simonko912/simllama-1:q8

simonko912/ simllama-1:q8_0

22 Downloads Updated 2 months ago

General purpose chatting model in 0.2b, super dumb but lightweight.

ollama run simonko912/simllama-1:q8_0

curl http://localhost:11434/api/chat \
  -d '{
    "model": "simonko912/simllama-1:q8_0",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='simonko912/simllama-1:q8_0',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'simonko912/simllama-1:q8_0',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Details

Updated 2 months ago

2 months ago

9084eb366928 · 173MB

model

archllama

parameters162M

quantizationQ8_0

173MB

template

{{ range .Messages }} {{- if eq .Role "user" -}} [INST] {{ .Content }} [/INST] {{- else if eq .Role

203B

system

You are a helpful assistant. Keep your answers short and direct. Do not repeat yourself.

88B

params

{ "num_ctx": 1024, "repeat_penalty": 1.45, "stop": [ "[/INST]", "</s>",

126B

Readme

Simllama 1 0.2b

Simllama 1 is a dumb lightweight model for super basic tasks.