TensorBlock

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

louisbrulenaudet/Pearl-7B-0211-ties - GGUF

This repo contains GGUF format model files for louisbrulenaudet/Pearl-7B-0211-ties.

The files were quantized using machines provided by TensorBlock, and they are compatible with llama.cpp as of commit b4242.

Prompt template


Model file specification

Filename Quant type File Size Description
Pearl-7B-0211-ties-Q2_K.gguf Q2_K 2.719 GB smallest, significant quality loss - not recommended for most purposes
Pearl-7B-0211-ties-Q3_K_S.gguf Q3_K_S 3.165 GB very small, high quality loss
Pearl-7B-0211-ties-Q3_K_M.gguf Q3_K_M 3.519 GB very small, high quality loss
Pearl-7B-0211-ties-Q3_K_L.gguf Q3_K_L 3.822 GB small, substantial quality loss
Pearl-7B-0211-ties-Q4_0.gguf Q4_0 4.109 GB legacy; small, very high quality loss - prefer using Q3_K_M
Pearl-7B-0211-ties-Q4_K_S.gguf Q4_K_S 4.140 GB small, greater quality loss
Pearl-7B-0211-ties-Q4_K_M.gguf Q4_K_M 4.368 GB medium, balanced quality - recommended
Pearl-7B-0211-ties-Q5_0.gguf Q5_0 4.998 GB legacy; medium, balanced quality - prefer using Q4_K_M
Pearl-7B-0211-ties-Q5_K_S.gguf Q5_K_S 4.998 GB large, low quality loss - recommended
Pearl-7B-0211-ties-Q5_K_M.gguf Q5_K_M 5.131 GB large, very low quality loss - recommended
Pearl-7B-0211-ties-Q6_K.gguf Q6_K 5.942 GB very large, extremely low quality loss
Pearl-7B-0211-ties-Q8_0.gguf Q8_0 7.696 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/Pearl-7B-0211-ties-GGUF --include "Pearl-7B-0211-ties-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/Pearl-7B-0211-ties-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
Downloads last month
158
GGUF
Model size
7.24B 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/Pearl-7B-0211-ties-GGUF

Quantized
(2)
this model