ibm-granite

granite-3.1-2b-instruct

Granite-3.1-2B-Instruct is a lightweight and open-source 2B parameter model designed to excel in instruction following tasks such as summarization, problem-solving, text translation, reasoning, code tasks, function-calling, and more.

Official

9.1K runs

Priced by multiple properties

New model available: Try out Granite-3.3-8b-instruct View the new model

Run with an API

Pricing

GitHub

License

Playground API Examples Train README

Prediction

ibm-granite/granite-3.1-2b-instruct:0581cf4c919c6e6398e0e1486008e12a70c0a0ff7ffeacbef73d292bed3e0cdf

Model

ibm-granite/granite-3.1-2b-instruct

vqe8pncx2drm80ckv9r8swx6c0

Status

Succeeded

Source

Web

Hardware

H100

Total duration

1m 46s

Created

9 months ago

Input

top_k: 50
top_p: 0.9
prompt: Please list an IBM Research laboratory located in the United States.
max_tokens: 512
min_tokens: 0
temperature: 0.6
system_prompt: You are an expert in tech history and can answer questions eloquently about the milestones of software organizations.
presence_penalty: 0
frequency_penalty: 0

{
  "top_k": 50,
  "top_p": 0.9,
  "prompt": "Please list an IBM Research laboratory located in the United States.",
  "max_tokens": 512,
  "min_tokens": 0,
  "temperature": 0.6,
  "system_prompt": "You are an expert in tech history and can answer questions eloquently about the milestones of software organizations.",
  "presence_penalty": 0,
  "frequency_penalty": 0
}

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 ibm-granite/granite-3.1-2b-instruct using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const input = {
  top_k: 50,
  top_p: 0.9,
  prompt: "Please list an IBM Research laboratory located in the United States.",
  max_tokens: 512,
  min_tokens: 0,
  temperature: 0.6,
  system_prompt: "You are an expert in tech history and can answer questions eloquently about the milestones of software organizations.",
  presence_penalty: 0,
  frequency_penalty: 0
};

for await (const event of replicate.stream("ibm-granite/granite-3.1-2b-instruct", { input })) {
  process.stdout.write(event.toString());
};

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 ibm-granite/granite-3.1-2b-instruct using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

# The ibm-granite/granite-3.1-2b-instruct model can stream output as it's running.
for event in replicate.stream(
    "ibm-granite/granite-3.1-2b-instruct",
    input={
        "top_k": 50,
        "top_p": 0.9,
        "prompt": "Please list an IBM Research laboratory located in the United States.",
        "max_tokens": 512,
        "min_tokens": 0,
        "temperature": 0.6,
        "system_prompt": "You are an expert in tech history and can answer questions eloquently about the milestones of software organizations.",
        "presence_penalty": 0,
        "frequency_penalty": 0
    },
):
    print(str(event), end="")

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

Run ibm-granite/granite-3.1-2b-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 $'{
    "input": {
      "top_k": 50,
      "top_p": 0.9,
      "prompt": "Please list an IBM Research laboratory located in the United States.",
      "max_tokens": 512,
      "min_tokens": 0,
      "temperature": 0.6,
      "system_prompt": "You are an expert in tech history and can answer questions eloquently about the milestones of software organizations.",
      "presence_penalty": 0,
      "frequency_penalty": 0
    }
  }' \
  https://api.replicate.com/v1/models/ibm-granite/granite-3.1-2b-instruct/predictions

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

Output

One of IBM's renowned research laboratories in the United States is the IBM Laboratory located in Almaden, California. Established in 1952, it's one of the oldest and largest research centers in the world, focusing on a broad spectrum of disciplines, including computer science, services, storage systems, and materials science and technology. The Almaden lab has made significant contributions to various technological advancements, including the development of the IBM Personal Computer, the RAID storage technology, and the IBM Chemistry Field-Programmable Gate Array (C-FFA).

{
  "completed_at": "2024-12-18T15:45:39.903913Z",
  "created_at": "2024-12-18T15:43:53.619000Z",
  "data_removed": false,
  "error": null,
  "id": "vqe8pncx2drm80ckv9r8swx6c0",
  "input": {
    "top_k": 50,
    "top_p": 0.9,
    "prompt": "Please list an IBM Research laboratory located in the United States.",
    "max_tokens": 512,
    "min_tokens": 0,
    "temperature": 0.6,
    "system_prompt": "You are an expert in tech history and can answer questions eloquently about the milestones of software organizations.",
    "presence_penalty": 0,
    "frequency_penalty": 0
  },
  "logs": "INFO:     ::1:53940 - \"POST /v1/chat/completions HTTP/1.1\" 200 OK\nGeneration took 2.55sFormatted prompt: Please list an IBM Research laboratory located in the United States.",
  "metrics": {
    "predict_time": 2.547046923,
    "total_time": 106.284913
  },
  "output": [
    "",
    "One",
    " of",
    " IBM",
    "'s",
    " re",
    "nown",
    "ed",
    " research",
    " labor",
    "ator",
    "ies",
    " in",
    " the",
    " United",
    " States",
    " is",
    " the",
    " IBM",
    " Laboratory",
    " located",
    " in",
    " Al",
    "mad",
    "en",
    ",",
    " California",
    ".",
    " Est",
    "ab",
    "lished",
    " in",
    " ",
    "1",
    "9",
    "5",
    "2",
    ",",
    " it",
    "'s",
    " one",
    " of",
    " the",
    " oldest",
    " and",
    " largest",
    " research",
    " centers",
    " in",
    " the",
    " world",
    ",",
    " foc",
    "using",
    " on",
    " a",
    " broad",
    " spectrum",
    " of",
    " dis",
    "cipl",
    "ines",
    ",",
    " including",
    " computer",
    " science",
    ",",
    " services",
    ",",
    " storage",
    " systems",
    ",",
    " and",
    " materials",
    " science",
    " and",
    " technology",
    ".",
    " The",
    " Al",
    "mad",
    "en",
    " lab",
    " has",
    " made",
    " significant",
    " contributions",
    " to",
    " various",
    " tech",
    "no",
    "logical",
    " advance",
    "ments",
    ",",
    " including",
    " the",
    " development",
    " of",
    " the",
    " IBM",
    " Personal",
    " Computer",
    ",",
    " the",
    " RA",
    "ID",
    " storage",
    " technology",
    ",",
    " and",
    " the",
    " IBM",
    " Che",
    "mistry",
    " Field",
    "-",
    "Program",
    "mable",
    " Gate",
    " Array",
    " (",
    "C",
    "-",
    "FF",
    "A",
    ").",
    ""
  ],
  "started_at": "2024-12-18T15:45:37.356866Z",
  "status": "succeeded",
  "urls": {
    "stream": "https://stream-b.svc.ric1.c.replicate.net/v1/streams/twm4vlbrinpgqyev2g4svg5lqe2yvch3clcq64q5rjlj3dm2oika",
    "get": "https://api.replicate.com/v1/predictions/vqe8pncx2drm80ckv9r8swx6c0",
    "cancel": "https://api.replicate.com/v1/predictions/vqe8pncx2drm80ckv9r8swx6c0/cancel"
  },
  "version": "0581cf4c919c6e6398e0e1486008e12a70c0a0ff7ffeacbef73d292bed3e0cdf"
}

Generated in

2.5 seconds

Tweak it Iterate in playground Share Report

Want to make some of these yourself?

Run this model