Qwen 2: A 1.5 billion parameter language model from Alibaba Cloud, fine tuned for chat completions

Warm

Public

52.6K runs

L40S

License

GitHub

Paper

Playground API Examples README Versions

Prediction

zsxkib/qwen2-1.5b-instruct:18d7fe65057b30e9ba64aa311fa839dd14c43831afcbaa51155625bb0b1e07f9

Model

zsxkib/qwen2-1.5b-instruct:18d7fe65

y4038rxajsrgj0cga1e9hysd2g

Status

Succeeded

Source

Web

Hardware

A40 (Large)

Total duration

3m 26s

Created

over 1 year ago

Input

top_k: 1
top_p: 1
prompt: Tell me a joke about only having 1.5 billion parameters
model_type: Qwen2-1.5B-Instruct
temperature: 1
system_prompt: You are a funny and helpful assistant.
max_new_tokens: 512
repetition_penalty: 1

{
  "top_k": 1,
  "top_p": 1,
  "prompt": "Tell me a joke about only having 1.5 billion parameters",
  "model_type": "Qwen2-1.5B-Instruct",
  "temperature": 1,
  "system_prompt": "You are a funny and helpful assistant.",
  "max_new_tokens": 512,
  "repetition_penalty": 1
}

Install Replicate’s Node.js client library:

npm install replicate

Import and set up the client:

import Replicate from "replicate";

const replicate = new Replicate({
  auth: process.env.REPLICATE_API_TOKEN,
});

Run zsxkib/qwen2-1.5b-instruct using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "zsxkib/qwen2-1.5b-instruct:18d7fe65057b30e9ba64aa311fa839dd14c43831afcbaa51155625bb0b1e07f9",
  {
    input: {
      top_k: 1,
      top_p: 1,
      prompt: "Tell me a joke about only having 1.5 billion parameters",
      model_type: "Qwen2-1.5B-Instruct",
      temperature: 1,
      system_prompt: "You are a funny and helpful assistant.",
      max_new_tokens: 512,
      repetition_penalty: 1
    }
  }
);

console.log(output);

To learn more, take a look at the guide on getting started with Node.js.

Install Replicate’s Python client library:

pip install replicate

Import the client:

import replicate

Run zsxkib/qwen2-1.5b-instruct using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "zsxkib/qwen2-1.5b-instruct:18d7fe65057b30e9ba64aa311fa839dd14c43831afcbaa51155625bb0b1e07f9",
    input={
        "top_k": 1,
        "top_p": 1,
        "prompt": "Tell me a joke about only having 1.5 billion parameters",
        "model_type": "Qwen2-1.5B-Instruct",
        "temperature": 1,
        "system_prompt": "You are a funny and helpful assistant.",
        "max_new_tokens": 512,
        "repetition_penalty": 1
    }
)

# The zsxkib/qwen2-1.5b-instruct model can stream output as it's running.
# The predict method returns an iterator, and you can iterate over that output.
for item in output:
    # https://replicate.com/zsxkib/qwen2-1.5b-instruct/api#output-schema
    print(item, end="")

To learn more, take a look at the guide on getting started with Python.

Run zsxkib/qwen2-1.5b-instruct using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

curl -s -X POST \
  -H "Authorization: Bearer $REPLICATE_API_TOKEN" \
  -H "Content-Type: application/json" \
  -H "Prefer: wait" \
  -d $'{
    "version": "zsxkib/qwen2-1.5b-instruct:18d7fe65057b30e9ba64aa311fa839dd14c43831afcbaa51155625bb0b1e07f9",
    "input": {
      "top_k": 1,
      "top_p": 1,
      "prompt": "Tell me a joke about only having 1.5 billion parameters",
      "model_type": "Qwen2-1.5B-Instruct",
      "temperature": 1,
      "system_prompt": "You are a funny and helpful assistant.",
      "max_new_tokens": 512,
      "repetition_penalty": 1
    }
  }' \
  https://api.replicate.com/v1/predictions

To learn more, take a look at Replicate’s HTTP API reference docs.

Output

Why did the neural network have only 1.5 billion parameters? Because it was a tiny little network!

Generated in

1.2 seconds

Tweak it Iterate in playground Share Report

Want to make some of these yourself?

Run this model