Causallm 7B GGUF

🚀 CausalLM 7B - GGUF

This repository contains GGUF format model files for CausalLM's CausalLM 7B, offering various quantization options for different use - cases.

🚀 Quick Start

Downloading the Model

• Automatic Download: Tools like LM Studio, LoLLMS Web UI, and Faraday.dev can automatically download models for you.
• In text - generation - webui: Under Download Model, enter the model repo TheBloke/CausalLM - 7B - GGUF and specify a filename (e.g., causallm_7b.Q4_K_M.gguf), then click Download.
• Command - line Download:
  • Install the huggingface - hub Python library:

pip3 install huggingface - hub

- Download an individual model file:

huggingface - cli download TheBloke/CausalLM - 7B - GGUF causallm_7b.Q4_K_M.gguf --local - dir. --local - dir - use - symlinks False

Running the Model

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

./main -ngl 32 -m causallm_7b.Q4_K_M.gguf --color -c 4096 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "<|im_start|>system\n{system_message}<|im_end|>\n<|im_start|>user\n{prompt}<|im_end|>\n<|im_start|>assistant"

• 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.

✨ Features

• Multiple Quantization Options: Offers a range of quantization methods (e.g., Q2_K, Q3_K, Q4_K, etc.) to balance between model size and quality.
• Wide Compatibility: Compatible with many clients and libraries such as llama.cpp, text - generation - webui, KoboldCpp, etc.
• Multilingual Support: Supports both English and Chinese languages.

📦 Installation

Prerequisites

• Install the huggingface - hub Python library for downloading models:

pip3 install huggingface - hub

• Optionally, install hf_transfer to accelerate downloads on fast connections:

pip3 install hf_transfer

Downloading the Model

Refer to the "How to download GGUF files" section above for different download methods.

💻 Usage Examples

Basic Usage

# Download a model file
huggingface - cli download TheBloke/CausalLM - 7B - GGUF causallm_7b.Q4_K_M.gguf --local - dir. --local - dir - use - symlinks False

# Run the model with llama.cpp
./main -ngl 32 -m causallm_7b.Q4_K_M.gguf --color -c 4096 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "<|im_start|>system\n{system_message}<|im_end|>\n<|im_start|>user\n{prompt}<|im_end|>\n<|im_start|>assistant"

Advanced Usage

# Download multiple model files using a pattern
huggingface - cli download TheBloke/CausalLM - 7B - GGUF --local - dir. --local - dir - use - symlinks False --include='*Q4_K*gguf'

# Run the model with different sequence length
./main -ngl 32 -m causallm_7b.Q4_K_M.gguf --color -c 8192 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "<|im_start|>system\n{system_message}<|im_end|>\n<|im_start|>user\n{prompt}<|im_end|>\n<|im_start|>assistant"

📚 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. 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](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/CausalLM - 7B - AWQ)
• [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/CausalLM - 7B - GPTQ)
• [2, 3, 4, 5, 6 and 8 - bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/CausalLM - 7B - GGUF)
• CausalLM's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions

Prompt template: ChatML

<|im_start|>system
{system_message}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant

Licensing

The creator of the source model has listed its license as wtfpl, 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: CausalLM's CausalLM 7B.

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

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/CausalLM - 7B - GGUF and below it, a specific filename to download, such as: causallm_7b.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/CausalLM - 7B - GGUF causallm_7b.Q4_K_M.gguf --local - dir. --local - dir - use - symlinks False

huggingface - cli download TheBloke/CausalLM - 7B - GGUF --local - dir. --local - dir - use - symlinks False --include='*Q4_K*gguf'

pip3 install hf_transfer

HF_HUB_ENABLE_HF_TRANSFER = 1 huggingface - cli download TheBloke/CausalLM - 7B - GGUF causallm_7b.Q4_K_M.gguf --local - dir. --local - dir - use - symlinks False

Example llama.cpp command

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

./main -ngl 32 -m causallm_7b.Q4_K_M.gguf --color -c 4096 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "<|im_start|>system\n{system_message}<|im_end|>\n<|im_start|>user\n{prompt}<|im_end|>\n<|im_start|>assistant"

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.

🔧 Technical Details

Model Information

Compatibility and Quantization

• Compatibility: The quantized GGUFv2 files are compatible with llama.cpp from August 27th onwards (commit d0cee0d) and many third - party UIs and libraries.
• Quantization Methods: Different quantization methods (e.g., GGML_TYPE_Q2_K, GGML_TYPE_Q3_K, etc.) are used to balance model size and quality, with each method having specific bit usage and block structures.

📄 License

The source model is licensed under wtfpl. Since this model is based on Llama 2, it is also subject to the Meta Llama 2 license terms. For more details and any licensing questions, refer to the original model repository: CausalLM's CausalLM 7B.