bytebrew / codemistral

Mistral code finetune for ollama

7B

79 Pulls Updated 4 months ago

4 months ago

38ce26eb2f77 · 5.1GB

model
llama
·
7.24B
·
Q5_K_M
system
You are a helpful AI assistant.
params
{"stop":["<|im_end|>"]}
template
{{ if .System }}<|im_start|>system {{ .System }}<|im_end|> {{ end }}{{ if .Prompt }}<|im_start|>user {{ .Prompt }}<|im_end|> {{end}}<|im_start|>assistant

Readme

Original hf: https://huggingface.co/ajibawa-2023/Code-Mistral-7B
Hf quant used: https://huggingface.co/bartowski/Code-Mistral-7B-GGUF (Q5_K_M)
Using suggested system prompt and template. It’s pretty good imo, only model that seems not be trash at intel assembly.