Description

This is an instruction following model (based on Mistral v0.1 Instruct) optimized for Russian language. It was trained using kolibrify on a multitude of instruction datasets.

The model uses ChatML template. Adding a system prompt will likely improve the model's performance on your task (experiment with it). I recommend using the model with LMStudio.

Currently in pre-alpha, later releases will include more details regarding training procedure and data mix.

Instruction following evals

The model was tested using the following benchmarks:

Eval name Strict Value Loose Value
Avg. 44.99 47.47
ifeval-prompt-level 45.84 48.05
ifeval-instruction-level 56.84 58.99
ru-ifeval-prompt-level 32.71 35.48
ru-ifeval-instruction-level 44.60 47.36
Downloads last month
16
GGUF
Model size
7.24B params
Architecture
llama

4-bit

8-bit

Inference API
Unable to determine this model’s pipeline type. Check the docs .

Collection including kaleinaNyan/kolibri-mistral-0427-2.gguf