Saiga2 70B - GPTQ, Russian LLaMA2-based chatbot

Description

This repo contains GPTQ model files for Saiga2 70B

Downloads last month
21
Safetensors
Model size
9.7B params
Tensor type
I32
·
FP16
·
Inference Examples
Inference API (serverless) has been turned off for this model.

Model tree for Komposter43/saiga2_70b_lora-GPTQ

Quantized
(1)
this model