antoinelyset/openhermes-2-mistral-7b – Run with an API on Replicate

antoinelyset / openhermes-2-mistral-7b

Simple version of https://huggingface.co/teknium/OpenHermes-2-Mistral-7B

Cold

Public
244 runs
L40S
GitHub
Paper
License

Iterate in playground

Run with an API

Playground API Examples README Versions

Input

prompt

*string

Shift + Return to add a new line

[
      {
        "role": "system",
        "content": "You are a helpful assistant."
      },
      {
        "role": "user",
        "content": "What is Slite?"
      }
    ][
      {
        "role": "system",
        "content": "You are a helpful assistant."
      },
      {
        "role": "user",
        "content": "What is Slite?"
      }
    ]

The JSON stringified of the messages (array of objects with role/content like OpenAI) to predict on

max_new_tokens

integer

(minimum: 1)

Max new tokens

Default: 512

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

top_p

number

(minimum: 0, maximum: 1)

When decoding text, samples from the top p percentage of most likely tokens; lower to ignore less likely tokens

Default: 0.9

top_k

integer

(minimum: 0)

When decoding text, samples from the top k most likely tokens; lower to ignore less likely tokens

Default: 50

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

npx create-replicate --model=antoinelyset/openhermes-2-mistral-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 antoinelyset/openhermes-2-mistral-7b using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "antoinelyset/openhermes-2-mistral-7b:4a459338d2bd1ba653184c49e1424bc0792432bfbe1aa4e43837528f0134cae4",
  {
    input: {
      top_k: 50,
      top_p: 0.9,
      prompt: "[\n      {\n        \"role\": \"system\",\n        \"content\": \"You are a helpful assistant.\"\n      },\n      {\n        \"role\": \"user\",\n        \"content\": \"What is Slite?\"\n      }\n    ]",
      temperature: 0.75,
      max_new_tokens: 512
    }
  }
);

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 antoinelyset/openhermes-2-mistral-7b using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "antoinelyset/openhermes-2-mistral-7b:4a459338d2bd1ba653184c49e1424bc0792432bfbe1aa4e43837528f0134cae4",
    input={
        "top_k": 50,
        "top_p": 0.9,
        "prompt": "[\n      {\n        \"role\": \"system\",\n        \"content\": \"You are a helpful assistant.\"\n      },\n      {\n        \"role\": \"user\",\n        \"content\": \"What is Slite?\"\n      }\n    ]",
        "temperature": 0.75,
        "max_new_tokens": 512
    }
)

# The antoinelyset/openhermes-2-mistral-7b 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/antoinelyset/openhermes-2-mistral-7b/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 antoinelyset/openhermes-2-mistral-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": "antoinelyset/openhermes-2-mistral-7b:4a459338d2bd1ba653184c49e1424bc0792432bfbe1aa4e43837528f0134cae4",
    "input": {
      "top_k": 50,
      "top_p": 0.9,
      "prompt": "[\\n      {\\n        \\"role\\": \\"system\\",\\n        \\"content\\": \\"You are a helpful assistant.\\"\\n      },\\n      {\\n        \\"role\\": \\"user\\",\\n        \\"content\\": \\"What is Slite?\\"\\n      }\\n    ]",
      "temperature": 0.75,
      "max_new_tokens": 512
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

Slite is a collaborative workspace for teams that provides a centralized platform for creating, organizing, and sharing documents, notes, and files. It is designed to help teams improve their productivity, communication, and knowledge management. Slite offers features such as real-time collaboration, task management, note-taking, document organization, and search functionality, making it easy for team members to access and work on documents together.

{
  "completed_at": "2023-11-02T14:28:13.138964Z",
  "created_at": "2023-11-02T14:28:09.530380Z",
  "data_removed": false,
  "error": null,
  "id": "n25q3wtbjbefplybohc3acamji",
  "input": {
    "top_k": 50,
    "top_p": 0.9,
    "prompt": "[\n      {\n        \"role\": \"system\",\n        \"content\": \"You are a helpful assistant.\"\n      },\n      {\n        \"role\": \"user\",\n        \"content\": \"What is Slite?\"\n      }\n    ]",
    "temperature": 0.75,
    "max_new_tokens": 512
  },
  "logs": "The attention mask and the pad token id were not set. As a consequence, you may observe unexpected behavior. Please pass your input's `attention_mask` to obtain reliable results.\nSetting `pad_token_id` to `eos_token_id`:32000 for open-end generation.",
  "metrics": {
    "predict_time": 3.637687,
    "total_time": 3.608584
  },
  "output": [
    "",
    "",
    "Slite ",
    "is ",
    "a ",
    "",
    "collaborative ",
    "workspace ",
    "for ",
    "teams ",
    "that ",
    "provides ",
    "a ",
    "",
    "centralized ",
    "platform ",
    "for ",
    "",
    "creating, ",
    "",
    "",
    "organizing, ",
    "and ",
    "sharing ",
    "",
    "documents, ",
    "",
    "notes, ",
    "and ",
    "",
    "files. ",
    "It ",
    "is ",
    "designed ",
    "to ",
    "help ",
    "teams ",
    "improve ",
    "their ",
    "",
    "productivity, ",
    "",
    "communication, ",
    "and ",
    "knowledge ",
    "",
    "management. ",
    "",
    "Slite ",
    "offers ",
    "features ",
    "such ",
    "as ",
    "",
    "",
    "real-time ",
    "",
    "collaboration, ",
    "task ",
    "",
    "management, ",
    "",
    "",
    "",
    "",
    "note-taking, ",
    "document ",
    "",
    "organization, ",
    "and ",
    "search ",
    "",
    "functionality, ",
    "making ",
    "it ",
    "easy ",
    "for ",
    "team ",
    "members ",
    "to ",
    "access ",
    "and ",
    "work ",
    "on ",
    "documents ",
    "",
    "",
    "together."
  ],
  "started_at": "2023-11-02T14:28:09.501277Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/n25q3wtbjbefplybohc3acamji",
    "cancel": "https://api.replicate.com/v1/predictions/n25q3wtbjbefplybohc3acamji/cancel"
  },
  "version": "8b1782b697a9f67a3ddf1499a4bbcc69a8ba8d18b6274c47847d62881f607f05"
}

Generated in

3.6 seconds

Tweak it Report

This output was created using a different version of the model, antoinelyset/openhermes-2-mistral-7b:8b1782b6.

Run time and cost

This model runs on Nvidia L40S GPU hardware. We don't yet have enough runs of this model to provide performance information.

Readme

Adaptation of https://huggingface.co/teknium/OpenHermes-2-Mistral-7B, this is my first test so it maybe a bit too simple.

I preferred to use OpenAI prompt format, and let apply_chat_template do the work:

[
  {"role": "system", "content": "You are a helpful assistant."},
  {"role": "user", "content": "Who won the world series in 2020?"},
  {"role": "assistant", "content": "The Los Angeles Dodgers won the World Series in 2020."},
  {"role": "user", "content": "Where was it played?"}
]