nwhitehead/llama2-7b-chat-gptq:8c1f632f | Run with an API on Replicate

Version

You're looking at a specific version of this model. Jump to the model overview.

nwhitehead /llama2-7b-chat-gptq:8c1f632f

Input

prompt

string

Shift + Return to add a new line

USER: Hello, who are you?
ASSISTANT:USER: Hello, who are you?
ASSISTANT:

Text prompt for the model

Default: "USER: Hello, who are you?\nASSISTANT:"

temperature

number

(minimum: 0.01, maximum: 2)

Temperature of the output, it's best to keep it below 1

Default: 0.5

top_p

number

(minimum: 0.01, maximum: 1)

Top cumulative probability to filter candidates

Default: 1

top_k

integer

(minimum: 1, maximum: 100)

Number of top candidates to keep

Default: 20

repetition_penalty

number

(minimum: 1, maximum: 1.5)

Penalty for repeated tokens in the model's output

Default: 1

max_tokens

integer

(minimum: 1, maximum: 4096)

Maximum tokens to generate

Default: 50

min_tokens

integer

(minimum: 0, maximum: 4096)

Minimum tokens to generate

Default: 1

seed

integer

(minimum: -2147483648, maximum: 2147483647)

Seed for reproducibility, -1 for random seed

Default: -1

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

npx create-replicate --model=nwhitehead/llama2-7b-chat-gptq

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 nwhitehead/llama2-7b-chat-gptq using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "nwhitehead/llama2-7b-chat-gptq:8c1f632f7a9df740bfbe8f6b35e491ddfe5c43a79b43f062f719ccbe03772b52",
  {
    input: {
      seed: -1,
      top_k: 20,
      top_p: 1,
      prompt: "USER: Hello, who are you?\nASSISTANT:",
      max_tokens: 50,
      min_tokens: 1,
      temperature: 0.5,
      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

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 nwhitehead/llama2-7b-chat-gptq using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "nwhitehead/llama2-7b-chat-gptq:8c1f632f7a9df740bfbe8f6b35e491ddfe5c43a79b43f062f719ccbe03772b52",
    input={
        "seed": -1,
        "top_k": 20,
        "top_p": 1,
        "prompt": "USER: Hello, who are you?\nASSISTANT:",
        "max_tokens": 50,
        "min_tokens": 1,
        "temperature": 0.5,
        "repetition_penalty": 1
    }
)

# The nwhitehead/llama2-7b-chat-gptq 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/nwhitehead/llama2-7b-chat-gptq/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 nwhitehead/llama2-7b-chat-gptq 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": "nwhitehead/llama2-7b-chat-gptq:8c1f632f7a9df740bfbe8f6b35e491ddfe5c43a79b43f062f719ccbe03772b52",
    "input": {
      "seed": -1,
      "top_k": 20,
      "top_p": 1,
      "prompt": "USER: Hello, who are you?\\nASSISTANT:",
      "max_tokens": 50,
      "min_tokens": 1,
      "temperature": 0.5,
      "repetition_penalty": 1
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

No output yet! Press "Submit" to start a prediction.