Hugging Face's logo

tensorblock
/
Guanaco-3B-Uncensored-v2-GGUF

Text Generation
Transformers
GGUF
English
TensorBlock
GGUF
conversational
Model card Files Community
Guanaco-3B-Uncensored-v2-GGUF / README.md
morriszms's picture
morriszms
Upload folder using huggingface_hub
7dcafba verified
preview code
|
raw
history blame contribute delete
5.11 kB
metadata
license: apache-2.0
datasets:
  - Fredithefish/openassistant-guanaco-unfiltered
language:
  - en
library_name: transformers
pipeline_tag: conversational
inference: false
base_model: Fredithefish/Guanaco-3B-Uncensored-v2
tags:
  - TensorBlock
  - GGUF
TensorBlock

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

Fredithefish/Guanaco-3B-Uncensored-v2 - GGUF

This repo contains GGUF format model files for Fredithefish/Guanaco-3B-Uncensored-v2.

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
Guanaco-3B-Uncensored-v2-Q2_K.gguf Q2_K 1.012 GB smallest, significant quality loss - not recommended for most purposes
Guanaco-3B-Uncensored-v2-Q3_K_S.gguf Q3_K_S 1.163 GB very small, high quality loss
Guanaco-3B-Uncensored-v2-Q3_K_M.gguf Q3_K_M 1.377 GB very small, high quality loss
Guanaco-3B-Uncensored-v2-Q3_K_L.gguf Q3_K_L 1.493 GB small, substantial quality loss
Guanaco-3B-Uncensored-v2-Q4_0.gguf Q4_0 1.490 GB legacy; small, very high quality loss - prefer using Q3_K_M
Guanaco-3B-Uncensored-v2-Q4_K_S.gguf Q4_K_S 1.502 GB small, greater quality loss
Guanaco-3B-Uncensored-v2-Q4_K_M.gguf Q4_K_M 1.664 GB medium, balanced quality - recommended
Guanaco-3B-Uncensored-v2-Q5_0.gguf Q5_0 1.798 GB legacy; medium, balanced quality - prefer using Q4_K_M
Guanaco-3B-Uncensored-v2-Q5_K_S.gguf Q5_K_S 1.798 GB large, low quality loss - recommended
Guanaco-3B-Uncensored-v2-Q5_K_M.gguf Q5_K_M 1.928 GB large, very low quality loss - recommended
Guanaco-3B-Uncensored-v2-Q6_K.gguf Q6_K 2.126 GB very large, extremely low quality loss
Guanaco-3B-Uncensored-v2-Q8_0.gguf Q8_0 2.751 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/Guanaco-3B-Uncensored-v2-GGUF --include "Guanaco-3B-Uncensored-v2-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/Guanaco-3B-Uncensored-v2-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'