simonbutt
/

am_llama3_alpaca

text-generation-inference

Model card Files Files and versions

Llama3 Amharic Alpaca Tuned

Llama3 8B instruction tuned on an amharic translated alpaca dataset.

Very token inefficient.

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

Downloads last month: 4

Safetensors

Model size

8B params

Tensor type

BF16

·

Inference Providers NEW

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

Model tree for simonbutt/am_llama3_alpaca

Base model

meta-llama/Meta-Llama-3-8B

Quantized

unsloth/llama-3-8b-bnb-4bit

Quantized

(861)

this model

Dataset used to train simonbutt/am_llama3_alpaca

Collection including simonbutt/am_llama3_alpaca

amharic_llama

Goal: to create the best possible Amharic language models that can run offline on a budget smartphone • 4 items • Updated Apr 27, 2024