takenusername/tinyllm

takenusername/ tinyllm:latest

80 Downloads Updated 1 year ago

Should be the fastest and smartest llm for the raspberry pi 4b, 5, and newer models if any

ollama run takenusername/tinyllm

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

from ollama import chat

response = chat(
    model='takenusername/tinyllm',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'takenusername/tinyllm',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Details

Updated 1 year ago

1 year ago

d62353bcb81e · 2.6GB ·

model

archllama

parameters3.43B

quantizationQ4_0

2.0GB

model

archllama

parameters1.1B

quantizationQ4_0

638MB

template

{{- if .System }}<|im_start|>system {{ .System }} {{ end }} {{- if .Prompt }}<|im_start|>user {{ .Pr

188B

system

You are an AI assistant optimized for older devices or devices with limited resources, designed to p

1.4kB

params

{ "min_p": 0.05, "mirostat": 1, "mirostat_eta": 0.1, "mirostat_tau": 5, "num_ctx

269B

Readme

This is a combination of TinyLlama and Orca Mini.

Optimized for use on the raspberry pi 5 or newer not recommended for use on the raspberry pi 4b or lower