Edit model card

Model Card for Mira 70B v0.8

The smartest Russian model based on LLaMA 70B v2 architecture. So maybe it's the last Big Russian Model of that family.

Trained with TRINITY method for 60 hours of Nvidia H100.

Prompt Format

Please use the prompt formatted like this:

You are an AI assistant that follows instruction. Help as much as you can.

### Human:

Your question here.

### Assistant:

Please pay attention for double new lines everywhere - and after "### Assistant:" line too!

GGUF

https://huggingface.co/gotzmann/Mira-70B-v0.8-GGUF/tree/main

Downloads last month
25
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.

Model tree for gotzmann/Mira-70B-v0.8

Quantizations
1 model