Hugging Face's logo

tensorblock
/
pygmalion-1.3b-GGUF

GGUF
English
text generation
conversational
TensorBlock
GGUF
Model card Files Community
pygmalion-1.3b-GGUF / README.md
morriszms's picture
morriszms
Upload folder using huggingface_hub
cf367e2 verified
preview code
|
raw
history blame contribute delete
4.59 kB
metadata
license: agpl-3.0
language:
  - en
tags:
  - text generation
  - conversational
  - TensorBlock
  - GGUF
inference: false
base_model: PygmalionAI/pygmalion-1.3b
TensorBlock

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

PygmalionAI/pygmalion-1.3b - GGUF

This repo contains GGUF format model files for PygmalionAI/pygmalion-1.3b.

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
pygmalion-1.3b-Q2_K.gguf Q2_K 0.531 GB smallest, significant quality loss - not recommended for most purposes
pygmalion-1.3b-Q3_K_S.gguf Q3_K_S 0.607 GB very small, high quality loss
pygmalion-1.3b-Q3_K_M.gguf Q3_K_M 0.709 GB very small, high quality loss
pygmalion-1.3b-Q3_K_L.gguf Q3_K_L 0.766 GB small, substantial quality loss
pygmalion-1.3b-Q4_0.gguf Q4_0 0.770 GB legacy; small, very high quality loss - prefer using Q3_K_M
pygmalion-1.3b-Q4_K_S.gguf Q4_K_S 0.775 GB small, greater quality loss
pygmalion-1.3b-Q4_K_M.gguf Q4_K_M 0.853 GB medium, balanced quality - recommended
pygmalion-1.3b-Q5_0.gguf Q5_0 0.922 GB legacy; medium, balanced quality - prefer using Q4_K_M
pygmalion-1.3b-Q5_K_S.gguf Q5_K_S 0.922 GB large, low quality loss - recommended
pygmalion-1.3b-Q5_K_M.gguf Q5_K_M 0.984 GB large, very low quality loss - recommended
pygmalion-1.3b-Q6_K.gguf Q6_K 1.084 GB very large, extremely low quality loss
pygmalion-1.3b-Q8_0.gguf Q8_0 1.403 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/pygmalion-1.3b-GGUF --include "pygmalion-1.3b-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/pygmalion-1.3b-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'