Edit model card

Model Card for Model ID

Multilingual fine tuned version of LLAMA-3-8B quantized in 4 bits.

Model Details

Model Description

Multilingual fine tuned version of LLAMA-3-8B quantized in 4 bits using common open source datasets and showing improvements over multilingual tasks. It has been used the standard bitquantized technique for post-fine-tuning quantization reducing the computational time complexity and space complexity required to run the model. The overall architecture it's all LLAMA-3 based.

  • Developed by: Daniele Comi
  • Model type: LLAMA-3-8B
  • Language(s) (NLP): Multilingual
  • License: MIT
  • Finetuned from model: LLAMA-3-8B
Downloads last month
15
Safetensors
Model size
3.6B params
Tensor type
F32
FP16
U8
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.