokay
  • 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.

Converstion of Base Model

These are models directly converted from the base model without change

  • Primary for a starting base of future customizations
Downloads last month
3
Safetensors
Model size
4.65B params
Tensor type
FP16
F32
U8
Inference Examples
Inference API (serverless) is not available, repository is disabled.

Model tree for Deeokay/llama3-8B-Instruct-base-4bit

Quantized
this model