NexusRaven-V2-13B
Maintainer: Nexusflow
417
🧠
| Property | Value |
|---|---|
| Run this model | Run on HuggingFace |
| API spec | View on HuggingFace |
| Github link | No Github link provided |
| Paper link | No paper link provided |
Create account to get full access
Model Overview
The NexusRaven-V2-13B is an open-source and commercially viable large language model (LLM) developed by Nexusflow that surpasses the state-of-the-art in function calling capabilities. It is capable of generating single function calls, nested calls, and parallel calls across many challenging cases. The model has been fine-tuned on a large corpus of function calls and can provide detailed explanations for the function calls it generates.
Compared to the GPT-4 model, NexusRaven-V2-13B achieves a 7% higher function calling success rate on human-generated use cases involving nested and composite functions. Notably, the model has never been trained on the specific functions used in the evaluation, demonstrating strong generalization to the unseen. The training data for the model does not include any proprietary data from models like GPT-4, giving users full control when deploying it in commercial applications.
Model Inputs and Outputs
Inputs
- List of Python functions: The model accepts a list of Python functions as input. The functions can perform any task, including sending GET/POST requests to external APIs.
- Function signatures and docstrings: To enable the model to generate function calls, the input must include the Python function signature and an appropriate docstring.
- Function arguments: The model performs best on functions that require arguments, so users should provide functions with arguments.
Outputs
- Function calls: The primary output of the model is function calls, which can be single, nested, or parallel.
- Detailed explanations: The model can also generate detailed explanations for the function calls it produces, though this behavior can be turned off to save tokens during inference.
Capabilities
The NexusRaven-V2-13B model excels at zero-shot function calling, surpassing the performance of GPT-4 by a significant margin. It can handle a wide range of function call types, from simple single calls to complex nested and parallel calls. The model's ability to generalize to unseen functions is particularly impressive, as it demonstrates its versatility and potential for real-world applications.
What Can I Use it For?
The NexusRaven-V2-13B model is well-suited for a variety of applications that require function calling capabilities, such as:
- Automated software development: The model can be used to assist developers in writing and orchestrating complex software systems by generating function calls on-the-fly.
- Intelligent virtual assistants: The model's function calling abilities can be leveraged to build virtual assistants that can perform a wide range of tasks by dynamically calling relevant functions.
- Data processing and analysis: The model's function calling capabilities can be used to build pipelines for data processing and analysis, automating complex workflows.
Things to Try
One interesting thing to try with the NexusRaven-V2-13B model is to provide it with a diverse set of custom functions and observe how it handles the function calling process. You can experiment with different types of functions, including those that interact with external APIs, to see the model's versatility and adaptability. Additionally, you can explore the model's ability to generate detailed explanations for the function calls it produces and how this feature can be leveraged in various applications.
This summary was produced with help from an AI and may contain inaccuracies - check out the links to read the original source documents!
Related Models
👁️
NexusRaven-13B
97
NexusRaven-13B is an open-source and commercially viable function calling language model developed by Nexusflow that surpasses the state-of-the-art in function calling capabilities. It was fine-tuned from the codellama/CodeLlama-13b-Instruct-hf model. Compared to GPT-4, NexusRaven-13B achieves a 95% success rate in using cybersecurity tools like CVE/CPE Search and VirusTotal, while GPT-4 achieves 64%. It has significantly lower cost and faster inference speed. NexusRaven-13B also generalizes well to tools never seen during training, achieving performance comparable to GPT-3.5 in zero-shot settings, outperforming other open-source LLMs of similar sizes. Model inputs and outputs NexusRaven-13B is a function calling language model that takes in a list of Python functions with their docstrings and generates JSON outputs with the function name and arguments. The model works best when provided with well-documented functions that have arguments, whether required or optional. Inputs Functions**: A list of Python functions with their docstrings User Query**: A prompt for the model to generate a function call response to Outputs Function Call**: A JSON object with the function name and argument values Explanation (optional)**: A detailed explanation of the generated function call Capabilities NexusRaven-13B is capable of generating single function calls, nested calls, and parallel calls in many challenging cases. It can also provide detailed explanations for the function calls it generates, which can be turned off to save tokens during inference. What can I use it for? NexusRaven-13B can be used in a variety of applications that require interacting with APIs or executing functions based on user prompts. For example, you could use it to build a chatbot that can perform web scraping, make API calls, or execute other programmatic tasks on demand. The model's strong performance on cybersecurity tools makes it a promising candidate for building security-focused applications. Things to try One interesting thing to try with NexusRaven-13B is to provide it with a set of functions that interact with external APIs, such as fetching weather data or geolocating a city. You can then prompt the model to generate function calls that combine these capabilities to answer complex user queries, like "What's the weather like in Seattle right now?". The model's ability to chain together function calls and provide detailed explanations can make it a powerful tool for building conversational AI applications.
Updated Invalid Date
💬
NexusRaven-V2-13B-GGUF
48
The NexusRaven-V2-13B-GGUF is a large language model created by Nexusflow and quantized in the GGUF format by TheBloke. It is based on the original NexusRaven V2 13B model. The GGUF format offers improved tokenization and support for special tokens compared to the previous GGML format. Model inputs and outputs Inputs Text prompt**: The model accepts natural language text prompts as input. Outputs Text generation**: The model can generate coherent and contextual text continuations of the input prompt. Capabilities The NexusRaven-V2-13B-GGUF model demonstrates strong natural language understanding and generation capabilities. It can engage in open-ended conversations, summarize information, and answer questions on a wide range of topics. The model's capabilities make it well-suited for tasks like chatbots, content generation, and language-based AI assistants. What can I use it for? The NexusRaven-V2-13B-GGUF model could be used for a variety of natural language processing applications. Some potential use cases include: Conversational AI**: Integrating the model into a chatbot or virtual assistant to engage in open-ended conversations and assist users with a range of tasks. Content generation**: Using the model to generate articles, stories, scripts, or other forms of written content. Summarization**: Leveraging the model's text summarization capabilities to condense long-form text into concise summaries. Question answering**: Deploying the model to answer questions on a variety of topics, drawing upon its broad knowledge base. Things to try Experiment with providing the model with different types of prompts, such as open-ended questions, creative writing prompts, or task-oriented instructions. Observe how the model responds and generates text, noting its coherence, contextual awareness, and ability to stay on topic. Additionally, try varying the model parameters, like temperature and repetition penalty, to see how they affect the output.
Updated Invalid Date
↗️
glaive-function-calling-v1
64
glaive-function-calling-v1 is a 2.7B parameter AI model trained by glaiveai that has similar function calling abilities as GPT-3.5 and GPT-4. It is built on top of the replit/replit-code-v1-3b model and can have multi-turn conversations, intelligently choosing when to execute a provided function based on the conversation. Similar models include gorilla-openfunctions-v1 and gorilla-openfunctions-v2, which also provide function calling capabilities. Model inputs and outputs Inputs A provided function specification in JSON format at the start of the conversation User prompts that can reference the provided functions Outputs Function calls in the format {...} Responses that incorporate the results of the executed functions Capabilities The glaive-function-calling-v1 model can intelligently decide when to execute a provided function based on the conversation context. It supports multi-turn interactions, allowing the user to build upon previous function calls. What can I use it for? The glaive-function-calling-v1 model could be useful for building conversational applications that allow users to interact with and execute specific functions, such as planning a vacation, booking a ride, or retrieving information. Its ability to have multi-turn dialogues and choose when to execute functions makes it well-suited for interactive, task-oriented applications. Things to try One interesting thing to try with glaive-function-calling-v1 would be to provide it with a diverse set of functions and see how it handles more complex, multi-step request flows. You could also experiment with different types of functions beyond the vacation planning example, to see how the model generalizes to other domains.
Updated Invalid Date
👁️
Llama-2-7b-chat-hf-function-calling
47
The Llama-2-7b-chat-hf-function-calling model extends the popular Hugging Face Llama 2 models with function calling capabilities. Developed by Trelis, this model responds with a structured JSON argument containing the function name and arguments, allowing for seamless integration into applications that require programmatic interactions. Model inputs and outputs Inputs Text**: The model takes text prompts as input, which can include instructions for the desired function to be executed. Outputs Structured JSON**: The model generates a JSON object with two key-value pairs - "function" (the name of the function) and "arguments" (the arguments for the function). Capabilities The Llama-2-7b-chat-hf-function-calling model is capable of understanding function call requests and generating the appropriate JSON response. This allows developers to easily incorporate the model's functionality into their applications, automating tasks and integrating with various systems. What can I use it for? With the function calling capabilities of this model, you can build applications that streamline workflows, automate repetitive tasks, and enhance user experiences. Some potential use cases include: Developing intelligent chatbots or virtual assistants that can execute specific functions on behalf of users Integrating the model into business software to enable natural language-driven automation Building productivity tools that allow users to issue commands and have the model handle the underlying logic Things to try One interesting aspect of this model is its ability to handle function calls with varying numbers of arguments, from 0 to 3. You can experiment with different function descriptions and prompts to see how the model responds, ensuring that the expected JSON format is generated correctly. Additionally, you can explore how the model's performance scales with larger parameter sizes, such as the 13B, 70B, and other versions available from the Trelis creator profile.
Updated Invalid Date