kcaverly/nexus-raven-v2-13b-gguf – Run with an API on Replicate

kcaverly / nexus-raven-v2-13b-gguf

A quantized 13B parameter language model from NexusFlow for SOTA zero-shot function calling

Cold

Public
178 runs
L40S
GitHub
Paper
License

Run with an API

Playground API Examples README Versions

Input

prompt

*string

Shift + Return to add a new line

Function:
def get_weather_data(coordinates):
    """
    Fetches weather data from the Open-Meteo API for the given latitude and longitude.

    Args:
    coordinates (tuple): The latitude of the location.

    Returns:
    float: The current temperature in the coordinates you've asked for
    """

Function:
def get_coordinates_from_city(city_name):
    """
    Fetches the latitude and longitude of a given city name using the Maps.co Geocoding API.

    Args:
    city_name (str): The name of the city.

    Returns:
    tuple: The latitude and longitude of the city.
    """

User Query: What is the weather like in Seattle right now?<human_end>Function:
def get_weather_data(coordinates):
    """
    Fetches weather data from the Open-Meteo API for the given latitude and longitude.

    Args:
    coordinates (tuple): The latitude of the location.

    Returns:
    float: The current temperature in the coordinates you've asked for
    """

Function:
def get_coordinates_from_city(city_name):
    """
    Fetches the latitude and longitude of a given city name using the Maps.co Geocoding API.

    Args:
    city_name (str): The name of the city.

    Returns:
    tuple: The latitude and longitude of the city.
    """

User Query: What is the weather like in Seattle right now?<human_end>

Instruction for model

max_new_tokens

integer

Maximum new tokens to generate.

Default: -1

temperature

number

This parameter used to control the 'warmth' or responsiveness of an AI model based on the LLaMA architecture. It adjusts how likely the model is to generate new, unexpected information versus sticking closely to what it has been trained on. A higher value for this parameter can lead to more creative and diverse responses, while a lower value results in safer, more conservative answers that are closer to those found in its training data. This parameter is particularly useful when fine-tuning models for specific tasks where you want to balance between generating novel insights and maintaining accuracy and coherence.

Default: 0.001

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

npx create-replicate --model=kcaverly/nexus-raven-v2-13b-gguf

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 kcaverly/nexus-raven-v2-13b-gguf using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "kcaverly/nexus-raven-v2-13b-gguf:adc42ab5943973f0ce05425376b2d5ff48eda3f5735ab3598cce028a54251b2f",
  {
    input: {
      prompt: "Function:\ndef get_weather_data(coordinates):\n    \"\"\"\n    Fetches weather data from the Open-Meteo API for the given latitude and longitude.\n\n    Args:\n    coordinates (tuple): The latitude of the location.\n\n    Returns:\n    float: The current temperature in the coordinates you've asked for\n    \"\"\"\n\nFunction:\ndef get_coordinates_from_city(city_name):\n    \"\"\"\n    Fetches the latitude and longitude of a given city name using the Maps.co Geocoding API.\n\n    Args:\n    city_name (str): The name of the city.\n\n    Returns:\n    tuple: The latitude and longitude of the city.\n    \"\"\"\n\nUser Query: What is the weather like in Seattle right now?<human_end>",
      temperature: 0.001,
      max_new_tokens: -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 kcaverly/nexus-raven-v2-13b-gguf using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "kcaverly/nexus-raven-v2-13b-gguf:adc42ab5943973f0ce05425376b2d5ff48eda3f5735ab3598cce028a54251b2f",
    input={
        "prompt": "Function:\ndef get_weather_data(coordinates):\n    \"\"\"\n    Fetches weather data from the Open-Meteo API for the given latitude and longitude.\n\n    Args:\n    coordinates (tuple): The latitude of the location.\n\n    Returns:\n    float: The current temperature in the coordinates you've asked for\n    \"\"\"\n\nFunction:\ndef get_coordinates_from_city(city_name):\n    \"\"\"\n    Fetches the latitude and longitude of a given city name using the Maps.co Geocoding API.\n\n    Args:\n    city_name (str): The name of the city.\n\n    Returns:\n    tuple: The latitude and longitude of the city.\n    \"\"\"\n\nUser Query: What is the weather like in Seattle right now?<human_end>",
        "temperature": 0.001,
        "max_new_tokens": -1
    }
)

# The kcaverly/nexus-raven-v2-13b-gguf 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/kcaverly/nexus-raven-v2-13b-gguf/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 kcaverly/nexus-raven-v2-13b-gguf 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": "adc42ab5943973f0ce05425376b2d5ff48eda3f5735ab3598cce028a54251b2f",
    "input": {
      "prompt": "Function:\\ndef get_weather_data(coordinates):\\n    \\"\\"\\"\\n    Fetches weather data from the Open-Meteo API for the given latitude and longitude.\\n\\n    Args:\\n    coordinates (tuple): The latitude of the location.\\n\\n    Returns:\\n    float: The current temperature in the coordinates you\'ve asked for\\n    \\"\\"\\"\\n\\nFunction:\\ndef get_coordinates_from_city(city_name):\\n    \\"\\"\\"\\n    Fetches the latitude and longitude of a given city name using the Maps.co Geocoding API.\\n\\n    Args:\\n    city_name (str): The name of the city.\\n\\n    Returns:\\n    tuple: The latitude and longitude of the city.\\n    \\"\\"\\"\\n\\nUser Query: What is the weather like in Seattle right now?<human_end>",
      "temperature": 0.001,
      "max_new_tokens": -1
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

Call: get_weather_data(coordinates=get_coordinates_from_city(city_name='Seattle')) Thought: The function call `get_weather_data(coordinates=get_coordinates_from_city(city_name='Seattle'))` answers the question "What is the weather like in Seattle right now?" by first fetching the latitude and longitude of Seattle using the Maps.co Geocoding API, and then using those coordinates to fetch the current temperature from the Open-Meteo API. Here's a step-by-step breakdown of what happens when you call this function: 1. The `get_coordinates_from_city` function is called with the argument `'Seattle'`. This function uses the Maps.co Geocoding API to fetch the latitude and longitude of Seattle. 2. The `get_weather_data` function is then called with the coordinates returned by `get_coordinates_from_city`. This function uses the Open-Meteo API to fetch the current temperature in the given coordinates. 3. The `get_weather_data` function returns the current temperature in the coordinates you've asked for. In this case, it will return the current temperature in Seattle. Therefore, the function call `get_weather_data(coordinates=get_coordinates_from_city(city_name='Seattle'))` answers the question "What is the weather like in Seattle right now?" by first fetching the latitude and longitude of Seattle using the Maps.co Geocoding API, and then using those coordinates to fetch the current temperature from the Open-Meteo API.

{
  "completed_at": "2023-12-11T18:40:39.574879Z",
  "created_at": "2023-12-11T18:40:04.552491Z",
  "data_removed": false,
  "error": null,
  "id": "ljsylolbxfl3f3kuohlnznzgxi",
  "input": {
    "prompt": "Function:\ndef get_weather_data(coordinates):\n    \"\"\"\n    Fetches weather data from the Open-Meteo API for the given latitude and longitude.\n\n    Args:\n    coordinates (tuple): The latitude of the location.\n\n    Returns:\n    float: The current temperature in the coordinates you've asked for\n    \"\"\"\n\nFunction:\ndef get_coordinates_from_city(city_name):\n    \"\"\"\n    Fetches the latitude and longitude of a given city name using the Maps.co Geocoding API.\n\n    Args:\n    city_name (str): The name of the city.\n\n    Returns:\n    tuple: The latitude and longitude of the city.\n    \"\"\"\n\nUser Query: What is the weather like in Seattle right now?<human_end>",
    "temperature": 0.001,
    "max_new_tokens": -1
  },
  "logs": "llama_print_timings:        load time =     158.92 ms\nllama_print_timings:      sample time =      52.20 ms /   370 runs   (    0.14 ms per token,  7087.99 tokens per second)\nllama_print_timings: prompt eval time =     158.68 ms /   183 tokens (    0.87 ms per token,  1153.29 tokens per second)\nllama_print_timings:        eval time =    7089.73 ms /   369 runs   (   19.21 ms per token,    52.05 tokens per second)\nllama_print_timings:       total time =    7997.34 ms",
  "metrics": {
    "predict_time": 8.011637,
    "total_time": 35.022388
  },
  "output": [
    " ",
    "\n",
    " ",
    "\n",
    "Call",
    ":",
    " get",
    "_",
    "we",
    "ather",
    "_",
    "data",
    "(",
    "co",
    "ordinates",
    "=",
    "get",
    "_",
    "co",
    "ordinates",
    "_",
    "from",
    "_",
    "city",
    "(",
    "city",
    "_",
    "name",
    "='",
    "Se",
    "attle",
    "'))",
    "",
    " ",
    "\n",
    "Th",
    "ought",
    ":",
    " The",
    " function",
    " call",
    " `",
    "get",
    "_",
    "we",
    "ather",
    "_",
    "data",
    "(",
    "co",
    "ordinates",
    "=",
    "get",
    "_",
    "co",
    "ordinates",
    "_",
    "from",
    "_",
    "city",
    "(",
    "city",
    "_",
    "name",
    "='",
    "Se",
    "attle",
    "'))",
    "`",
    " answers",
    " the",
    " question",
    " \"",
    "What",
    " is",
    " the",
    " weather",
    " like",
    " in",
    " Seattle",
    " right",
    " now",
    "?\"",
    " by",
    " first",
    " fetch",
    "ing",
    " the",
    " latitude",
    " and",
    " longitude",
    " of",
    " Seattle",
    " using",
    " the",
    " Maps",
    ".",
    "co",
    " Ge",
    "oc",
    "oding",
    " API",
    ",",
    " and",
    " then",
    " using",
    " those",
    " coordinates",
    " to",
    " fetch",
    " the",
    " current",
    " temperature",
    " from",
    " the",
    " Open",
    "-",
    "M",
    "ete",
    "o",
    " API",
    ".",
    "\n",
    "\n",
    "Here",
    "'",
    "s",
    " a",
    " step",
    "-",
    "by",
    "-",
    "step",
    " break",
    "down",
    " of",
    " what",
    " happens",
    " when",
    " you",
    " call",
    " this",
    " function",
    ":",
    "\n",
    "\n",
    "1",
    ".",
    " The",
    " `",
    "get",
    "_",
    "co",
    "ordinates",
    "_",
    "from",
    "_",
    "city",
    "`",
    " function",
    " is",
    " called",
    " with",
    " the",
    " argument",
    " `'",
    "Se",
    "attle",
    "'",
    "`.",
    " This",
    " function",
    " uses",
    " the",
    " Maps",
    ".",
    "co",
    " Ge",
    "oc",
    "oding",
    " API",
    " to",
    " fetch",
    " the",
    " latitude",
    " and",
    " longitude",
    " of",
    " Seattle",
    ".",
    "\n",
    "2",
    ".",
    " The",
    " `",
    "get",
    "_",
    "we",
    "ather",
    "_",
    "data",
    "`",
    " function",
    " is",
    " then",
    " called",
    " with",
    " the",
    " coordinates",
    " returned",
    " by",
    " `",
    "get",
    "_",
    "co",
    "ordinates",
    "_",
    "from",
    "_",
    "city",
    "`.",
    " This",
    " function",
    " uses",
    " the",
    " Open",
    "-",
    "M",
    "ete",
    "o",
    " API",
    " to",
    " fetch",
    " the",
    " current",
    " temperature",
    " in",
    " the",
    " given",
    " coordinates",
    ".",
    "\n",
    "3",
    ".",
    " The",
    " `",
    "get",
    "_",
    "we",
    "ather",
    "_",
    "data",
    "`",
    " function",
    " returns",
    " the",
    " current",
    " temperature",
    " in",
    " the",
    " coordinates",
    " you",
    "'",
    "ve",
    " asked",
    " for",
    ".",
    " In",
    " this",
    " case",
    ",",
    " it",
    " will",
    " return",
    " the",
    " current",
    " temperature",
    " in",
    " Seattle",
    ".",
    "\n",
    "\n",
    "There",
    "fore",
    ",",
    " the",
    " function",
    " call",
    " `",
    "get",
    "_",
    "we",
    "ather",
    "_",
    "data",
    "(",
    "co",
    "ordinates",
    "=",
    "get",
    "_",
    "co",
    "ordinates",
    "_",
    "from",
    "_",
    "city",
    "(",
    "city",
    "_",
    "name",
    "='",
    "Se",
    "attle",
    "'))",
    "`",
    " answers",
    " the",
    " question",
    " \"",
    "What",
    " is",
    " the",
    " weather",
    " like",
    " in",
    " Seattle",
    " right",
    " now",
    "?\"",
    " by",
    " first",
    " fetch",
    "ing",
    " the",
    " latitude",
    " and",
    " longitude",
    " of",
    " Seattle",
    " using",
    " the",
    " Maps",
    ".",
    "co",
    " Ge",
    "oc",
    "oding",
    " API",
    ",",
    " and",
    " then",
    " using",
    " those",
    " coordinates",
    " to",
    " fetch",
    " the",
    " current",
    " temperature",
    " from",
    " the",
    " Open",
    "-",
    "M",
    "ete",
    "o",
    " API",
    ".",
    ""
  ],
  "started_at": "2023-12-11T18:40:31.563242Z",
  "status": "succeeded",
  "urls": {
    "stream": "https://streaming-api.svc.us.c.replicate.net/v1/predictions/ljsylolbxfl3f3kuohlnznzgxi",
    "get": "https://api.replicate.com/v1/predictions/ljsylolbxfl3f3kuohlnznzgxi",
    "cancel": "https://api.replicate.com/v1/predictions/ljsylolbxfl3f3kuohlnznzgxi/cancel"
  },
  "version": "adc42ab5943973f0ce05425376b2d5ff48eda3f5735ab3598cce028a54251b2f"
}

Generated in

8.0 seconds

Tweak it Report

Run time and cost

This model costs approximately $0.0084 to run on Replicate, or 119 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 9 seconds. The predict time for this model varies significantly based on the inputs.

Readme

TheBloke’s NexusRaven-V2-13B-GGUF.

This implements a quantized version of the original model, specifically the Q5_K_M version.

Full prompt examples, and templates are available here