An uncensored model derived from Mistral-Nemo (12b). It ranks top 3 on the UGI leaderboard for models of its size. It was created by "Yamata Zen" and quantized by "team mradermacher".

tools

ollama run MartinRizzo/Ayla-Light-v2:12b-q4_K_M

curl http://localhost:11434/api/chat \
  -d '{
    "model": "MartinRizzo/Ayla-Light-v2:12b-q4_K_M",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='MartinRizzo/Ayla-Light-v2:12b-q4_K_M',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'MartinRizzo/Ayla-Light-v2:12b-q4_K_M',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Details

Updated 1 year ago

1 year ago

26a9e2db4cfd · 7.5GB ·

model

archllama

parameters12.2B

quantizationQ4_K_M

7.5GB

license

Apache License Version 2.0, January 2004 http://www.apache.org/licenses/ TERMS AND CONDITIONS FOR US

11kB

params

{ "stop": [ "[INST]", "[/INST]" ] }

30B

template

{{- range $i, $_ := .Messages }} {{- if eq .Role "user" }} {{- if and $.Tools (le (len (slice $.Mess

688B

Readme

Ayla-Light-v2

This model was developed by Yamata Zen and ranks among the top 3 on the UGI leaderboard for models with 12 billion parameters or less. It is an uncensored version of mistral-nemo that demonstrates excellent performance.

Reference

HuggingFace Model Card

GGUF Quants by mradermacher