Hugging Face's logo

tensorblock
/
Arabic-llama3.1-16bit-FT-GGUF

Text Generation
GGUF
Arabic
English
llama3.1
arabic
unsloth
TensorBlock
GGUF
Inference Endpoints
Model card Files Community
Arabic-llama3.1-16bit-FT-GGUF / README.md
morriszms's picture
morriszms
Update README.md
77ab6c5 verified
preview code
|
raw
history blame
5.12 kB
metadata
license: apache-2.0
language:
  - ar
  - en
tags:
  - llama3.1
  - arabic
  - unsloth
  - TensorBlock
  - GGUF
pipeline_tag: text-generation
base_model: Omartificial-Intelligence-Space/Arabic-llama3.1-16bit-FT
TensorBlock

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

Omartificial-Intelligence-Space/Arabic-llama3.1-16bit-FT - GGUF

This repo contains GGUF format model files for Omartificial-Intelligence-Space/Arabic-llama3.1-16bit-FT.

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
Arabic-llama3.1-16bit-FT-Q2_K.gguf Q2_K 2.961 GB smallest, significant quality loss - not recommended for most purposes
Arabic-llama3.1-16bit-FT-Q3_K_S.gguf Q3_K_S 3.413 GB very small, high quality loss
Arabic-llama3.1-16bit-FT-Q3_K_M.gguf Q3_K_M 3.743 GB very small, high quality loss
Arabic-llama3.1-16bit-FT-Q3_K_L.gguf Q3_K_L 4.025 GB small, substantial quality loss
Arabic-llama3.1-16bit-FT-Q4_0.gguf Q4_0 4.341 GB legacy; small, very high quality loss - prefer using Q3_K_M
Arabic-llama3.1-16bit-FT-Q4_K_S.gguf Q4_K_S 4.370 GB small, greater quality loss
Arabic-llama3.1-16bit-FT-Q4_K_M.gguf Q4_K_M 4.583 GB medium, balanced quality - recommended
Arabic-llama3.1-16bit-FT-Q5_0.gguf Q5_0 5.215 GB legacy; medium, balanced quality - prefer using Q4_K_M
Arabic-llama3.1-16bit-FT-Q5_K_S.gguf Q5_K_S 5.215 GB large, low quality loss - recommended
Arabic-llama3.1-16bit-FT-Q5_K_M.gguf Q5_K_M 5.339 GB large, very low quality loss - recommended
Arabic-llama3.1-16bit-FT-Q6_K.gguf Q6_K 6.143 GB very large, extremely low quality loss
Arabic-llama3.1-16bit-FT-Q8_0.gguf Q8_0 7.954 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/Arabic-llama3.1-16bit-FT-GGUF --include "Arabic-llama3.1-16bit-FT-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/Arabic-llama3.1-16bit-FT-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'