01-ai/yi-34b-200k – Run with an API on Replicate

01-ai / yi-34b-200k

The Yi series models are large language models trained from scratch by developers at 01.AI.

Cold

Public
1.7K runs
L40S
GitHub
License

Run with an API

Playground API Examples README Versions

Input

prompt

*string

Shift + Return to add a new line

Here is the itinerary for my dog's birthday party:
Here is the itinerary for my dog's birthday party:

max_new_tokens

integer

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

Default: 512

temperature

number

The value used to modulate the next token probabilities.

Default: 0.8

top_p

number

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

Presence penalty

Default: 0

frequency_penalty

number

Frequency penalty

Default: 0

prompt_template

string

Shift + Return to add a new line

The template used to format the prompt. The input prompt is inserted into the template using the `{prompt}` placeholder.

Default: "{prompt}"

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

npx create-replicate --model=01-ai/yi-34b-200k

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 01-ai/yi-34b-200k using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "01-ai/yi-34b-200k:9060f47173629dc2a77c067b7c4a5d260dc1e32e303a99298994d0ab8e903118",
  {
    input: {
      top_k: 50,
      top_p: 0.95,
      prompt: "Here is the itinerary for my dog's birthday party:\n",
      temperature: 0.8,
      max_new_tokens: 512,
      prompt_template: "{prompt}",
      presence_penalty: 0,
      frequency_penalty: 0
    }
  }
);
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 01-ai/yi-34b-200k using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "01-ai/yi-34b-200k:9060f47173629dc2a77c067b7c4a5d260dc1e32e303a99298994d0ab8e903118",
    input={
        "top_k": 50,
        "top_p": 0.95,
        "prompt": "Here is the itinerary for my dog's birthday party:\n",
        "temperature": 0.8,
        "max_new_tokens": 512,
        "prompt_template": "{prompt}",
        "presence_penalty": 0,
        "frequency_penalty": 0
    }
)

# The 01-ai/yi-34b-200k 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/01-ai/yi-34b-200k/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 01-ai/yi-34b-200k 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": "9060f47173629dc2a77c067b7c4a5d260dc1e32e303a99298994d0ab8e903118",
    "input": {
      "top_k": 50,
      "top_p": 0.95,
      "prompt": "Here is the itinerary for my dog\'s birthday party:\\n",
      "temperature": 0.8,
      "max_new_tokens": 512,
      "prompt_template": "{prompt}",
      "presence_penalty": 0,
      "frequency_penalty": 0
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

10:00 AM - Guests arrive 10:30 AM - Pupcakes and dog-friendly treats 11:00 AM - Games and activities 12:00 PM - Cake and ice cream 1:00 PM - Goodbye hugs and take home treats "Wow!" Sophie exclaims. "That sounds like an amazing party! I'm sure Daisy will have a great time." "Thanks, Sophie! I can't wait for Daisy to celebrate her special day with her friends." As the party draws to a close, everyone gathers around Daisy, who is now surrounded by colorful balloons and party decorations. The guests sing "Happy Birthday" to Daisy, and she wags her tail excitedly. "Wow, Daisy! I can't believe how much fun we all had at your party!" says Sophie, holding Daisy's paw. "Me too! I'm so happy my friends came to celebrate with me." "You know what, Daisy? I think it's time for another playdate soon, so we can continue our adventures together!" "Yes! Let's plan another playdate soon. I can't wait to see you again, Sophie!" As the guests start to leave, Daisy and Sophie say goodbye, promising to meet again soon. The party ends on a high note, filled with laughter, fun, and lots of love for Daisy.

{
  "completed_at": "2023-11-14T21:04:28.562399Z",
  "created_at": "2023-11-14T21:03:42.077870Z",
  "data_removed": false,
  "error": null,
  "id": "jn7w6ktbxp4khkvw2flilic26e",
  "input": {
    "top_k": 50,
    "top_p": 0.95,
    "prompt": "Here is the itinerary for my dog's birthday party:\n",
    "temperature": 0.8,
    "max_new_tokens": 512,
    "prompt_template": "{prompt}",
    "presence_penalty": 0,
    "frequency_penalty": 0
  },
  "logs": "Generated 319 tokens in 11.517454862594604 seconds.",
  "metrics": {
    "predict_time": 11.523663,
    "total_time": 46.484529
  },
  "output": [
    "\n",
    "1",
    "0",
    ":",
    "0",
    "0",
    " AM",
    " -",
    " Guests",
    " arrive",
    "\n",
    "\n",
    "1",
    "0",
    ":",
    "3",
    "0",
    " AM",
    " -",
    " Pup",
    "c",
    "akes",
    " and",
    " dog",
    "-",
    "friendly",
    " treats",
    "\n",
    "\n",
    "1",
    "1",
    ":",
    "0",
    "0",
    " AM",
    " -",
    " Games",
    " and",
    " activities",
    "\n",
    "\n",
    "1",
    "2",
    ":",
    "0",
    "0",
    " PM",
    " -",
    " Cake",
    " and",
    " ice",
    " cream",
    "\n",
    "\n",
    "1",
    ":",
    "0",
    "0",
    " PM",
    " -",
    " Good",
    "bye",
    " hugs",
    " and",
    " take",
    " home",
    " treats",
    "\n",
    "\n",
    "\"",
    "Wow",
    "!",
    "\"",
    " Sophie",
    " ex",
    "claims",
    ".",
    " \"",
    "That",
    " sounds",
    " like",
    " an",
    " amazing",
    " party",
    "!",
    " I",
    "'",
    "m",
    " sure",
    " Daisy",
    " will",
    " have",
    " a",
    " great",
    " time",
    ".",
    "\"",
    "\n",
    "\n",
    "\"",
    "Thanks",
    ",",
    " Sophie",
    "!",
    " I",
    " can",
    "'",
    "t",
    " wait",
    " for",
    " Daisy",
    " to",
    " celebrate",
    " her",
    " special",
    " day",
    " with",
    " her",
    " friends",
    ".",
    "\"",
    "\n",
    "\n",
    "As",
    " the",
    " party",
    " draws",
    " to",
    " a",
    " close",
    ",",
    " everyone",
    " gather",
    "s",
    " around",
    " Daisy",
    ",",
    " who",
    " is",
    " now",
    " surrounded",
    " by",
    " colorful",
    " balloons",
    " and",
    " party",
    " decorations",
    ".",
    " The",
    " guests",
    " sing",
    " \"",
    "Happy",
    " Birthday",
    "\"",
    " to",
    " Daisy",
    ",",
    " and",
    " she",
    " w",
    "ags",
    " her",
    " tail",
    " excited",
    "ly",
    ".",
    "\n",
    "\n",
    "\"",
    "Wow",
    ",",
    " Daisy",
    "!",
    " I",
    " can",
    "'",
    "t",
    " believe",
    " how",
    " much",
    " fun",
    " we",
    " all",
    " had",
    " at",
    " your",
    " party",
    "!",
    "\"",
    " says",
    " Sophie",
    ",",
    " holding",
    " Daisy",
    "'",
    "s",
    " paw",
    ".",
    "\n",
    "\n",
    "\"",
    "Me",
    " too",
    "!",
    " I",
    "'",
    "m",
    " so",
    " happy",
    " my",
    " friends",
    " came",
    " to",
    " celebrate",
    " with",
    " me",
    ".",
    "\"",
    "\n",
    "\n",
    "\"",
    "You",
    " know",
    " what",
    ",",
    " Daisy",
    "?",
    " I",
    " think",
    " it",
    "'",
    "s",
    " time",
    " for",
    " another",
    " play",
    "date",
    " soon",
    ",",
    " so",
    " we",
    " can",
    " continue",
    " our",
    " adventures",
    " together",
    "!",
    "\"",
    "\n",
    "\n",
    "\"",
    "Yes",
    "!",
    " Let",
    "'",
    "s",
    " plan",
    " another",
    " play",
    "date",
    " soon",
    ".",
    " I",
    " can",
    "'",
    "t",
    " wait",
    " to",
    " see",
    " you",
    " again",
    ",",
    " Sophie",
    "!",
    "\"",
    "\n",
    "\n",
    "As",
    " the",
    " guests",
    " start",
    " to",
    " leave",
    ",",
    " Daisy",
    " and",
    " Sophie",
    " say",
    " goodbye",
    ",",
    " promising",
    " to",
    " meet",
    " again",
    " soon",
    ".",
    " The",
    " party",
    " ends",
    " on",
    " a",
    " high",
    " note",
    ",",
    " filled",
    " with",
    " laughter",
    ",",
    " fun",
    ",",
    " and",
    " lots",
    " of",
    " love",
    " for",
    " Daisy",
    ".",
    ""
  ],
  "started_at": "2023-11-14T21:04:17.038736Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/jn7w6ktbxp4khkvw2flilic26e",
    "cancel": "https://api.replicate.com/v1/predictions/jn7w6ktbxp4khkvw2flilic26e/cancel"
  },
  "version": "9060f47173629dc2a77c067b7c4a5d260dc1e32e303a99298994d0ab8e903118"
}

Generated in

11.5 seconds

Tweak it Report

Run time and cost

This model costs approximately $0.00098 to run on Replicate, or 1020 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 1 seconds. The predict time for this model varies significantly based on the inputs.

Readme

See the full model card here

The model served here is the AWQ quantized version from here. Thank you to @TheBloke for sharing this model!

NOTE: As per the license, replicate was granted permission to share the model here.

NOTE: The sequence length here is limited to 8024 tokens due to GPU memory constraints.