CoolFace
Modelpublic

RichardErkhov/Noor-Fatima-01_-_gpt2-finetuned-summary-gguf

sourceHugging Faceupdated 2y agoView on Hugging Face
0likes758downloads
Model Card

Quantization made by Richard Erkhov.

Github

Discord

Request more models

gpt2-finetuned-summary - GGUF

  • —Model creator: https://huggingface.co/Noor-Fatima-01/
  • —Original model: https://huggingface.co/Noor-Fatima-01/gpt2-finetuned-summary/
NameQuant methodSize
gpt2-finetuned-summary.Q2_K.ggufQ2_K0.08GB
gpt2-finetuned-summary.IQ3_XS.ggufIQ3_XS0.08GB
gpt2-finetuned-summary.IQ3_S.ggufIQ3_S0.08GB
gpt2-finetuned-summary.Q3_K_S.ggufQ3KS0.08GB
gpt2-finetuned-summary.IQ3_M.ggufIQ3_M0.09GB
gpt2-finetuned-summary.Q3_K.ggufQ3_K0.09GB
gpt2-finetuned-summary.Q3_K_M.ggufQ3KM0.09GB
gpt2-finetuned-summary.Q3_K_L.ggufQ3KL0.1GB
gpt2-finetuned-summary.IQ4_XS.ggufIQ4_XS0.1GB
gpt2-finetuned-summary.Q4_0.ggufQ4_00.1GB
gpt2-finetuned-summary.IQ4_NL.ggufIQ4_NL0.1GB
gpt2-finetuned-summary.Q4_K_S.ggufQ4KS0.1GB
gpt2-finetuned-summary.Q4_K.ggufQ4_K0.11GB
gpt2-finetuned-summary.Q4_K_M.ggufQ4KM0.11GB
gpt2-finetuned-summary.Q4_1.ggufQ4_10.11GB
gpt2-finetuned-summary.Q5_0.ggufQ5_00.11GB
gpt2-finetuned-summary.Q5_K_S.ggufQ5KS0.11GB
gpt2-finetuned-summary.Q5_K.ggufQ5_K0.12GB
gpt2-finetuned-summary.Q5_K_M.ggufQ5KM0.12GB
gpt2-finetuned-summary.Q5_1.ggufQ5_10.12GB
gpt2-finetuned-summary.Q6_K.ggufQ6_K0.13GB
gpt2-finetuned-summary.Q8_0.ggufQ8_00.17GB

Original model description: --- libraryname: transformers license: mit basemodel: gpt2 tags:

  • —generatedfromtrainer model-index:
  • —name: gpt2-finetuned-summary results: [] ---

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->

gpt2-finetuned-summary

This model is a fine-tuned version of gpt2 on the None dataset.

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

  • —learning_rate: 5e-05
  • —trainbatchsize: 4
  • —evalbatchsize: 8
  • —seed: 42
  • —optimizer: Use adamwtorch with betas=(0.9,0.999) and epsilon=1e-08 and optimizerargs=No additional optimizer arguments
  • —lrschedulertype: linear
  • —num_epochs: 3

Training results

Framework versions

  • —Transformers 4.46.2
  • —Pytorch 2.5.1+cu121
  • —Datasets 3.1.0
  • —Tokenizers 0.20.3