You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

Zlatorog-12B-Instruct-Beta

This model is a fine-tuned version of zidsi/MistralNemoCPT6 on the custom mix of SFT datasets.

More information needed

Research explore and have fun with Slovenian LLM :)

Bad standard Slovenian benchmarks results but sometimes impresssive "real world" prompt responses :)

Reduced hallucinations rate on "Who is ...?" prompts.

Tools use to be evaluated

Up to 16k ctx should work OK, for longer contexts training data would be required to improve CPT Long stage

More information needed

The HF model was coverted to GGUF using llama.cpp

GGUF

Model size

12B params

Architecture

llama

Hardware compatibility

4-bit

8-bit

16-bit

Base model

Quantized

(1)

this model