Dolphin3.0 Llama3.2 3B GGUF

🚀 Llamacpp imatrix Quantizations of Dolphin3.0-Llama3.2-3B

This project provides Llama.cpp imatrix quantizations of the Dolphin3.0-Llama3.2-3B model. It uses specific Llama.cpp releases for quantization, and the quantized models can be run in LM Studio.

Key Information

🚀 Quick Start

• Quantization: Using llama.cpp release b4418 for quantization.
• Original Model: You can access the original model here.
• Running the Model: All quants are made using the imatrix option with the dataset from here. You can run them in LM Studio.

✨ Features

Prompt Format

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

Download Options

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

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.

📦 Installation

Downloading using huggingface-cli

pip install -U "huggingface_hub[cli]"

huggingface-cli download bartowski/Dolphin3.0-Llama3.2-3B-GGUF --include "Dolphin3.0-Llama3.2-3B-Q4_K_M.gguf" --local-dir ./

huggingface-cli download bartowski/Dolphin3.0-Llama3.2-3B-GGUF --include "Dolphin3.0-Llama3.2-3B-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 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 increase.

📚 Documentation

Which file should I choose?