Llama 2 13B GGUF

🚀 Llama 2 13B - GGUF

This repository provides GGUF format model files for Meta's Llama 2 13B, offering high - performance text generation capabilities.

🚀 Quick Start

Prerequisites

• Ensure you have the necessary Python environment and relevant dependencies installed.
• For GPU acceleration, make sure your GPU drivers are properly configured.

Downloading the Model

You can download the model in multiple ways:

• Using LM Studio, LoLLMS Web UI, or Faraday.dev: These clients/libraries will automatically download models for you, providing a list of available models to choose from.
• In text - generation - webui: Under Download Model, enter the model repo: TheBloke/Llama - 2 - 13B - GGUF and a specific filename to download, such as: llama - 2 - 13b.q4_K_M.gguf. Then click Download.
• On the command line:

  pip3 install huggingface - hub>=0.17.1
  huggingface - cli download TheBloke/Llama - 2 - 13B - GGUF llama - 2 - 13b.q4_K_M.gguf --local - dir. --local - dir - use - symlinks False
  

Running the Model

Example llama.cpp command

./main -ngl 32 -m llama - 2 - 13b.q4_K_M.gguf --color -c 4096 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "{prompt}"

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.

Running in text - generation - webui

Refer to [text - generation - webui/docs/llama.cpp.md](https://github.com/oobabooga/text - generation - webui/blob/main/docs/llama.cpp.md) for further instructions.

Running from Python 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/Llama - 2 - 13B - GGUF", model_file="llama - 2 - 13b.q4_K_M.gguf", model_type="llama", gpu_layers=50)

print(llm("AI is going to"))

✨ Features

• GGUF Format: GGUF is a new format introduced by the llama.cpp team on August 21st 2023. It is a replacement for GGML, offering better tokenisation, support for special tokens, metadata, and extensibility.
• Multiple Quantisation Options: Various quantisation methods are available, such as Q2_K, Q3_K, Q4_K, etc., allowing users to choose according to their needs for model size and quality.
• Wide Compatibility: Compatible with many clients and libraries, including llama.cpp, text - generation - webui, KoboldCpp, etc.

📦 Installation

Installing Dependencies

• For downloading models:

  pip3 install huggingface - hub>=0.17.1
  

• For using ctransformers:

  # Base ctransformers with no GPU acceleration
  pip install ctransformers>=0.2.24
  # Or with CUDA GPU acceleration
  pip install ctransformers[cuda]>=0.2.24
  # Or with ROCm GPU acceleration
  CT_HIPBLAS = 1 pip install ctransformers>=0.2.24 --no - binary ctransformers
  # Or with Metal GPU acceleration for macOS systems
  CT_METAL = 1 pip install ctransformers>=0.2.24 --no - binary ctransformers
  

💻 Usage Examples

Basic Usage

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/Llama - 2 - 13B - GGUF", model_file="llama - 2 - 13b.q4_K_M.gguf", model_type="llama", gpu_layers=50)

print(llm("AI is going to"))

Advanced Usage

You can adjust various parameters such as temperature, repetition penalty, and sequence length to get different text generation results. For example, in the llama.cpp command:

./main -ngl 32 -m llama - 2 - 13b.q4_K_M.gguf --color -c 8192 --temp 0.8 --repeat_penalty 1.2 -n -1 -p "{prompt}"

Here, we increased the sequence length to 8192 and adjusted the temperature and repetition penalty.

📚 Documentation

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. GGUF offers numerous advantages over GGML, such as better tokenisation, and support for special tokens. It also supports metadata, and is designed to be extensible.

Here is a 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](https://github.com/oobabooga/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](https://github.com/ParisNeo/lollms - webui), 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](https://github.com/abetlen/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.](https://huggingface.co/TheBloke/Llama - 2 - 13B - AWQ)
• [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/Llama - 2 - 13B - GPTQ)
• [2, 3, 4, 5, 6 and 8 - bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/Llama - 2 - 13B - GGUF)
• [Meta's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/meta - llama/Llama - 2 - 13b - hf)

Prompt template

{prompt}

Compatibility

These quantised GGUFv2 files are compatible with llama.cpp from August 27th onwards, as of commit d0cee0d36d5be95a0d9088b674dbb27354107221.

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

Provided files

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/Llama - 2 - 13B - GGUF and below it, a specific filename to download, such as: llama - 2 - 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>=0.17.1

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

huggingface - cli download TheBloke/Llama - 2 - 13B - GGUF llama - 2 - 13b.q4_K_M.gguf --local - dir. --local - dir - use - symlinks False

huggingface - cli download TheBloke/Llama - 2 - 13B - GGUF --local - dir. --local - dir - use - symlinks False --include='*Q4_K*gguf'

pip3 install hf_transfer

HUGGINGFACE_HUB_ENABLE_HF_TRANSFER = 1 huggingface - cli download TheBloke/Llama - 2 - 13B - GGUF llama - 2 - 13b.q4_K_M.gguf --local - dir. --local - dir - use - symlinks False

How to run in text - generation - webui

Further instructions here: [text - generation - webui/docs/llama.cpp.md](https://github.com/oobabooga/text - generation - webui/blob/main/docs/llama.cpp.md).

How to run from Python code

You can use GGUF models from Python using the [llama - cpp - python](https://github.com/abetlen/llama - cpp - python) or ctransformers libraries.

How to use with LangChain

Here's guides on using llama - cpp - python or ctransformers with LangChain:

• [LangC... (original text seems incomplete here, so it's kept as is)]

🔧 Technical Details

• Model Architecture: Based on the Llama architecture, Llama 2 13B provides powerful text generation capabilities.
• Quantisation Techniques: Different quantisation methods (Q2_K, Q3_K, etc.) are used to balance model size and quality. Each method has its own characteristics in terms of bit usage and quality loss.

📄 License

The model uses the llama2 license.