smollm2:1.7b-instruct-q3_K

smollm2:1.7b-instruct-q3_K_L

2.4M Downloads Updated 1 year ago

SmolLM2 is a family of compact language models available in three size: 135M, 360M, and 1.7B parameters.

tools 135m 360m 1.7b

ollama run smollm2:1.7b-instruct-q3_K_L

curl http://localhost:11434/api/chat \
  -d '{
    "model": "smollm2:1.7b-instruct-q3_K_L",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='smollm2:1.7b-instruct-q3_K_L',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'smollm2:1.7b-instruct-q3_K_L',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Details

Updated 1 year ago

1 year ago

8e9bf65b4fc1 · 933MB ·

model

archllama

parameters1.71B

quantizationQ3_K_L

933MB

system

You are a helpful AI assistant named SmolLM, trained by Hugging Face

68B

template

{{- if .Messages }} {{- if .Tools }}<|im_start|>system You are an expert in composing functions. You

1.8kB

params

{ "stop": [ "<|im_start|>", "<|im_end|>" ] }

59B

license

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

11kB

Readme

SmolLM2 is a family of compact language models available in three size: 135M, 360M, and 1.7B parameters. They are capable of solving a wide range of tasks while being lightweight enough to run on-device.

References

HuggingFace