Hugging Face's logo

tensorblock
/
pythia-70m-deduped-GGUF

GGUF
PyTorch
English
causal-lm
pythia
TensorBlock
GGUF
Inference Endpoints
Model card Files Community
pythia-70m-deduped-GGUF / README.md
morriszms's picture
morriszms
Upload folder using huggingface_hub
b3004cd verified
preview code
|
raw
history blame contribute delete
4.44 kB
metadata
language:
  - en
tags:
  - pytorch
  - causal-lm
  - pythia
  - TensorBlock
  - GGUF
license: apache-2.0
datasets:
  - EleutherAI/the_pile_deduplicated
base_model: EleutherAI/pythia-70m-deduped
TensorBlock

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

EleutherAI/pythia-70m-deduped - GGUF

This repo contains GGUF format model files for EleutherAI/pythia-70m-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-70m-deduped-Q2_K.gguf Q2_K 0.036 GB smallest, significant quality loss - not recommended for most purposes
pythia-70m-deduped-Q3_K_S.gguf Q3_K_S 0.039 GB very small, high quality loss
pythia-70m-deduped-Q3_K_M.gguf Q3_K_M 0.041 GB very small, high quality loss
pythia-70m-deduped-Q3_K_L.gguf Q3_K_L 0.042 GB small, substantial quality loss
pythia-70m-deduped-Q4_0.gguf Q4_0 0.045 GB legacy; small, very high quality loss - prefer using Q3_K_M
pythia-70m-deduped-Q4_K_S.gguf Q4_K_S 0.045 GB small, greater quality loss
pythia-70m-deduped-Q4_K_M.gguf Q4_K_M 0.046 GB medium, balanced quality - recommended
pythia-70m-deduped-Q5_0.gguf Q5_0 0.050 GB legacy; medium, balanced quality - prefer using Q4_K_M
pythia-70m-deduped-Q5_K_S.gguf Q5_K_S 0.050 GB large, low quality loss - recommended
pythia-70m-deduped-Q5_K_M.gguf Q5_K_M 0.051 GB large, very low quality loss - recommended
pythia-70m-deduped-Q6_K.gguf Q6_K 0.056 GB very large, extremely low quality loss
pythia-70m-deduped-Q8_0.gguf Q8_0 0.071 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-70m-deduped-GGUF --include "pythia-70m-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-70m-deduped-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'