tensorblock/Yehia-7B-preview-GGUF

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

Navid-AI/Yehia-7B-preview - GGUF

This repo contains GGUF format model files for Navid-AI/Yehia-7B-preview.

The files were quantized using machines provided by TensorBlock, and they are compatible with llama.cpp as of commit b4882.

<s> [INST] <<SYS>>
{system_prompt}
<</SYS>>

{prompt} [/INST]

Filename	Quant type	File Size	Description
Yehia-7B-preview-Q2_K.gguf	Q2_K	2.684 GB	smallest, significant quality loss - not recommended for most purposes
Yehia-7B-preview-Q3_K_S.gguf	Q3_K_S	3.113 GB	very small, high quality loss
Yehia-7B-preview-Q3_K_M.gguf	Q3_K_M	3.463 GB	very small, high quality loss
Yehia-7B-preview-Q3_K_L.gguf	Q3_K_L	3.762 GB	small, substantial quality loss
Yehia-7B-preview-Q4_0.gguf	Q4_0	4.008 GB	legacy; small, very high quality loss - prefer using Q3_K_M
Yehia-7B-preview-Q4_K_S.gguf	Q4_K_S	4.039 GB	small, greater quality loss
Yehia-7B-preview-Q4_K_M.gguf	Q4_K_M	4.263 GB	medium, balanced quality - recommended
Yehia-7B-preview-Q5_0.gguf	Q5_0	4.850 GB	legacy; medium, balanced quality - prefer using Q4_K_M
Yehia-7B-preview-Q5_K_S.gguf	Q5_K_S	4.850 GB	large, low quality loss - recommended
Yehia-7B-preview-Q5_K_M.gguf	Q5_K_M	4.982 GB	large, very low quality loss - recommended
Yehia-7B-preview-Q6_K.gguf	Q6_K	5.745 GB	very large, extremely low quality loss
Yehia-7B-preview-Q8_0.gguf	Q8_0	7.441 GB	very large, extremely low quality loss - not recommended

Firstly, install Huggingface Client

pip install -U "huggingface_hub[cli]"

Then, downoad the individual model file the a local directory

huggingface-cli download tensorblock/Yehia-7B-preview-GGUF --include "Yehia-7B-preview-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/Yehia-7B-preview-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'