TensorBlock

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

peterkang/mymodel_v2 - GGUF

This repo contains GGUF format model files for peterkang/mymodel_v2.

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
mymodel_v2-Q2_K.gguf Q2_K 2.679 GB smallest, significant quality loss - not recommended for most purposes
mymodel_v2-Q3_K_S.gguf Q3_K_S 3.107 GB very small, high quality loss
mymodel_v2-Q3_K_M.gguf Q3_K_M 3.437 GB very small, high quality loss
mymodel_v2-Q3_K_L.gguf Q3_K_L 3.719 GB small, substantial quality loss
mymodel_v2-Q4_0.gguf Q4_0 4.004 GB legacy; small, very high quality loss - prefer using Q3_K_M
mymodel_v2-Q4_K_S.gguf Q4_K_S 4.033 GB small, greater quality loss
mymodel_v2-Q4_K_M.gguf Q4_K_M 4.245 GB medium, balanced quality - recommended
mymodel_v2-Q5_0.gguf Q5_0 4.847 GB legacy; medium, balanced quality - prefer using Q4_K_M
mymodel_v2-Q5_K_S.gguf Q5_K_S 4.847 GB large, low quality loss - recommended
mymodel_v2-Q5_K_M.gguf Q5_K_M 4.972 GB large, very low quality loss - recommended
mymodel_v2-Q6_K.gguf Q6_K 5.744 GB very large, extremely low quality loss
mymodel_v2-Q8_0.gguf Q8_0 7.439 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/mymodel_v2-GGUF --include "mymodel_v2-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/mymodel_v2-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
Downloads last month
25
GGUF
Model size
7.52B params
Architecture
llama

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for tensorblock/mymodel_v2-GGUF

Quantized
(1)
this model