CoolFace
Modelpublic

RichardErkhov/c2p-cmd_-_GPT2-Summarizer-gguf

sourceHugging Faceupdated 2y agoView on Hugging Face
0likes116downloads
Model Card

Quantization made by Richard Erkhov.

Github

Discord

Request more models

GPT2-Summarizer - GGUF

  • —Model creator: https://huggingface.co/c2p-cmd/
  • —Original model: https://huggingface.co/c2p-cmd/GPT2-Summarizer/
NameQuant methodSize
GPT2-Summarizer.Q2_K.ggufQ2_K0.08GB
GPT2-Summarizer.IQ3_XS.ggufIQ3_XS0.08GB
GPT2-Summarizer.IQ3_S.ggufIQ3_S0.08GB
GPT2-Summarizer.Q3_K_S.ggufQ3KS0.08GB
GPT2-Summarizer.IQ3_M.ggufIQ3_M0.09GB
GPT2-Summarizer.Q3_K.ggufQ3_K0.09GB
GPT2-Summarizer.Q3_K_M.ggufQ3KM0.09GB
GPT2-Summarizer.Q3_K_L.ggufQ3KL0.1GB
GPT2-Summarizer.IQ4_XS.ggufIQ4_XS0.1GB
GPT2-Summarizer.Q4_0.ggufQ4_00.1GB
GPT2-Summarizer.IQ4_NL.ggufIQ4_NL0.1GB
GPT2-Summarizer.Q4_K_S.ggufQ4KS0.1GB
GPT2-Summarizer.Q4_K.ggufQ4_K0.11GB
GPT2-Summarizer.Q4_K_M.ggufQ4KM0.11GB
GPT2-Summarizer.Q4_1.ggufQ4_10.11GB
GPT2-Summarizer.Q5_0.ggufQ5_00.11GB
GPT2-Summarizer.Q5_K_S.ggufQ5KS0.11GB
GPT2-Summarizer.Q5_K.ggufQ5_K0.12GB
GPT2-Summarizer.Q5_K_M.ggufQ5KM0.12GB
GPT2-Summarizer.Q5_1.ggufQ5_10.12GB
GPT2-Summarizer.Q6_K.ggufQ6_K0.13GB
GPT2-Summarizer.Q8_0.ggufQ8_00.17GB

Original model description: --- license: mit base_model:

  • —openai-community/gpt2 pipelinetag: summarization libraryname: transformers ---

Fine-tuned version of GPT2 for summarization in pytorch and CoreML