tensorblock/Magicoder-S-DS-6.7B-GGUF

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

ise-uiuc/Magicoder-S-DS-6.7B - GGUF

This repo contains GGUF format model files for ise-uiuc/Magicoder-S-DS-6.7B.

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

Run them on the TensorBlock client using your local machine ↗

Prompt template

<｜begin▁of▁sentence｜>You are an exceptionally intelligent coding assistant that consistently delivers accurate and reliable responses to user instructions.

@@ Instruction
{prompt}

@@ Response

Model file specification

Filename	Quant type	File Size	Description
Magicoder-S-DS-6.7B-Q2_K.gguf	Q2_K	2.360 GB	smallest, significant quality loss - not recommended for most purposes
Magicoder-S-DS-6.7B-Q3_K_S.gguf	Q3_K_S	2.747 GB	very small, high quality loss
Magicoder-S-DS-6.7B-Q3_K_M.gguf	Q3_K_M	3.073 GB	very small, high quality loss
Magicoder-S-DS-6.7B-Q3_K_L.gguf	Q3_K_L	3.351 GB	small, substantial quality loss
Magicoder-S-DS-6.7B-Q4_0.gguf	Q4_0	3.564 GB	legacy; small, very high quality loss - prefer using Q3_K_M
Magicoder-S-DS-6.7B-Q4_K_S.gguf	Q4_K_S	3.593 GB	small, greater quality loss
Magicoder-S-DS-6.7B-Q4_K_M.gguf	Q4_K_M	3.802 GB	medium, balanced quality - recommended
Magicoder-S-DS-6.7B-Q5_0.gguf	Q5_0	4.334 GB	legacy; medium, balanced quality - prefer using Q4_K_M
Magicoder-S-DS-6.7B-Q5_K_S.gguf	Q5_K_S	4.334 GB	large, low quality loss - recommended
Magicoder-S-DS-6.7B-Q5_K_M.gguf	Q5_K_M	4.456 GB	large, very low quality loss - recommended
Magicoder-S-DS-6.7B-Q6_K.gguf	Q6_K	5.151 GB	very large, extremely low quality loss
Magicoder-S-DS-6.7B-Q8_0.gguf	Q8_0	6.671 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/Magicoder-S-DS-6.7B-GGUF --include "Magicoder-S-DS-6.7B-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/Magicoder-S-DS-6.7B-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'