replicate / gpt-j-6b

A large language model by EleutherAI

Cold

Public
9.5K runs
A100 (80GB)
GitHub
License

Run with an API

Playground API Examples Train README Versions

Input

prompt

*string

Shift + Return to add a new line

Input Prompt.

max_length

integer

(minimum: 1)

Maximum number of tokens to generate. A word is generally 2-3 tokens

Default: 500

decoding

string

Choose a decoding method

Default: "top_p"

top_k

integer

Valid if you choose top_k decoding. The number of highest probability vocabulary tokens to keep for top-k-filtering

Default: 50

top_p

number

(minimum: 0.01, maximum: 1)

Valid if you choose top_p decoding. When decoding text, samples from the top p percentage of most likely tokens; lower to ignore less likely tokens

Default: 1

temperature

number

(minimum: 0.01, maximum: 5)

Adjusts randomness of outputs, greater than 1 is random and 0 is deterministic, 0.75 is a good starting value.

Default: 0.75

repetition_penalty

number

(minimum: 0.01, maximum: 5)

Penalty for repeated words in generated text; 1 is no penalty, values greater than 1 discourage repetition, less than 1 encourage it.

Default: 1.2

Run this model in Node.js with one line of code:

npx create-replicate --model=replicate/gpt-j-6b

or set up a project from scratch

Install Replicate’s Node.js client library:

npm install replicate

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Import and set up the client:

import Replicate from "replicate";

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

Run replicate/gpt-j-6b using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "replicate/gpt-j-6b:b3546aeec6c9891f0dd9929c2d3bedbf013c12e02e7dd0346af09c37e008c827",
  {
    input: {
      top_k: 50,
      top_p: 1,
      prompt: "Is a hot dog a sandwich?",
      decoding: "top_p",
      max_length: 50,
      temperature: 0.75,
      repetition_penalty: 1.2
    }
  }
);

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

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Import the client:

import replicate

Run replicate/gpt-j-6b using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "replicate/gpt-j-6b:b3546aeec6c9891f0dd9929c2d3bedbf013c12e02e7dd0346af09c37e008c827",
    input={
        "top_k": 50,
        "top_p": 1,
        "prompt": "Is a hot dog a sandwich?",
        "decoding": "top_p",
        "max_length": 50,
        "temperature": 0.75,
        "repetition_penalty": 1.2
    }
)

# The replicate/gpt-j-6b 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/replicate/gpt-j-6b/api#output-schema
    print(item, end="")

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

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Run replicate/gpt-j-6b 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": "b3546aeec6c9891f0dd9929c2d3bedbf013c12e02e7dd0346af09c37e008c827",
    "input": {
      "top_k": 50,
      "top_p": 1,
      "prompt": "Is a hot dog a sandwich?",
      "decoding": "top_p",
      "max_length": 50,
      "temperature": 0.75,
      "repetition_penalty": 1.2
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

A. Yes, it is a sandwich because it's eaten between two pieces of bread or other edible products and served in the same way as sandwiches. An open-faced sandwich would be an example

Generated in

1.9 seconds

Tweak it Report

Run time and cost

This model costs approximately $0.031 to run on Replicate, or 32 runs per $1, but this varies depending on your inputs. It is also open source and you can run it on your own computer with Docker.

This model runs on Nvidia A100 (80GB) GPU hardware. Predictions typically complete within 23 seconds.

Readme

GPT-J-6B

GPT-J-6B is a 6 billion parameter language model by EleutherAI.

Official page: https://huggingface.co/EleutherAI/gpt-j-6b

Fine-tuning

If you have access to the training beta, you can fine-tune this model.

Here’s an example using replicate-python:

training = replicate.trainings.create(
    version="replicate/gpt-j-6b:b3546aeec6c9891f0dd9929c2d3bedbf013c12e02e7dd0346af09c37e008c827", 
    input={
        "train_data": "https://storage.googleapis.com/dan-scratch-public/fine-tuning/70k_samples.jsonl", 
    }, 
    destination="my-username/my-model"
)

Training takes these input parameters:

train_data (required): URL to a file in JSONL where each line is in the format {"prompt": ..., "completion": ...}
epochs (optional, default=1): Number of times to iterate over the training dataset
max_steps (optional, default=-1): Maximum number of training steps. Unlimited if max_steps=-1