Model Card for Model ID

This is a GPTQ quantized version of https://huggingface.co/amd/Instella-3B-Instruct

Results

Benchmark Score
MMLU 57.13
TruthfulQA 55.23
Downloads last month
4
Safetensors
Model size
641M params
Tensor type
I32
·
FP16
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support