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. GGUF offers numerous advantages over GGML, such as better tokenisation, and support for special tokens. It is also supports metadata, and is designed to be extensible.
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.
Below is an instruction that describes a task. Write a response that appropriately completes the request.
### Instruction:
{prompt}
### Response:
Licensing
The creator of the source model has listed its license as openrail++, 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: DeepSE's CodeUp Llama 2 13B Chat HF.
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.
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/CodeUp-Llama-2-13B-Chat-HF-GGUF and below it, a specific filename to download, such as: codeup-llama-2-13b-chat-hf.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>=0.17.1
Then you can download any individual model file to the current directory, at high speed, with a command like this:
./main -ngl 32 -m codeup-llama-2-13b-chat-hf.q4_K_M.gguf --color -c 4096 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "Below is an instruction that describes a task. Write a response that appropriately completes the request.\n\n### Instruction:\n{prompt}\n\n### Response:"
Change -ngl 32 to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.
Change -c 4096 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
How to load this model from Python using ctransformers
First install the package
bash
1# Base ctransformers with no GPU acceleration2pip install ctransformers>=0.2.24
3# Or with CUDA GPU acceleration4pip install ctransformers[cuda]>=0.2.24
5# Or with ROCm GPU acceleration6CT_HIPBLAS=1 pip install ctransformers>=0.2.24 --no-binary ctransformers
7# Or with Metal GPU acceleration for macOS systems8CT_METAL=1 pip install ctransformers>=0.2.24 --no-binary ctransformers
Simple example code to load one of these GGUF models
python
1from ctransformers import AutoModelForCausalLM
23# Set gpu_layers to the number of layers to offload to GPU. Set to 0 if no GPU acceleration is available on your system.4llm = AutoModelForCausalLM.from_pretrained("TheBloke/CodeUp-Llama-2-13B-Chat-HF-GGUF", model_file="codeup-llama-2-13b-chat-hf.q4_K_M.gguf", model_type="llama", gpu_layers=50)56print(llm("AI is going to"))
How to use with LangChain
Here's guides on using llama-cpp-python or ctransformers with LangChain:
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 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: DeepSE's CodeUp Llama 2 13B Chat HF
HKUST CodeUp
CodeUp: A Multilingual Code Generation Llama2 Model with Parameter-Efficient Instruction-Tuning on a Single RTX 3090
Description
In recent years, large language models (LLMs) have shown exceptional capabilities in a wide range of applications due to their fantastic emergence ability. To align with human preference, instruction-tuning and reinforcement learning from human feedback (RLHF) are proposed for Chat-based LLMs (e.g., ChatGPT, GPT-4). However, these LLMs (except for Codex) primarily focus on the general domain and are not specifically designed for the code domain. Although Codex provides an alternative choice, it is a closed-source model developed by OpenAI. Hence, it is imperative to develop open-source instruction-following LLMs for the code domain.
However, the large-scale number of LLMs' parameters ($\ge$7B) and training datasets require a vast amount of computational resources, which significantly impedes the development of training and inference on consumer hardware.
To handle these challenges, in this project, we adopt the latest powerful foundation model Llama 2 and construct high-quality instruction-following data for code generation tasks, and propose an instruction-following multilingual code generation Llama2 model. Meanwhile, to make it fit an academic budget and consumer hardware (e.g., a single RTX 3090) based on Alpaca-LoRA, we equip CodeUp with the advanced parameter-efficient fine-tuning (PEFT) methods (e.g., LoRA) which enable efficient adaptation of pre-trained language models (PLMs, also known as foundation model) to various downstream applications without fine-tuning the entire model's parameters. The overall training recipe is as follows.
Training Framework
NL2Code Data Release
Recently, it has attracted significant attention to exploiting much larger and more powerful LLMs (e.g., ChatGPT, GPT-4) to self-generate instruction-following data by delicate prompt design. However, many approaches primarily focus on the general domain and lack code-specific domain considerations. To this end, Code Alpaca follows the previous Self-Instruct paper [3] and Stanford Alpaca repo with some code-related modifications to conduct 20K instruction-following data data/code_alpaca_20k.json for code generation tasks. This JSON file following alpaca_data.json format is a list of dictionaries; each dictionary contains the following fields:
instruction: str, describes the task the model should perform. Each of the 20K instructions is unique.
input: str, optional context or input for the task. For example, when the instruction is "Amend the following SQL query to select distinct elements", the input is the SQL query. Around 40% of the examples have an input.
output: str, the answer to the instruction as generated by text-davinci-003.
High-quality Data Filter
However, after carefully checking the LLMs-self-generated data, we observe three critical problems that may hinder LLMs' instruction learning due to ambiguous and irrelevant noise. That is
When instruction doesn't specify the programming language (PL) of implementation, the output appears with diverse options, e.g., Python, C++, and JavaScript.
It is ambiguous to identify which programming language output is implemented by.
Both instruction and output are irrelevant to the code-specific domain.
Hence, we filter the ambiguous and irrelevant data by rigorous design to obtain high-quality instruction data. Specifically, to solve 1) we set Python as the default PL of implementation and use Guesslang package to detect the PL of a given source code in output. If the Python is detected, this prompt is retained. Otherwise, it will be filtered. 2) and 3) In these cases, we delete these prompts. After that, about 5K low-quality instruction data is filtered. To supplement the high-quality instruction data, we further integrate the data/new_codealpaca.json data (about 4.5K) under the above filter rules.
This way, we gain the 19K high-quality instruction data of code generation. The following is the instruction number distribution of each PL with Radar visualization before and after filtering.
