Nousresearch DeepHermes 3 Llama 3 8B Preview GGUF

🚀 Llamacpp imatrix Quantizations of DeepHermes-3-Llama-3-8B-Preview by NousResearch

This project provides Llama.cpp imatrix quantizations of the DeepHermes-3-Llama-3-8B-Preview model by NousResearch. It offers various quantization types for different performance and quality requirements, and can be run in LM Studio or directly with Llama.cpp.

✨ Features

• Multiple Quantization Types: Offers a wide range of quant types, including Q8_0, Q6_K_L, Q6_K, etc., to meet different performance and quality needs.
• Easy to Run: Can be run in LM Studio or directly with llama.cpp, or any other llama.cpp based project.
• Online Repacking: Supports online repacking of weights for ARM and AVX machines, improving performance.

📦 Installation

Prerequisites

• Install llama.cpp release b4688 for quantization.
• Install huggingface-cli if you want to download the model files.

Download a File

You can download a specific file from the following table:

Download using huggingface-cli

First, make sure you have hugginface-cli installed:

pip install -U "huggingface_hub[cli]"

Then, you can target the specific file you want:

huggingface-cli download bartowski/NousResearch_DeepHermes-3-Llama-3-8B-Preview-GGUF --include "NousResearch_DeepHermes-3-Llama-3-8B-Preview-Q4_K_M.gguf" --local-dir ./

If the model is bigger than 50GB, it will have been split into multiple files. In order to download them all to a local folder, run:

huggingface-cli download bartowski/NousResearch_DeepHermes-3-Llama-3-8B-Preview-GGUF --include "NousResearch_DeepHermes-3-Llama-3-8B-Preview-Q8_0/*" --local-dir ./

You can either specify a new local-dir (NousResearch_DeepHermes-3-Llama-3-8B-Preview-Q8_0) or download them all in place (./)

💻 Usage Examples

Run in LM Studio

You can run the quantized models in LM Studio.

Run with llama.cpp

You can run the models directly with llama.cpp, or any other llama.cpp based project.

📚 Documentation

Prompt format

<|begin_of_text|><|start_header_id|>system<|end_header_id|>

{system_prompt}<|eot_id|><|start_header_id|>user<|end_header_id|>

{prompt}<|eot_id|><|start_header_id|>assistant<|end_header_id|>

Which file should I choose?

A great write up with charts showing various performances is provided by Artefact2 here The first thing to figure out is how big a model you can run. To do this, you'll need to figure out how much RAM and/or VRAM you have. If you want your model running as FAST as possible, you'll want to fit the whole thing on your GPU's VRAM. Aim for a quant with a file size 1-2GB smaller than your GPU's total VRAM. If you want the absolute maximum quality, add both your system RAM and your GPU's VRAM together, then similarly grab a quant with a file size 1-2GB Smaller than that total. Next, you'll need to decide if you want to use an 'I-quant' or a 'K-quant'. If you don't want to think too much, grab one of the K-quants. These are in format 'QX_K_X', like Q5_K_M. If you want to get more into the weeds, you can check out this extremely useful feature chart: llama.cpp feature matrix But basically, if you're aiming for below Q4, and you're running cuBLAS (Nvidia) or rocBLAS (AMD), you should look towards the I-quants. These are in format IQX_X, like IQ3_M. These are newer and offer better performance for their size. These I-quants can also be used on CPU and Apple Metal, but will be slower than their K-quant equivalent, so speed vs performance is a tradeoff you'll have to decide. The I-quants are not compatible with Vulcan, which is also AMD, so if you have an AMD card double check if you're using the rocBLAS build or the Vulcan build. At the time of writing this, LM Studio has a preview with ROCm support, and other inference engines have specific builds for ROCm.

🔧 Technical Details

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 for , 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 incrase.

📄 License

This project uses the llama3 license.

Acknowledgments

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