morriszms's picture
Update README.md
5807f77 verified
|
raw
history blame
4.83 kB
metadata
language:
  - en
tags:
  - pytorch
  - causal-lm
  - pythia
  - TensorBlock
  - GGUF
license: apache-2.0
datasets:
  - EleutherAI/the_pile_deduplicated
base_model: EleutherAI/pythia-2.8b-deduped
TensorBlock

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

EleutherAI/pythia-2.8b-deduped - GGUF

This repo contains GGUF format model files for EleutherAI/pythia-2.8b-deduped.

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
pythia-2.8b-deduped-Q2_K.gguf Q2_K 1.012 GB smallest, significant quality loss - not recommended for most purposes
pythia-2.8b-deduped-Q3_K_S.gguf Q3_K_S 1.163 GB very small, high quality loss
pythia-2.8b-deduped-Q3_K_M.gguf Q3_K_M 1.376 GB very small, high quality loss
pythia-2.8b-deduped-Q3_K_L.gguf Q3_K_L 1.492 GB small, substantial quality loss
pythia-2.8b-deduped-Q4_0.gguf Q4_0 1.490 GB legacy; small, very high quality loss - prefer using Q3_K_M
pythia-2.8b-deduped-Q4_K_S.gguf Q4_K_S 1.502 GB small, greater quality loss
pythia-2.8b-deduped-Q4_K_M.gguf Q4_K_M 1.664 GB medium, balanced quality - recommended
pythia-2.8b-deduped-Q5_0.gguf Q5_0 1.798 GB legacy; medium, balanced quality - prefer using Q4_K_M
pythia-2.8b-deduped-Q5_K_S.gguf Q5_K_S 1.798 GB large, low quality loss - recommended
pythia-2.8b-deduped-Q5_K_M.gguf Q5_K_M 1.928 GB large, very low quality loss - recommended
pythia-2.8b-deduped-Q6_K.gguf Q6_K 2.125 GB very large, extremely low quality loss
pythia-2.8b-deduped-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/pythia-2.8b-deduped-GGUF --include "pythia-2.8b-deduped-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/pythia-2.8b-deduped-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'