nexusraven

Nexus Raven is a 13B instruction tuned model for function calling tasks.

13b
Hızlı Kurulum (Ollama kuruluysa)
ollama run nexusraven

Ollama kurulu değil mi? ollama.com/download — Windows, macOS ve Linux için ücretsiz. İlk çalıştırmada model indirilir, sonrası tamamen çevrimdışıdır.

Varyantlar

Boyut büyüdükçe kalite artar, donanım ihtiyacı yükselir. Başlangıç için küçük varyantı deneyin.

EtiketBoyutBağlamGirdiKomut
latest 7.4GB 16K Text ollama run nexusraven:latest
13b 7.4GB 16K Text ollama run nexusraven:13b
13b-v2-q2_K 5.4GB 16K Text ollama run nexusraven:13b-v2-q2_K
13b-v2-q3_K_S 5.7GB 16K Text ollama run nexusraven:13b-v2-q3_K_S
13b-v2-q3_K_M 6.3GB 16K Text ollama run nexusraven:13b-v2-q3_K_M
13b-v2-q3_K_L 6.9GB 16K Text ollama run nexusraven:13b-v2-q3_K_L
13b-v2-q4_0 7.4GB 16K Text ollama run nexusraven:13b-v2-q4_0
13b-v2-q4_1 8.2GB 16K Text ollama run nexusraven:13b-v2-q4_1
13b-v2-q4_K_S 7.4GB 16K Text ollama run nexusraven:13b-v2-q4_K_S
13b-v2-q4_K_M 7.9GB 16K Text ollama run nexusraven:13b-v2-q4_K_M
13b-v2-q5_0 9.0GB 16K Text ollama run nexusraven:13b-v2-q5_0
13b-v2-q5_1 9.8GB 16K Text ollama run nexusraven:13b-v2-q5_1
13b-v2-q5_K_S 9.0GB 16K Text ollama run nexusraven:13b-v2-q5_K_S
13b-v2-q5_K_M 9.2GB 16K Text ollama run nexusraven:13b-v2-q5_K_M
13b-v2-q6_K 11GB 16K Text ollama run nexusraven:13b-v2-q6_K
13b-v2-q8_0 14GB 16K Text ollama run nexusraven:13b-v2-q8_0
13b-v2-fp16 26GB 16K Text ollama run nexusraven:13b-v2-fp16
13b-q2_K 5.4GB 16K Text ollama run nexusraven:13b-q2_K
13b-q3_K_S 5.7GB 16K Text ollama run nexusraven:13b-q3_K_S
13b-q3_K_M 6.3GB 16K Text ollama run nexusraven:13b-q3_K_M
13b-q3_K_L 6.9GB 16K Text ollama run nexusraven:13b-q3_K_L
13b-q4_0 7.4GB 16K Text ollama run nexusraven:13b-q4_0
13b-q4_1 8.2GB 16K Text ollama run nexusraven:13b-q4_1
13b-q4_K_S 7.4GB 16K Text ollama run nexusraven:13b-q4_K_S
13b-q4_K_M 7.9GB 16K Text ollama run nexusraven:13b-q4_K_M

7 varyant daha var — tümü için ollama.com.

Model Detayları ve Benchmarklar (kaynak: ollama.com)

Nexus Raven is a 13 billion parameter model designed for function calling tasks.

Updated to NexusRaven-V2, this model is an updated open-source and commercially viable function calling model:

  • Versatile Function Calling Capability: capable of generating single function calls, nested calls, and parallel calls in many challenging cases.
  • Fully Explainable: capable of generating very detailed explanations for the function calls it generates. This behavior can be turned off, to save tokens during inference.
  • Performance Highlights: surpasses GPT-4 by up to 7% in function calling success rates in human-generated use cases involving nested and composite functions.
  • Generalization to the Unseen: has never been trained on the functions used in evaluation.
  • Commercially Permissive: The training does not involve any data generated by proprietary LLMs such as GPT-4. You have full control of the model when deployed in commercial applications.

Example 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: {query}<human_end>

This will generate a response similar to:

Call: get_weather_data(coordinates=get_coordinates_from_city(city_name='Seattle'))<bot_end>
Thought: The function call `get_weather_data(coordinates=get_coordinates_from_city(city_name='Seattle'))` answers the question "What's the weather like in Seattle right now?" by following these steps:

1. `get_coordinates_from_city(city_name='Seattle')`: This function call fetches the latitude and longitude of the city "Seattle" using the Maps.co Geocoding API.
2. `get_weather_data(coordinates=...)`: This function call fetches the current weather data for the coordinates returned by the previous function call.

Therefore, the function call `get_weather_data(coordinates=get_coordinates_from_city(city_name='Seattle'))` answers the question "What's the weather like in Seattle right now?" by first fetching the coordinates of the city "Seattle" and then fetching the current weather data for those coordinates.

References

GitHub

Hugging Face