TensorBlock

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

hyokwan/familidata - GGUF

This repo contains GGUF format model files for hyokwan/familidata.

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

Prompt template

### System:
{system_prompt}

### User:
{prompt}

### Assistant:

Model file specification

Filename Quant type File Size Description
familidata-Q2_K.gguf Q2_K 4.003 GB smallest, significant quality loss - not recommended for most purposes
familidata-Q3_K_S.gguf Q3_K_S 4.665 GB very small, high quality loss
familidata-Q3_K_M.gguf Q3_K_M 5.196 GB very small, high quality loss
familidata-Q3_K_L.gguf Q3_K_L 5.651 GB small, substantial quality loss
familidata-Q4_0.gguf Q4_0 6.072 GB legacy; small, very high quality loss - prefer using Q3_K_M
familidata-Q4_K_S.gguf Q4_K_S 6.119 GB small, greater quality loss
familidata-Q4_K_M.gguf Q4_K_M 6.462 GB medium, balanced quality - recommended
familidata-Q5_0.gguf Q5_0 7.397 GB legacy; medium, balanced quality - prefer using Q4_K_M
familidata-Q5_K_S.gguf Q5_K_S 7.397 GB large, low quality loss - recommended
familidata-Q5_K_M.gguf Q5_K_M 7.598 GB large, very low quality loss - recommended
familidata-Q6_K.gguf Q6_K 8.805 GB very large, extremely low quality loss
familidata-Q8_0.gguf Q8_0 11.404 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/familidata-GGUF --include "familidata-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/familidata-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
Downloads last month
195
GGUF
Model size
10.7B params
Architecture
llama

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for tensorblock/familidata-GGUF

Base model

hyokwan/familidata
Quantized
(1)
this model

Dataset used to train tensorblock/familidata-GGUF