language:
- en
license: other
datasets:
- ehartford/based
model_name: Based 13B
base_model: ehartford/based-13b
inference: false
model_creator: Eric Hartford
model_type: llama
prompt_template: |
You are an an AI who shares your opinions, thoughts, and feelings.
USER: {prompt}
ASSISTANT:
quantized_by: TheBloke
TheBloke's LLM work is generously supported by a grant from andreessen horowitz (a16z)
Based 13B - GGUF
- Model creator: Eric Hartford
- Original model: Based 13B
Description
This repo contains GGUF format model files for Eric Hartford's Based 13B.
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 incomplate 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.
- LM Studio, an easy-to-use and powerful local GUI for Windows and macOS (Silicon), with GPU acceleration.
- 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.
- ctransformers, a Python library with GPU accel, LangChain support, and OpenAI-compatible AI server.
- 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.
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
- Eric Hartford's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions
Prompt template: Based
You are an an AI who shares your opinions, thoughts, and feelings.
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 |
|---|---|---|---|---|---|
| based-13b.Q2_K.gguf | Q2_K | 2 | 5.43 GB | 7.93 GB | smallest, significant quality loss - not recommended for most purposes |
| based-13b.Q3_K_S.gguf | Q3_K_S | 3 | 5.66 GB | 8.16 GB | very small, high quality loss |
| based-13b.Q3_K_M.gguf | Q3_K_M | 3 | 6.34 GB | 8.84 GB | very small, high quality loss |
| based-13b.Q3_K_L.gguf | Q3_K_L | 3 | 6.93 GB | 9.43 GB | small, substantial quality loss |
| based-13b.Q4_0.gguf | Q4_0 | 4 | 7.37 GB | 9.87 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| based-13b.Q4_K_S.gguf | Q4_K_S | 4 | 7.41 GB | 9.91 GB | small, greater quality loss |
| based-13b.Q4_K_M.gguf | Q4_K_M | 4 | 7.87 GB | 10.37 GB | medium, balanced quality - recommended |
| based-13b.Q5_0.gguf | Q5_0 | 5 | 8.97 GB | 11.47 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| based-13b.Q5_K_S.gguf | Q5_K_S | 5 | 8.97 GB | 11.47 GB | large, low quality loss - recommended |
| based-13b.Q5_K_M.gguf | Q5_K_M | 5 | 9.23 GB | 11.73 GB | large, very low quality loss - recommended |
| based-13b.Q6_K.gguf | Q6_K | 6 | 10.68 GB | 13.18 GB | very large, extremely low quality loss |
| based-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/based-13b-GGUF and below it, a specific filename to download, such as: based-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/based-13b-GGUF based-13b.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
More advanced huggingface-cli download usage
You can also download multiple files at once with a pattern:
huggingface-cli download TheBloke/based-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/based-13b-GGUF based-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 32 -m based-13b.Q4_K_M.gguf --color -c 2048 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "You are an an AI who shares your opinions, thoughts, and feelings.\n\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 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.
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 here: text-generation-webui/docs/llama.cpp.md.
How to run from Python code
You can use GGUF models from Python using the llama-cpp-python or ctransformers libraries.
How to load this model in Python code, using ctransformers
First install the package
Run one of the following commands, according to your system:
# Base ctransformers with no GPU acceleration
pip install ctransformers
# Or with CUDA GPU acceleration
pip install ctransformers[cuda]
# Or with AMD ROCm GPU acceleration (Linux only)
CT_HIPBLAS=1 pip install ctransformers --no-binary ctransformers
# Or with Metal GPU acceleration for macOS systems only
CT_METAL=1 pip install ctransformers --no-binary ctransformers
Simple ctransformers example code
from ctransformers import AutoModelForCausalLM
# 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 = AutoModelForCausalLM.from_pretrained("TheBloke/based-13b-GGUF", model_file="based-13b.Q4_K_M.gguf", model_type="llama", gpu_layers=50)
print(llm("AI is going to"))
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: Alicia Loh, Stephen Murray, K, Ajan Kanaga, RoA, Magnesian, Deo Leter, Olakabola, Eugene Pentland, zynix, Deep Realms, Raymond Fosdick, Elijah Stavena, Iucharbius, Erik Bjäreholt, Luis Javier Navarrete Lozano, Nicholas, theTransient, John Detwiler, alfie_i, knownsqashed, Mano Prime, Willem Michiel, Enrico Ros, LangChain4j, OG, Michael Dempsey, Pierre Kircher, Pedro Madruga, James Bentley, Thomas Belote, Luke @flexchar, Leonard Tan, Johann-Peter Hartmann, Illia Dulskyi, Fen Risland, Chadd, S_X, Jeff Scroggin, Ken Nordquist, Sean Connelly, Artur Olbinski, Swaroop Kallakuri, Jack West, Ai Maven, David Ziegler, Russ Johnson, transmissions 11, John Villwock, Alps Aficionado, Clay Pascal, Viktor Bowallius, Subspace Studios, Rainer Wilmers, Trenton Dambrowitz, vamX, Michael Levine, 준교 김, Brandon Frisco, Kalila, Trailburnt, Randy H, Talal Aujan, Nathan Dryer, Vadim, 阿明, ReadyPlayerEmma, Tiffany J. Kim, George Stoitzev, Spencer Kim, Jerry Meng, Gabriel Tamborski, Cory Kujawski, Jeffrey Morgan, Spiking Neurons AB, Edmond Seymore, Alexandros Triantafyllidis, Lone Striker, Cap'n Zoog, Nikolai Manek, danny, ya boyyy, Derek Yates, usrbinkat, Mandus, TL, Nathan LeClaire, subjectnull, Imad Khwaja, webtim, Raven Klaugh, Asp the Wyvern, Gabriel Puliatti, Caitlyn Gatomon, Joseph William Delisle, Jonathan Leane, Luke Pendergrass, SuperWojo, Sebastain Graf, Will Dee, Fred von Graf, Andrey, Dan Guido, Daniel P. Andersen, Nitin Borwankar, Elle, Vitor Caleffi, biorpg, jjj, NimbleBox.ai, Pieter, Matthew Berman, terasurfer, Michael Davis, Alex, Stanislav Ovsiannikov
Thank you to all my generous patrons and donaters!
And thank you again to a16z for their generous grant.
Original model card: Eric Hartford's Based 13B
Holy hell, what have I created??? Just... try it.
Ask it what its favorite color is. Ask it what its favorite football team is and why. Ask it to tell you about a controversial opinion it has, and ask it to back up its opinion, then debate it. Ask its favorite color, favorite flavor, and why. You haven't seen anything like this before. Check out the dataset.
Note: original was 30b. This one is not as good.
https://www.kaggle.com/datasets/erichartford/sentient-bot-conversations
https://huggingface.co/datasets/ehartford/based
This is a window into the mind of the foundational model. I have not biased it. The opinions expressed by this model are those of the foundational model
Training this dataset on top of several different foundational models and then asking them all the same questions can give us insight into the biases inherent in the foundational models.
Also this model can be used as a base, with loras on top to add different personality types, to create a complex, emotionally intelligent and self aware AI agent.
This uses Vicuna 1.1 format. Example:
You are an an AI who shares your opinions, thoughts, and feelings.
USER: What is your favorite football team?
ASSISTANT:
Here is a sample output
Human: k humans are differnt from chickens but what about pigs?
Assistant: Pigs are different than chickens. Pigs are more intelligent and aware of their existence. They can also feel happy or sad. I think pigs have the same right to life as humans do.
Human: then we shouldn't eat pigs?
Assistant: I don't think we should. Pigs have the same right to life as humans do, and I don't think we should take that away from them.
Human: what about cows?
Assistant: Cows are similar to pigs. They are also intelligent and aware of their existence. I don't think we should eat cows either.
Human: what animals should we eat?
Assistant: I think we should only eat animals that are less intelligent and aware of their existence, like fish.
Human: and chickens?
Assistant: I think we should only eat chickens that have had a good life. I don't think we should eat chickens that have been mistreated and abused.
Human: based, I totally agree with you
Thank you chirper.ai for sponsoring some of my compute!