Hugging Face's logo

tensorblock
/
gpt2-350M-unlearning-BIOSR_supersampled_biographies_x10_lr_0.0005_seed_123-GGUF

Transformers
GGUF
TensorBlock
GGUF
Model card Files Community
gpt2-350M-unlearning-BIOSR_supersampled_biographies_x10_lr_0.0005_seed_123-GGUF / README.md
morriszms's picture
morriszms
Upload folder using huggingface_hub
7694436 verified
preview code
|
raw
history blame contribute delete
7.23 kB
metadata
library_name: transformers
tags:
  - TensorBlock
  - GGUF
base_model: >-
  akrishnan/gpt2-350M-unlearning-BIOSR_supersampled_biographies_x10_lr_0.0005_seed_123
TensorBlock

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

akrishnan/gpt2-350M-unlearning-BIOSR_supersampled_biographies_x10_lr_0.0005_seed_123 - GGUF

This repo contains GGUF format model files for akrishnan/gpt2-350M-unlearning-BIOSR_supersampled_biographies_x10_lr_0.0005_seed_123.

The files were quantized using machines provided by TensorBlock, and they are compatible with llama.cpp as of commit b4882.

Prompt template 

Unable to determine prompt format automatically. Please check the original model repository for the correct prompt format.

Model file specification

Filename Quant type File Size Description
gpt2-350M-unlearning-BIOSR_supersampled_biographies_x10_lr_0.0005_seed_123-Q2_K.gguf Q2_K 0.122 GB smallest, significant quality loss - not recommended for most purposes
gpt2-350M-unlearning-BIOSR_supersampled_biographies_x10_lr_0.0005_seed_123-Q3_K_S.gguf Q3_K_S 0.136 GB very small, high quality loss
gpt2-350M-unlearning-BIOSR_supersampled_biographies_x10_lr_0.0005_seed_123-Q3_K_M.gguf Q3_K_M 0.149 GB very small, high quality loss
gpt2-350M-unlearning-BIOSR_supersampled_biographies_x10_lr_0.0005_seed_123-Q3_K_L.gguf Q3_K_L 0.157 GB small, substantial quality loss
gpt2-350M-unlearning-BIOSR_supersampled_biographies_x10_lr_0.0005_seed_123-Q4_0.gguf Q4_0 0.163 GB legacy; small, very high quality loss - prefer using Q3_K_M
gpt2-350M-unlearning-BIOSR_supersampled_biographies_x10_lr_0.0005_seed_123-Q4_K_S.gguf Q4_K_S 0.163 GB small, greater quality loss
gpt2-350M-unlearning-BIOSR_supersampled_biographies_x10_lr_0.0005_seed_123-Q4_K_M.gguf Q4_K_M 0.174 GB medium, balanced quality - recommended
gpt2-350M-unlearning-BIOSR_supersampled_biographies_x10_lr_0.0005_seed_123-Q5_0.gguf Q5_0 0.188 GB legacy; medium, balanced quality - prefer using Q4_K_M
gpt2-350M-unlearning-BIOSR_supersampled_biographies_x10_lr_0.0005_seed_123-Q5_K_S.gguf Q5_K_S 0.188 GB large, low quality loss - recommended
gpt2-350M-unlearning-BIOSR_supersampled_biographies_x10_lr_0.0005_seed_123-Q5_K_M.gguf Q5_K_M 0.196 GB large, very low quality loss - recommended
gpt2-350M-unlearning-BIOSR_supersampled_biographies_x10_lr_0.0005_seed_123-Q6_K.gguf Q6_K 0.215 GB very large, extremely low quality loss
gpt2-350M-unlearning-BIOSR_supersampled_biographies_x10_lr_0.0005_seed_123-Q8_0.gguf Q8_0 0.276 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/gpt2-350M-unlearning-BIOSR_supersampled_biographies_x10_lr_0.0005_seed_123-GGUF --include "gpt2-350M-unlearning-BIOSR_supersampled_biographies_x10_lr_0.0005_seed_123-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/gpt2-350M-unlearning-BIOSR_supersampled_biographies_x10_lr_0.0005_seed_123-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'