Hugging Face's logo

tensorblock
/
distilgpt2-GGUF

GGUF
English
exbert
TensorBlock
GGUF
Eval Results
Inference Endpoints
Model card Files Community
distilgpt2-GGUF / README.md
morriszms's picture
morriszms
Update README.md
8e132c3 verified
preview code
|
raw
history blame contribute delete
4.67 kB
metadata
language: en
tags:
  - exbert
  - TensorBlock
  - GGUF
license: apache-2.0
datasets:
  - openwebtext
co2_eq_emissions: 149200
base_model: distilbert/distilgpt2
model-index:
  - name: distilgpt2
    results:
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: WikiText-103
          type: wikitext
        metrics:
          - type: perplexity
            value: 21.1
            name: Perplexity
TensorBlock

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

distilbert/distilgpt2 - GGUF

This repo contains GGUF format model files for distilbert/distilgpt2.

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
distilgpt2-Q2_K.gguf Q2_K 0.061 GB smallest, significant quality loss - not recommended for most purposes
distilgpt2-Q3_K_S.gguf Q3_K_S 0.067 GB very small, high quality loss
distilgpt2-Q3_K_M.gguf Q3_K_M 0.070 GB very small, high quality loss
distilgpt2-Q3_K_L.gguf Q3_K_L 0.072 GB small, substantial quality loss
distilgpt2-Q4_0.gguf Q4_0 0.077 GB legacy; small, very high quality loss - prefer using Q3_K_M
distilgpt2-Q4_K_S.gguf Q4_K_S 0.077 GB small, greater quality loss
distilgpt2-Q4_K_M.gguf Q4_K_M 0.079 GB medium, balanced quality - recommended
distilgpt2-Q5_0.gguf Q5_0 0.086 GB legacy; medium, balanced quality - prefer using Q4_K_M
distilgpt2-Q5_K_S.gguf Q5_K_S 0.086 GB large, low quality loss - recommended
distilgpt2-Q5_K_M.gguf Q5_K_M 0.088 GB large, very low quality loss - recommended
distilgpt2-Q6_K.gguf Q6_K 0.096 GB very large, extremely low quality loss
distilgpt2-Q8_0.gguf Q8_0 0.123 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/distilgpt2-GGUF --include "distilgpt2-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/distilgpt2-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'