ibm-granite

granite-3.1-8b-instruct

Granite-3.1-8B-Instruct is a lightweight and open-source 8B parameter model is designed to excel in instruction following tasks such as summarization, problem-solving, text translation, reasoning, code tasks, function-calling, and more.

Official

769.9K 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-3.1-8b-instruct:0261a65b61b38d0cbd5c484ea566a22ce6b2dfad92cb6d8f5b24ffca1f5c3814

Model

ibm-granite/granite-3.1-8b-instruct

w31njtvcwhrma0ckv9rr31404m

Status

Succeeded

Source

Web

Hardware

H100

Total duration

50.3s

Created

9 months ago by @ibm-granite

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-3.1-8b-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-3.1-8b-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-3.1-8b-instruct using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

# The ibm-granite/granite-3.1-8b-instruct model can stream output as it's running.
for event in replicate.stream(
    "ibm-granite/granite-3.1-8b-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-3.1-8b-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-3.1-8b-instruct/predictions

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

Output

One of IBM Research's laboratories located in the United States is the IBM Thomas J. Watson Research Center. This facility is situated in Yorktown Heights, New York, approximately 38 miles north of New York City. Established in 1956, it's one of the oldest corporate-backed research centers in the world. The center has played a pivotal role in numerous technological advancements, including the development of the relational database, the Scanning Tunneling Microscope, high-capacity data storage, and the Java programming language, among others.

{
  "completed_at": "2024-12-18T15:45:37.129722Z",
  "created_at": "2024-12-18T15:44:46.820000Z",
  "data_removed": false,
  "error": null,
  "id": "w31njtvcwhrma0ckv9rr31404m",
  "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:     ::1:45020 - \"POST /v1/chat/completions HTTP/1.1\" 200 OK\nGeneration took 3.01sFormatted prompt: Please list an IBM Research laboratory located in the United States.",
  "metrics": {
    "predict_time": 3.012751005,
    "total_time": 50.309722
  },
  "output": [
    "",
    "One",
    " of",
    " IBM",
    " Research",
    "'s",
    " labor",
    "ator",
    "ies",
    " located",
    " in",
    " the",
    " United",
    " States",
    " is",
    " the",
    " IBM",
    " Thomas",
    " J",
    ".",
    " W",
    "atson",
    " Research",
    " Center",
    ".",
    " This",
    " facility",
    " is",
    " situ",
    "ated",
    " in",
    " York",
    "town",
    " He",
    "ights",
    ",",
    " New",
    " York",
    ",",
    " approximately",
    " ",
    "3",
    "8",
    " m",
    "iles",
    " north",
    " of",
    " New",
    " York",
    " City",
    ".",
    " Est",
    "ab",
    "lished",
    " in",
    " ",
    "1",
    "9",
    "5",
    "6",
    ",",
    " it",
    "'s",
    " one",
    " of",
    " the",
    " oldest",
    " corpor",
    "ate",
    "-",
    "back",
    "ed",
    " research",
    " centers",
    " in",
    " the",
    " world",
    ".",
    " The",
    " center",
    " has",
    " played",
    " a",
    " p",
    "iv",
    "otal",
    " role",
    " in",
    " numero",
    "us",
    " tech",
    "no",
    "logical",
    " advance",
    "ments",
    ",",
    " including",
    " the",
    " development",
    " of",
    " the",
    " rel",
    "ational",
    " database",
    ",",
    " the",
    " Sc",
    "anning",
    " T",
    "unnel",
    "ing",
    " Micro",
    "scope",
    ",",
    " high",
    "-",
    "capacity",
    " data",
    " storage",
    ",",
    " and",
    " the",
    " Java",
    " programming",
    " language",
    ",",
    " among",
    " others",
    ".",
    ""
  ],
  "started_at": "2024-12-18T15:45:34.116971Z",
  "status": "succeeded",
  "urls": {
    "stream": "https://stream-b.svc.ric1.c.replicate.net/v1/streams/hbj7p6vu4un7h7vxvnb7a77ewsrv3sf2foa3disfheykc5besbtq",
    "get": "https://api.replicate.com/v1/predictions/w31njtvcwhrma0ckv9rr31404m",
    "cancel": "https://api.replicate.com/v1/predictions/w31njtvcwhrma0ckv9rr31404m/cancel"
  },
  "version": "0261a65b61b38d0cbd5c484ea566a22ce6b2dfad92cb6d8f5b24ffca1f5c3814"
}

Generated in

3.0 seconds

Tweak it Iterate in playground Share Report

Want to make some of these yourself?

Run this model