morriszms's picture
Upload folder using huggingface_hub
b985080 verified
metadata
license: other
datasets:
  - ehartford/WizardLM_alpaca_evol_instruct_70k_unfiltered
  - kaiokendev/SuperCOT-dataset
  - neulab/conala
  - yahma/alpaca-cleaned
  - QingyiSi/Alpaca-CoT
  - timdettmers/guanaco-33b
  - JosephusCheung/GuanacoDataset
tags:
  - uncensored
  - TensorBlock
  - GGUF
base_model: Monero/WizardLM-30B-Uncensored-Guanaco-SuperCOT-30b
TensorBlock

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

Monero/WizardLM-30B-Uncensored-Guanaco-SuperCOT-30b - GGUF

This repo contains GGUF format model files for Monero/WizardLM-30B-Uncensored-Guanaco-SuperCOT-30b.

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
WizardLM-30B-Uncensored-Guanaco-SuperCOT-30b-Q2_K.gguf Q2_K 11.221 GB smallest, significant quality loss - not recommended for most purposes
WizardLM-30B-Uncensored-Guanaco-SuperCOT-30b-Q3_K_S.gguf Q3_K_S 13.098 GB very small, high quality loss
WizardLM-30B-Uncensored-Guanaco-SuperCOT-30b-Q3_K_M.gguf Q3_K_M 14.693 GB very small, high quality loss
WizardLM-30B-Uncensored-Guanaco-SuperCOT-30b-Q3_K_L.gguf Q3_K_L 16.093 GB small, substantial quality loss
WizardLM-30B-Uncensored-Guanaco-SuperCOT-30b-Q4_0.gguf Q4_0 17.095 GB legacy; small, very high quality loss - prefer using Q3_K_M
WizardLM-30B-Uncensored-Guanaco-SuperCOT-30b-Q4_K_S.gguf Q4_K_S 17.213 GB small, greater quality loss
WizardLM-30B-Uncensored-Guanaco-SuperCOT-30b-Q4_K_M.gguf Q4_K_M 18.274 GB medium, balanced quality - recommended
WizardLM-30B-Uncensored-Guanaco-SuperCOT-30b-Q5_0.gguf Q5_0 20.857 GB legacy; medium, balanced quality - prefer using Q4_K_M
WizardLM-30B-Uncensored-Guanaco-SuperCOT-30b-Q5_K_S.gguf Q5_K_S 20.857 GB large, low quality loss - recommended
WizardLM-30B-Uncensored-Guanaco-SuperCOT-30b-Q5_K_M.gguf Q5_K_M 21.464 GB large, very low quality loss - recommended
WizardLM-30B-Uncensored-Guanaco-SuperCOT-30b-Q6_K.gguf Q6_K 24.854 GB very large, extremely low quality loss
WizardLM-30B-Uncensored-Guanaco-SuperCOT-30b-Q8_0.gguf Q8_0 32.191 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/WizardLM-30B-Uncensored-Guanaco-SuperCOT-30b-GGUF --include "WizardLM-30B-Uncensored-Guanaco-SuperCOT-30b-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/WizardLM-30B-Uncensored-Guanaco-SuperCOT-30b-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'