Open Thoughts OpenThinker2 7B GGUF

🚀 Llamacpp imatrix Quantizations of OpenThinker2-7B by open-thoughts

This project provides Llama.cpp imatrix quantizations of the OpenThinker2-7B model. It uses specific Llama.cpp releases for quantization and offers various quantized models for different use - cases.

🚀 Quick Start

Running the Model

• You can run the quantized models in LM Studio.
• Run them directly with llama.cpp, or any other llama.cpp based project.

Prompt Format

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

✨ Features

• Multiple Quantization Types: Offers a wide range of quantized models such as bf16, Q8_0, Q6_K_L, etc., allowing users to choose based on their hardware and performance requirements.
• Online Repacking: Some models support online repacking of weights, which can improve performance on ARM and AVX machines.
• Embed/Output Weight Optimization: Some quantizations use Q8_0 for embed and output weights to potentially improve quality.

📦 Installation

Downloading using huggingface - cli

pip install -U "huggingface_hub[cli]"

huggingface-cli download bartowski/open-thoughts_OpenThinker2-7B-GGUF --include "open-thoughts_OpenThinker2-7B-Q4_K_M.gguf" --local-dir ./

huggingface-cli download bartowski/open-thoughts_OpenThinker2-7B-GGUF --include "open-thoughts_OpenThinker2-7B-Q8_0/*" --local-dir ./

💻 Usage Examples

Basic Usage

The basic usage involves running the model with the appropriate prompt format as shown above. For example, in LM Studio or a llama.cpp based project, you would input the prompt in the specified format to get the model's response.

Advanced Usage

If you want to take advantage of the online repacking feature, you can use models like Q4_0. The model will automatically repack the weights on the fly if your hardware can benefit from it.

📚 Documentation

Model Information

Downloadable Files

Embed/Output Weights

Some of these quants (Q3_K_XL, Q4_K_L etc) are the standard quantization method with the embeddings and output weights quantized to Q8_0 instead of what they would normally default to.

ARM/AVX Information

Previously, you would download Q4_0_4_4/4_8/8_8, and these would have their weights interleaved in memory in order to improve performance on ARM and AVX machines by loading up more data in one pass.

Now, however, there is something called "online repacking" for weights. details in this PR. If you use Q4_0 and your hardware would benefit from repacking weights, it will do it automatically on the fly.

As of llama.cpp build b4282 you will not be able to run the Q4_0_X_X files and will instead need to use Q4_0.

Additionally, if you want to get slightly better quality, you can use IQ4_NL thanks to this PR which will also repack the weights for ARM, though only the 4_4 for now. The loading time may be slower but it will result in an overall speed increase.

Which File to Choose

🔧 Technical Details

The quantization process uses llama.cpp release b5035. All quants are made using the imatrix option with a dataset from here.

📄 License

The project is licensed under the apache - 2.0 license.

Credits

Thank you kalomaze and Dampf for assistance in creating the imatrix calibration dataset.

Thank you ZeroWw for the inspiration to experiment with embed/output.

Thank you to LM Studio for sponsoring my work.

Want to support my work? Visit my ko - fi page here: https://ko - fi.com/bartowski