kcaverly/nexus-raven-v2-13b-gguf 📝🔢 → 📝

▶️ 179 runs 📅 Dec 2023 ⚙️ Cog 0.8.6 🔗 GitHub 📄 Paper ⚖️ License

code-generation function-calling text-generation

About

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

Example Output

Prompt:

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?

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:

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.
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.
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.

Performance Metrics

8.01s Prediction Time

35.02s Total Time

All Input Parameters

{
  "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
}

Input Parameters

prompt (required) Type: string: Instruction for model
temperature Type: numberDefault: 0.001: 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.
max_new_tokens Type: integerDefault: -1: Maximum new tokens to generate.

Output Schema

Output

Type: array • Items Type: string

Example Execution Logs

llama_print_timings:        load time =     158.92 ms
llama_print_timings:      sample time =      52.20 ms /   370 runs   (    0.14 ms per token,  7087.99 tokens per second)
llama_print_timings: prompt eval time =     158.68 ms /   183 tokens (    0.87 ms per token,  1153.29 tokens per second)
llama_print_timings:        eval time =    7089.73 ms /   369 runs   (   19.21 ms per token,    52.05 tokens per second)
llama_print_timings:       total time =    7997.34 ms

Version Details

Version ID: adc42ab5943973f0ce05425376b2d5ff48eda3f5735ab3598cce028a54251b2f
Version Created: December 11, 2023

Run on Replicate →