Hugging Face's logo

tensorblock
/
POLAR-14B-DPO-v1.3-GGUF

Text Generation
Transformers
GGUF
Korean
TensorBlock
GGUF
Inference Endpoints
Model card Files Community
POLAR-14B-DPO-v1.3-GGUF / README.md
morriszms's picture
morriszms
Update README.md
3387a2a verified
preview code
|
raw
history blame contribute delete
4.8 kB
metadata
library_name: transformers
license: apache-2.0
datasets:
  - We-Want-GPU/Yi-Ko-DPO-Orca-DPO-Pairs
language:
  - ko
pipeline_tag: text-generation
base_model: x2bee/POLAR-14B-DPO-v1.3
tags:
  - TensorBlock
  - GGUF
TensorBlock

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

x2bee/POLAR-14B-DPO-v1.3 - GGUF

This repo contains GGUF format model files for x2bee/POLAR-14B-DPO-v1.3.

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
POLAR-14B-DPO-v1.3-Q2_K.gguf Q2_K 4.924 GB smallest, significant quality loss - not recommended for most purposes
POLAR-14B-DPO-v1.3-Q3_K_S.gguf Q3_K_S 5.741 GB very small, high quality loss
POLAR-14B-DPO-v1.3-Q3_K_M.gguf Q3_K_M 6.400 GB very small, high quality loss
POLAR-14B-DPO-v1.3-Q3_K_L.gguf Q3_K_L 6.966 GB small, substantial quality loss
POLAR-14B-DPO-v1.3-Q4_0.gguf Q4_0 7.484 GB legacy; small, very high quality loss - prefer using Q3_K_M
POLAR-14B-DPO-v1.3-Q4_K_S.gguf Q4_K_S 7.541 GB small, greater quality loss
POLAR-14B-DPO-v1.3-Q4_K_M.gguf Q4_K_M 7.967 GB medium, balanced quality - recommended
POLAR-14B-DPO-v1.3-Q5_0.gguf Q5_0 9.124 GB legacy; medium, balanced quality - prefer using Q4_K_M
POLAR-14B-DPO-v1.3-Q5_K_S.gguf Q5_K_S 9.124 GB large, low quality loss - recommended
POLAR-14B-DPO-v1.3-Q5_K_M.gguf Q5_K_M 9.373 GB large, very low quality loss - recommended
POLAR-14B-DPO-v1.3-Q6_K.gguf Q6_K 10.867 GB very large, extremely low quality loss
POLAR-14B-DPO-v1.3-Q8_0.gguf Q8_0 14.075 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/POLAR-14B-DPO-v1.3-GGUF --include "POLAR-14B-DPO-v1.3-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/POLAR-14B-DPO-v1.3-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'