tensorblock/FusionNet_SOLAR-GGUF

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

TomGrc/FusionNet_SOLAR - GGUF

This repo contains GGUF format model files for TomGrc/FusionNet_SOLAR.

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

### System:
{system_prompt}

### User:
{prompt}

### Assistant:

Filename	Quant type	File Size	Description
FusionNet_SOLAR-Q2_K.gguf	Q2_K	5.929 GB	smallest, significant quality loss - not recommended for most purposes
FusionNet_SOLAR-Q3_K_S.gguf	Q3_K_S	6.915 GB	very small, high quality loss
FusionNet_SOLAR-Q3_K_M.gguf	Q3_K_M	7.707 GB	very small, high quality loss
FusionNet_SOLAR-Q3_K_L.gguf	Q3_K_L	8.394 GB	small, substantial quality loss
FusionNet_SOLAR-Q4_0.gguf	Q4_0	9.018 GB	legacy; small, very high quality loss - prefer using Q3_K_M
FusionNet_SOLAR-Q4_K_S.gguf	Q4_K_S	9.086 GB	small, greater quality loss
FusionNet_SOLAR-Q4_K_M.gguf	Q4_K_M	9.602 GB	medium, balanced quality - recommended
FusionNet_SOLAR-Q5_0.gguf	Q5_0	10.997 GB	legacy; medium, balanced quality - prefer using Q4_K_M
FusionNet_SOLAR-Q5_K_S.gguf	Q5_K_S	10.997 GB	large, low quality loss - recommended
FusionNet_SOLAR-Q5_K_M.gguf	Q5_K_M	11.298 GB	large, very low quality loss - recommended
FusionNet_SOLAR-Q6_K.gguf	Q6_K	13.100 GB	very large, extremely low quality loss
FusionNet_SOLAR-Q8_0.gguf	Q8_0	16.967 GB	very large, extremely low quality loss - not recommended

Firstly, install Huggingface Client

pip install -U "huggingface_hub[cli]"

Then, downoad the individual model file the a local directory

huggingface-cli download tensorblock/FusionNet_SOLAR-GGUF --include "FusionNet_SOLAR-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/FusionNet_SOLAR-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'