1,130 1 year ago

Vikhr-Nemo-12B-Instruct-R-21-09-24

tools

1 year ago

a8149e66bb93 · 7.5GB ·

llama
·
12.2B
·
Q4_K_M
{ "stop": [ "<|start_header_id|>", "<|end_header_id|>", "<|eot_id|>"
{{ if .Messages }} {{- if or .System .Tools }}<|start_header_id|>system<|end_header_id|> {{- if .Sys

Readme

Russian Vikhr model finetuned from Mistral-Nemo-Instruct-2407
Authors: https://t.me/vikhrmodels

FP16 (latest): HF
Q4_K_M: Quantized using Ollama