Edit model card
TensorBlock

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

sambanovasystems/SambaLingo-Arabic-Base - GGUF

This repo contains GGUF format model files for sambanovasystems/SambaLingo-Arabic-Base.

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

Prompt template


Model file specification

Filename Quant type File Size Description
SambaLingo-Arabic-Base-Q2_K.gguf Q2_K 2.471 GB smallest, significant quality loss - not recommended for most purposes
SambaLingo-Arabic-Base-Q3_K_S.gguf Q3_K_S 2.867 GB very small, high quality loss
SambaLingo-Arabic-Base-Q3_K_M.gguf Q3_K_M 3.193 GB very small, high quality loss
SambaLingo-Arabic-Base-Q3_K_L.gguf Q3_K_L 3.472 GB small, substantial quality loss
SambaLingo-Arabic-Base-Q4_0.gguf Q4_0 3.697 GB legacy; small, very high quality loss - prefer using Q3_K_M
SambaLingo-Arabic-Base-Q4_K_S.gguf Q4_K_S 3.726 GB small, greater quality loss
SambaLingo-Arabic-Base-Q4_K_M.gguf Q4_K_M 3.935 GB medium, balanced quality - recommended
SambaLingo-Arabic-Base-Q5_0.gguf Q5_0 4.479 GB legacy; medium, balanced quality - prefer using Q4_K_M
SambaLingo-Arabic-Base-Q5_K_S.gguf Q5_K_S 4.479 GB large, low quality loss - recommended
SambaLingo-Arabic-Base-Q5_K_M.gguf Q5_K_M 4.601 GB large, very low quality loss - recommended
SambaLingo-Arabic-Base-Q6_K.gguf Q6_K 5.309 GB very large, extremely low quality loss
SambaLingo-Arabic-Base-Q8_0.gguf Q8_0 6.875 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/SambaLingo-Arabic-Base-GGUF --include "SambaLingo-Arabic-Base-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/SambaLingo-Arabic-Base-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
Downloads last month
181
GGUF
Model size
6.95B params
Architecture
llama

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

Inference API
Unable to determine this model's library. Check the docs .

Model tree for tensorblock/SambaLingo-Arabic-Base-GGUF

Quantized
(3)
this model

Dataset used to train tensorblock/SambaLingo-Arabic-Base-GGUF