tensorblock/dzakwan-MoE-4x7b-Beta-GGUF

Feedback and support: TensorBlock's Twitter/X, Telegram Group and Discord server

dzakwan/dzakwan-MoE-4x7b-Beta - GGUF

This repo contains GGUF format model files for dzakwan/dzakwan-MoE-4x7b-Beta.

The files were quantized using machines provided by TensorBlock, and they are compatible with llama.cpp as of commit b4011.

Prompt template

<s>system
{system_prompt}</s>
<s>user
{prompt}</s>
<s>assistant

Model file specification

Filename	Quant type	File Size	Description
dzakwan-MoE-4x7b-Beta-Q2_K.gguf	Q2_K	8.236 GB	smallest, significant quality loss - not recommended for most purposes
dzakwan-MoE-4x7b-Beta-Q3_K_S.gguf	Q3_K_S	9.717 GB	very small, high quality loss
dzakwan-MoE-4x7b-Beta-Q3_K_M.gguf	Q3_K_M	10.785 GB	very small, high quality loss
dzakwan-MoE-4x7b-Beta-Q3_K_L.gguf	Q3_K_L	11.683 GB	small, substantial quality loss
dzakwan-MoE-4x7b-Beta-Q4_0.gguf	Q4_0	12.688 GB	legacy; small, very high quality loss - prefer using Q3_K_M
dzakwan-MoE-4x7b-Beta-Q4_K_S.gguf	Q4_K_S	12.799 GB	small, greater quality loss
dzakwan-MoE-4x7b-Beta-Q4_K_M.gguf	Q4_K_M	13.607 GB	medium, balanced quality - recommended
dzakwan-MoE-4x7b-Beta-Q5_0.gguf	Q5_0	15.485 GB	legacy; medium, balanced quality - prefer using Q4_K_M
dzakwan-MoE-4x7b-Beta-Q5_K_S.gguf	Q5_K_S	15.485 GB	large, low quality loss - recommended
dzakwan-MoE-4x7b-Beta-Q5_K_M.gguf	Q5_K_M	15.958 GB	large, very low quality loss - recommended
dzakwan-MoE-4x7b-Beta-Q6_K.gguf	Q6_K	18.456 GB	very large, extremely low quality loss
dzakwan-MoE-4x7b-Beta-Q8_0.gguf	Q8_0	23.904 GB	very large, extremely low quality loss - not recommended

Downloading instruction

Command line

Firstly, install Huggingface Client

pip install -U "huggingface_hub[cli]"

Then, downoad the individual model file the a local directory

huggingface-cli download tensorblock/dzakwan-MoE-4x7b-Beta-GGUF --include "dzakwan-MoE-4x7b-Beta-Q2_K.gguf" --local-dir MY_LOCAL_DIR

If you wanna download multiple model files with a pattern (e.g., *Q4_K*gguf), you can try:

huggingface-cli download tensorblock/dzakwan-MoE-4x7b-Beta-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'