tomasmcm/mistral-trismegistus-7b – Run with an API on Replicate

tomasmcm / mistral-trismegistus-7b

Source: teknium/Mistral-Trismegistus-7B ✦ Quant: TheBloke/Mistral-Trismegistus-7B-AWQ ✦ Mistral Trismegistus is a model made for people interested in the esoteric, occult, and spiritual

Cold

Public
597 runs
L40S
Paper
License

Run with an API

Playground API Examples README Versions

Input

prompt

*string

Shift + Return to add a new line

USER: What is the philosopher’s stone, really?
ASSISTANT:
USER: What is the philosopher’s stone, really?
ASSISTANT:

Text prompt to send to the model.

max_new_tokens

integer

The maximum number of tokens the model should generate as output.

Default: 128

temperature

number

(minimum: 0.01, maximum: 5)

The value used to modulate the next token probabilities.

Default: 0.8

top_p

number

(minimum: 0.01, maximum: 1)

A probability threshold for generating the output. If < 1.0, only keep the top tokens with cumulative probability >= top_p (nucleus filtering). Nucleus filtering is described in Holtzman et al. (http://arxiv.org/abs/1904.09751).

Default: 0.95

top_k

integer

The number of highest probability tokens to consider for generating the output. If > 0, only keep the top k tokens with highest probability (top-k filtering).

Default: 50

presence_penalty

number

(minimum: 0.01, maximum: 5)

Presence penalty

Default: 1

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

npx create-replicate --model=tomasmcm/mistral-trismegistus-7b

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 tomasmcm/mistral-trismegistus-7b using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "tomasmcm/mistral-trismegistus-7b:645e682e1c915509bf8f64059a13e84ddd837e8209cfbe56ca0750604018dc88",
  {
    input: {
      top_k: 50,
      top_p: 0.95,
      prompt: "USER: What is the philosopher’s stone, really?\nASSISTANT:\n",
      temperature: 0.8,
      max_new_tokens: 128,
      presence_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 tomasmcm/mistral-trismegistus-7b using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "tomasmcm/mistral-trismegistus-7b:645e682e1c915509bf8f64059a13e84ddd837e8209cfbe56ca0750604018dc88",
    input={
        "top_k": 50,
        "top_p": 0.95,
        "prompt": "USER: What is the philosopher’s stone, really?\nASSISTANT:\n",
        "temperature": 0.8,
        "max_new_tokens": 128,
        "presence_penalty": 1
    }
)
print(output)

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 tomasmcm/mistral-trismegistus-7b 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": "645e682e1c915509bf8f64059a13e84ddd837e8209cfbe56ca0750604018dc88",
    "input": {
      "top_k": 50,
      "top_p": 0.95,
      "prompt": "USER: What is the philosopher’s stone, really?\\nASSISTANT:\\n",
      "temperature": 0.8,
      "max_new_tokens": 128,
      "presence_penalty": 1
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

The philosopher's stone, also known as the magnum opus or the great work, is a legendary substance that was purported to possess the power of turning base metals into gold and bestowing immortality on its possessor. It has been sought after by alchemists for centuries, and its discovery was thought to be the key to unlocking the secrets of the universe. To understand what the philosopher's stone really is, it's essential to delve into its history, benefits, and connection to alchemy. History: The concept of the philosopher's stone

Generated in

1.7 seconds

Tweak it Report

Run time and cost

This model costs approximately $0.0059 to run on Replicate, or 169 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 L40S GPU hardware. Predictions typically complete within 7 seconds.

Readme

Here are some outputs:

Answer questions about occult artifacts: image/png

Play the role of a hypnotist: image/png

Special Features:

The First Powerful Occult Expert Model: ~10,000 high quality, deep, rich, instructions on the occult, esoteric, and spiritual.
Fast: Trained on Mistral, a state of the art 7B parameter model, you can run this model FAST on even a cpu.
Not a positivity-nazi: This model was trained on all forms of esoteric tasks and knowledge, and is not burdened by the flowery nature of many other models, who chose positivity over creativity.

Acknowledgements:

Special thanks to @a16z.

Dataset:

This model was trained on a 100% synthetic, gpt-4 generated dataset, about ~10,000 examples, on a wide and diverse set of both tasks and knowledge about the esoteric, occult, and spiritual.

The dataset will be released soon!

Usage:

Prompt Format:

USER: <prompt>
ASSISTANT:

<system message>
USER: <prompt>
ASSISTANT:

Benchmarks:

No benchmark can capture the nature and essense of the quality of spirituality and esoteric knowledge and tasks. You will have to try testing it yourself!

Training run on wandb here: https://wandb.ai/teknium1/occult-expert-mistral-7b/runs/coccult-expert-mistral-6/overview

Licensing:

Apache 2.0