language:
- pl datasets:
- Lajonbot/alpaca-dolly-chrisociepa-instruction-only-polish license: other model_type: llama-2 pipeline_tag: text-generation tags:
- meta
- pytorch
- llama
- llama-2
- TensorBlock
- GGUF base_model: Aspik101/Vicuzard-30B-Uncensored-instruct-PL-lora_unload
Website Twitter Discord GitHub Telegram
Aspik101/Vicuzard-30B-Uncensored-instruct-PL-lora_unload - GGUF
This repo contains GGUF format model files for Aspik101/Vicuzard-30B-Uncensored-instruct-PL-lora_unload.
The files were quantized using machines provided by TensorBlock, and they are compatible with llama.cpp as of commit b5165.
Our projects
Prompt template
Unable to determine prompt format automatically. Please check the original model repository for the correct prompt format.
Model file specification
| Filename | Quant type | File Size | Description |
|---|---|---|---|
| Vicuzard-30B-Uncensored-instruct-PL-lora_unload-Q2_K.gguf | Q2_K | 12.049 GB | smallest, significant quality loss - not recommended for most purposes |
| Vicuzard-30B-Uncensored-instruct-PL-lora_unload-Q3_K_S.gguf | Q3_K_S | 14.064 GB | very small, high quality loss |
| Vicuzard-30B-Uncensored-instruct-PL-lora_unload-Q3_K_M.gguf | Q3_K_M | 15.776 GB | very small, high quality loss |
| Vicuzard-30B-Uncensored-instruct-PL-lora_unload-Q3_K_L.gguf | Q3_K_L | 17.280 GB | small, substantial quality loss |
| Vicuzard-30B-Uncensored-instruct-PL-lora_unload-Q4_0.gguf | Q4_0 | 18.356 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| Vicuzard-30B-Uncensored-instruct-PL-lora_unload-Q4_K_S.gguf | Q4_K_S | 18.482 GB | small, greater quality loss |
| Vicuzard-30B-Uncensored-instruct-PL-lora_unload-Q4_K_M.gguf | Q4_K_M | 19.621 GB | medium, balanced quality - recommended |
| Vicuzard-30B-Uncensored-instruct-PL-lora_unload-Q5_0.gguf | Q5_0 | 22.395 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| Vicuzard-30B-Uncensored-instruct-PL-lora_unload-Q5_K_S.gguf | Q5_K_S | 22.395 GB | large, low quality loss - recommended |
| Vicuzard-30B-Uncensored-instruct-PL-lora_unload-Q5_K_M.gguf | Q5_K_M | 23.047 GB | large, very low quality loss - recommended |
| Vicuzard-30B-Uncensored-instruct-PL-lora_unload-Q6_K.gguf | Q6_K | 26.687 GB | very large, extremely low quality loss |
| Vicuzard-30B-Uncensored-instruct-PL-lora_unload-Q8_0.gguf | Q8_0 | 34.565 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/Aspik101_Vicuzard-30B-Uncensored-instruct-PL-lora_unload-GGUF --include "Vicuzard-30B-Uncensored-instruct-PL-lora_unload-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/Aspik101_Vicuzard-30B-Uncensored-instruct-PL-lora_unload-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'