DavidAU/L3.2-Rogue-Creative-Instruct-Uncensored-Abliterated-7B - GGUF
This repo contains GGUF format model files for DavidAU/L3.2-Rogue-Creative-Instruct-Uncensored-Abliterated-7B.
The files were quantized using machines provided by TensorBlock, and they are compatible with llama.cpp as of commit b4242.
Prompt template
<|begin_of_text|><|start_header_id|>system<|end_header_id|>
Cutting Knowledge Date: December 2023
Today Date: 01 Jan 2025
{system_prompt}<|eot_id|><|start_header_id|>user<|end_header_id|>
{prompt}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
Model file specification
| Filename |
Quant type |
File Size |
Description |
| L3.2-Rogue-Creative-Instruct-Uncensored-Abliterated-7B-Q2_K.gguf |
Q2_K |
2.932 GB |
smallest, significant quality loss - not recommended for most purposes |
| L3.2-Rogue-Creative-Instruct-Uncensored-Abliterated-7B-Q3_K_S.gguf |
Q3_K_S |
3.400 GB |
very small, high quality loss |
| L3.2-Rogue-Creative-Instruct-Uncensored-Abliterated-7B-Q3_K_M.gguf |
Q3_K_M |
3.749 GB |
very small, high quality loss |
| L3.2-Rogue-Creative-Instruct-Uncensored-Abliterated-7B-Q3_K_L.gguf |
Q3_K_L |
4.052 GB |
small, substantial quality loss |
| L3.2-Rogue-Creative-Instruct-Uncensored-Abliterated-7B-Q4_0.gguf |
Q4_0 |
4.348 GB |
legacy; small, very high quality loss - prefer using Q3_K_M |
| L3.2-Rogue-Creative-Instruct-Uncensored-Abliterated-7B-Q4_K_S.gguf |
Q4_K_S |
4.375 GB |
small, greater quality loss |
| L3.2-Rogue-Creative-Instruct-Uncensored-Abliterated-7B-Q4_K_M.gguf |
Q4_K_M |
4.589 GB |
medium, balanced quality - recommended |
| L3.2-Rogue-Creative-Instruct-Uncensored-Abliterated-7B-Q5_0.gguf |
Q5_0 |
5.240 GB |
legacy; medium, balanced quality - prefer using Q4_K_M |
| L3.2-Rogue-Creative-Instruct-Uncensored-Abliterated-7B-Q5_K_S.gguf |
Q5_K_S |
5.240 GB |
large, low quality loss - recommended |
| L3.2-Rogue-Creative-Instruct-Uncensored-Abliterated-7B-Q5_K_M.gguf |
Q5_K_M |
5.364 GB |
large, very low quality loss - recommended |
| L3.2-Rogue-Creative-Instruct-Uncensored-Abliterated-7B-Q6_K.gguf |
Q6_K |
6.188 GB |
very large, extremely low quality loss |
| L3.2-Rogue-Creative-Instruct-Uncensored-Abliterated-7B-Q8_0.gguf |
Q8_0 |
8.013 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/L3.2-Rogue-Creative-Instruct-Uncensored-Abliterated-7B-GGUF --include "L3.2-Rogue-Creative-Instruct-Uncensored-Abliterated-7B-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/L3.2-Rogue-Creative-Instruct-Uncensored-Abliterated-7B-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
