Edit model card

TheBloke's LLM work is generously supported by a grant from andreessen horowitz (a16z)

NexusRaven V2 13B - GGUF


This repo contains GGUF format model files for Nexusflow's NexusRaven V2 13B.

These files were quantised using hardware kindly provided by Massed Compute.

About GGUF

GGUF is a new format introduced by the llama.cpp team on August 21st 2023. It is a replacement for GGML, which is no longer supported by llama.cpp.

Here is an incomplete list of clients and libraries that are known to support GGUF:

  • llama.cpp. The source project for GGUF. Offers a CLI and a server option.
  • text-generation-webui, the most widely used web UI, with many features and powerful extensions. Supports GPU acceleration.
  • KoboldCpp, a fully featured web UI, with GPU accel across all platforms and GPU architectures. Especially good for story telling.
  • GPT4All, a free and open source local running GUI, supporting Windows, Linux and macOS with full GPU accel.
  • LM Studio, an easy-to-use and powerful local GUI for Windows and macOS (Silicon), with GPU acceleration. Linux available, in beta as of 27/11/2023.
  • LoLLMS Web UI, a great web UI with many interesting and unique features, including a full model library for easy model selection.
  • Faraday.dev, an attractive and easy to use character-based chat GUI for Windows and macOS (both Silicon and Intel), with GPU acceleration.
  • llama-cpp-python, a Python library with GPU accel, LangChain support, and OpenAI-compatible API server.
  • candle, a Rust ML framework with a focus on performance, including GPU support, and ease of use.
  • ctransformers, a Python library with GPU accel, LangChain support, and OpenAI-compatible AI server. Note, as of time of writing (November 27th 2023), ctransformers has not been updated in a long time and does not support many recent models.

Repositories available

Prompt template: NexusRaven

def function_here(arg1):
    Comments explaining the function here

    list args

    list returns

def another_function_here(arg1):

User Query: {prompt}<human_end>


The creator of the source model has listed its license as other, and this quantization has therefore used that same license.

As this model is based on Llama 2, it is also subject to the Meta Llama 2 license terms, and the license files for that are additionally included. It should therefore be considered as being claimed to be licensed under both licenses. I contacted Hugging Face for clarification on dual licensing but they do not yet have an official position. Should this change, or should Meta provide any feedback on this situation, I will update this section accordingly.

In the meantime, any questions regarding licensing, and in particular how these two licenses might interact, should be directed to the original model repository: Nexusflow's NexusRaven V2 13B.


These quantised GGUFv2 files are compatible with llama.cpp from August 27th onwards, as of commit d0cee0d

They are also compatible with many third party UIs and libraries - please see the list at the top of this README.

Explanation of quantisation methods

Click to see details

The new methods available are:

  • GGML_TYPE_Q2_K - "type-1" 2-bit quantization in super-blocks containing 16 blocks, each block having 16 weight. Block scales and mins are quantized with 4 bits. This ends up effectively using 2.5625 bits per weight (bpw)
  • GGML_TYPE_Q3_K - "type-0" 3-bit quantization in super-blocks containing 16 blocks, each block having 16 weights. Scales are quantized with 6 bits. This end up using 3.4375 bpw.
  • GGML_TYPE_Q4_K - "type-1" 4-bit quantization in super-blocks containing 8 blocks, each block having 32 weights. Scales and mins are quantized with 6 bits. This ends up using 4.5 bpw.
  • GGML_TYPE_Q5_K - "type-1" 5-bit quantization. Same super-block structure as GGML_TYPE_Q4_K resulting in 5.5 bpw
  • GGML_TYPE_Q6_K - "type-0" 6-bit quantization. Super-blocks with 16 blocks, each block having 16 weights. Scales are quantized with 8 bits. This ends up using 6.5625 bpw

Refer to the Provided Files table below to see what files use which methods, and how.

Provided files

Name Quant method Bits Size Max RAM required Use case
nexusraven-v2-13b.Q2_K.gguf Q2_K 2 5.43 GB 7.93 GB smallest, significant quality loss - not recommended for most purposes
nexusraven-v2-13b.Q3_K_S.gguf Q3_K_S 3 5.66 GB 8.16 GB very small, high quality loss
nexusraven-v2-13b.Q3_K_M.gguf Q3_K_M 3 6.34 GB 8.84 GB very small, high quality loss
nexusraven-v2-13b.Q3_K_L.gguf Q3_K_L 3 6.93 GB 9.43 GB small, substantial quality loss
nexusraven-v2-13b.Q4_0.gguf Q4_0 4 7.37 GB 9.87 GB legacy; small, very high quality loss - prefer using Q3_K_M
nexusraven-v2-13b.Q4_K_S.gguf Q4_K_S 4 7.41 GB 9.91 GB small, greater quality loss
nexusraven-v2-13b.Q4_K_M.gguf Q4_K_M 4 7.87 GB 10.37 GB medium, balanced quality - recommended
nexusraven-v2-13b.Q5_0.gguf Q5_0 5 8.97 GB 11.47 GB legacy; medium, balanced quality - prefer using Q4_K_M
nexusraven-v2-13b.Q5_K_S.gguf Q5_K_S 5 8.97 GB 11.47 GB large, low quality loss - recommended
nexusraven-v2-13b.Q5_K_M.gguf Q5_K_M 5 9.23 GB 11.73 GB large, very low quality loss - recommended
nexusraven-v2-13b.Q6_K.gguf Q6_K 6 10.68 GB 13.18 GB very large, extremely low quality loss
nexusraven-v2-13b.Q8_0.gguf Q8_0 8 13.83 GB 16.33 GB very large, extremely low quality loss - not recommended

Note: the above RAM figures assume no GPU offloading. If layers are offloaded to the GPU, this will reduce RAM usage and use VRAM instead.

How to download GGUF files

Note for manual downloaders: You almost never want to clone the entire repo! Multiple different quantisation formats are provided, and most users only want to pick and download a single file.

The following clients/libraries will automatically download models for you, providing a list of available models to choose from:

  • LM Studio
  • LoLLMS Web UI
  • Faraday.dev

In text-generation-webui

Under Download Model, you can enter the model repo: TheBloke/NexusRaven-V2-13B-GGUF and below it, a specific filename to download, such as: nexusraven-v2-13b.Q4_K_M.gguf.

Then click Download.

On the command line, including multiple files at once

I recommend using the huggingface-hub Python library:

pip3 install huggingface-hub

Then you can download any individual model file to the current directory, at high speed, with a command like this:

huggingface-cli download TheBloke/NexusRaven-V2-13B-GGUF nexusraven-v2-13b.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
More advanced huggingface-cli download usage (click to read)

You can also download multiple files at once with a pattern:

huggingface-cli download TheBloke/NexusRaven-V2-13B-GGUF --local-dir . --local-dir-use-symlinks False --include='*Q4_K*gguf'

For more documentation on downloading with huggingface-cli, please see: HF -> Hub Python Library -> Download files -> Download from the CLI.

To accelerate downloads on fast connections (1Gbit/s or higher), install hf_transfer:

pip3 install hf_transfer

And set environment variable HF_HUB_ENABLE_HF_TRANSFER to 1:

HF_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download TheBloke/NexusRaven-V2-13B-GGUF nexusraven-v2-13b.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False

Windows Command Line users: You can set the environment variable by running set HF_HUB_ENABLE_HF_TRANSFER=1 before the download command.

Example llama.cpp command

Make sure you are using llama.cpp from commit d0cee0d or later.

./main -ngl 35 -m nexusraven-v2-13b.Q4_K_M.gguf --color -c 2048 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "Function:\ndef function_here(arg1):\n  """\n    Comments explaining the function here\n\n    Args:\n    list args\n\n    Returns:\n    list returns\n    """\n\nFunction:\ndef another_function_here(arg1):\n  ...\n\nUser Query: {prompt}<human_end>"

Change -ngl 32 to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.

Change -c 2048 to the desired sequence length. For extended sequence models - eg 8K, 16K, 32K - the necessary RoPE scaling parameters are read from the GGUF file and set by llama.cpp automatically. Note that longer sequence lengths require much more resources, so you may need to reduce this value.

If you want to have a chat-style conversation, replace the -p <PROMPT> argument with -i -ins

For other parameters and how to use them, please refer to the llama.cpp documentation

How to run in text-generation-webui

Further instructions can be found in the text-generation-webui documentation, here: text-generation-webui/docs/04 ‐ Model Tab.md.

How to run from Python code

You can use GGUF models from Python using the llama-cpp-python or ctransformers libraries. Note that at the time of writing (Nov 27th 2023), ctransformers has not been updated for some time and is not compatible with some recent models. Therefore I recommend you use llama-cpp-python.

How to load this model in Python code, using llama-cpp-python

For full documentation, please see: llama-cpp-python docs.

First install the package

Run one of the following commands, according to your system:

# Base ctransformers with no GPU acceleration
pip install llama-cpp-python
# With NVidia CUDA acceleration
CMAKE_ARGS="-DLLAMA_CUBLAS=on" pip install llama-cpp-python
# Or with OpenBLAS acceleration
CMAKE_ARGS="-DLLAMA_BLAS=ON -DLLAMA_BLAS_VENDOR=OpenBLAS" pip install llama-cpp-python
# Or with CLBLast acceleration
CMAKE_ARGS="-DLLAMA_CLBLAST=on" pip install llama-cpp-python
# Or with AMD ROCm GPU acceleration (Linux only)
CMAKE_ARGS="-DLLAMA_HIPBLAS=on" pip install llama-cpp-python
# Or with Metal GPU acceleration for macOS systems only
CMAKE_ARGS="-DLLAMA_METAL=on" pip install llama-cpp-python

# In windows, to set the variables CMAKE_ARGS in PowerShell, follow this format; eg for NVidia CUDA:
pip install llama-cpp-python

Simple llama-cpp-python example code

from llama_cpp import Llama

# Set gpu_layers to the number of layers to offload to GPU. Set to 0 if no GPU acceleration is available on your system.
llm = Llama(
  model_path="./nexusraven-v2-13b.Q4_K_M.gguf",  # Download the model file first
  n_ctx=2048,  # The max sequence length to use - note that longer sequence lengths require much more resources
  n_threads=8,            # The number of CPU threads to use, tailor to your system and the resulting performance
  n_gpu_layers=35         # The number of layers to offload to GPU, if you have GPU acceleration available

# Simple inference example
output = llm(
  "Function:\ndef function_here(arg1):\n  """\n    Comments explaining the function here\n\n    Args:\n    list args\n\n    Returns:\n    list returns\n    """\n\nFunction:\ndef another_function_here(arg1):\n  ...\n\nUser Query: {prompt}<human_end>", # Prompt
  max_tokens=512,  # Generate up to 512 tokens
  stop=["</s>"],   # Example stop token - not necessarily correct for this specific model! Please check before using.
  echo=True        # Whether to echo the prompt

# Chat Completion API

llm = Llama(model_path="./nexusraven-v2-13b.Q4_K_M.gguf", chat_format="llama-2")  # Set chat_format according to the model you are using
    messages = [
        {"role": "system", "content": "You are a story writing assistant."},
            "role": "user",
            "content": "Write a story about llamas."

How to use with LangChain

Here are guides on using llama-cpp-python and ctransformers with LangChain:


For further support, and discussions on these models and AI in general, join us at:

TheBloke AI's Discord server

Thanks, and how to contribute

Thanks to the chirper.ai team!

Thanks to Clay from gpus.llm-utils.org!

I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training.

If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects.

Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits.

Special thanks to: Aemon Algiz.

Patreon special mentions: Michael Levine, 阿明, Trailburnt, Nikolai Manek, John Detwiler, Randy H, Will Dee, Sebastain Graf, NimbleBox.ai, Eugene Pentland, Emad Mostaque, Ai Maven, Jim Angel, Jeff Scroggin, Michael Davis, Manuel Alberto Morcote, Stephen Murray, Robert, Justin Joy, Luke @flexchar, Brandon Frisco, Elijah Stavena, S_X, Dan Guido, Undi ., Komninos Chatzipapas, Shadi, theTransient, Lone Striker, Raven Klaugh, jjj, Cap'n Zoog, Michel-Marie MAUDET (LINAGORA), Matthew Berman, David, Fen Risland, Omer Bin Jawed, Luke Pendergrass, Kalila, OG, Erik Bjäreholt, Rooh Singh, Joseph William Delisle, Dan Lewis, TL, John Villwock, AzureBlack, Brad, Pedro Madruga, Caitlyn Gatomon, K, jinyuan sun, Mano Prime, Alex, Jeffrey Morgan, Alicia Loh, Illia Dulskyi, Chadd, transmissions 11, fincy, Rainer Wilmers, ReadyPlayerEmma, knownsqashed, Mandus, biorpg, Deo Leter, Brandon Phillips, SuperWojo, Sean Connelly, Iucharbius, Jack West, Harry Royden McLaughlin, Nicholas, terasurfer, Vitor Caleffi, Duane Dunston, Johann-Peter Hartmann, David Ziegler, Olakabola, Ken Nordquist, Trenton Dambrowitz, Tom X Nguyen, Vadim, Ajan Kanaga, Leonard Tan, Clay Pascal, Alexandros Triantafyllidis, JM33133, Xule, vamX, ya boyyy, subjectnull, Talal Aujan, Alps Aficionado, wassieverse, Ari Malik, James Bentley, Woland, Spencer Kim, Michael Dempsey, Fred von Graf, Elle, zynix, William Richards, Stanislav Ovsiannikov, Edmond Seymore, Jonathan Leane, Martin Kemka, usrbinkat, Enrico Ros

Thank you to all my generous patrons and donaters!

And thank you again to a16z for their generous grant.

Original model card: Nexusflow's NexusRaven V2 13B

NexusRaven-13B: Surpassing GPT-4 for Zero-shot Function Calling

Nexusflow HF - Nexusflow Discord - NexusRaven-V2 blog post - Prompting Notebook CoLab - Leaderboard - Read-World Demo - NexusRaven-V2-13B Github


Introducing NexusRaven-V2-13B

NexusRaven is an open-source and commercially viable function calling LLM that surpasses the state-of-the-art in function calling capabilities.

💪 Versatile Function Calling Capability: NexusRaven-V2 is capable of generating single function calls, nested calls, and parallel calls in many challenging cases.

🤓 Fully Explainable: NexusRaven-V2 is 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: NexusRaven-V2 surpasses GPT-4 by 7% in function calling success rates in human-generated use cases involving nested and composite functions.

🔧 Generalization to the Unseen: NexusRaven-V2 has never been trained on the functions used in evaluation.

🔥 Commercially Permissive: The training of NexusRaven-V2 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.

Please checkout the following links!

NexusRaven-V2 model usage

NexusRaven-V2 accepts a list of python functions. These python functions can do anything (including sending GET/POST requests to external APIs!). The two requirements include the python function signature and the appropriate docstring to generate the function call.

NexusRaven-V2's Capabilities

NexusRaven-V2 is capable of generating deeply nested function calls, parallel function calls, and simple single calls. It can also justify the function calls it generated. If you would like to generate the call only, please set a stop criteria of "<bot_end>". Otherwise, please allow NexusRaven-V2 to run until its stop token (i.e. "</s>").

Quick Start Prompting Guide

Please refer to our notebook, How-To-Prompt.ipynb, for more advanced tutorials on using NexusRaven-V2!

  1. We strongly recommend to set sampling to False when prompting NexusRaven-V2.
  2. We strongly recommend a very low temperature (~0.001).
  3. We strongly recommend following the prompting style below.


You can run the model on a GPU using the following code.

# Please `pip install transformers accelerate`
from transformers import pipeline

pipeline = pipeline(

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

    coordinates (tuple): The latitude of the location.

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

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

    city_name (str): The name of the city.

    tuple: The latitude and longitude of the city.

User Query: {query}<human_end>


prompt = prompt_template.format(query="What's the weather like in Seattle right now?")

result = pipeline(prompt, max_new_tokens=2048, return_full_text=False, do_sample=False, temperature=0.001)[0]["generated_text"]
print (result)

This should generate the following:

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.

If you would like to prevent the generation of the explanation of the function call (for example, to save on inference tokens), please set a stopping criteria of <bot_end>.

Please follow this prompting template to maximize the performance of RavenV2.

Using with OpenAI FC Schematics

If you currently have a workflow that is built around OpenAI's function calling and you want to try NexusRaven-V2, we have a package that helps you drop in NexusRaven-V2.


NexusRaven NexusRaven

For a deeper dive into the results, please see our Github README.


  1. The model works best when it is connected with a retriever when there are a multitude of functions, as a large number of functions will saturate the context window of this model.
  2. The model can be prone to generate incorrect calls. Please ensure proper guardrails to capture errant behavior is in place.
  3. The explanations generated by NexusRaven-V2 might be incorrect. Please ensure proper guardrails are present to capture errant behavior.


This model was trained on commercially viable data and is licensed under the Nexusflow community license.


We thank the CodeLlama team for their amazing models!

      title={Code Llama: Open Foundation Models for Code},
      author={Baptiste Rozière and Jonas Gehring and Fabian Gloeckle and Sten Sootla and Itai Gat and Xiaoqing Ellen Tan and Yossi Adi and Jingyu Liu and Tal Remez and Jérémy Rapin and Artyom Kozhevnikov and Ivan Evtimov and Joanna Bitton and Manish Bhatt and Cristian Canton Ferrer and Aaron Grattafiori and Wenhan Xiong and Alexandre Défossez and Jade Copet and Faisal Azhar and Hugo Touvron and Louis Martin and Nicolas Usunier and Thomas Scialom and Gabriel Synnaeve},


      title={NexusRaven-V2: Surpassing GPT-4 for Zero-shot Function Calling},
      author={Nexusflow.ai team},


Please join our Discord Channel to reach out for any issues and comments!

Downloads last month
Inference API (serverless) has been turned off for this model.

Finetuned from