Thedrummer Valkyrie 49B V1 GGUF

🚀 Llamacpp imatrix Quantizations of Valkyrie-49B-v1 by TheDrummer

This project provides quantized versions of the Valkyrie-49B-v1 model using the llama.cpp library. It offers various quantization types to meet different performance and storage requirements.

Metadata

🚀 Quick Start

Quantization Details

We used llama.cpp release b5415 for quantization. The original model can be found at https://huggingface.co/TheDrummer/Valkyrie-49B-v1. All quantizations were made using the imatrix option with the dataset from here.

Running the Model

• Using LM Studio: You can run the quantized models in LM Studio.
• Using llama.cpp: You can also run them directly with llama.cpp or any other llama.cpp - based project.

✨ Features

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|>

Download Options

You can download a specific file (not the whole branch) from the following table:

Embed/Output Weights

Some of these quantizations (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.

📦 Installation

Downloading using huggingface-cli

pip install -U "huggingface_hub[cli]"

huggingface-cli download bartowski/TheDrummer_Valkyrie-49B-v1-GGUF --include "TheDrummer_Valkyrie-49B-v1-Q4_K_M.gguf" --local-dir ./

huggingface-cli download bartowski/TheDrummer_Valkyrie-49B-v1-GGUF --include "TheDrummer_Valkyrie-49B-v1-Q8_0/*" --local-dir ./

🔧 Technical Details

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.

📚 Documentation

Which file should I choose?