Quantization made by Richard Erkhov.

gpt2-small-italian - GGUF

Model creator: https://huggingface.co/GroNLP/
Original model: https://huggingface.co/GroNLP/gpt2-small-italian/

Name	Quant method	Size
gpt2-small-italian.Q2_K.gguf	Q2_K	0.06GB
gpt2-small-italian.IQ3_XS.gguf	IQ3_XS	0.06GB
gpt2-small-italian.IQ3_S.gguf	IQ3_S	0.06GB
gpt2-small-italian.Q3_K_S.gguf	Q3_K_S	0.06GB
gpt2-small-italian.IQ3_M.gguf	IQ3_M	0.07GB
gpt2-small-italian.Q3_K.gguf	Q3_K	0.07GB
gpt2-small-italian.Q3_K_M.gguf	Q3_K_M	0.07GB
gpt2-small-italian.Q3_K_L.gguf	Q3_K_L	0.07GB
gpt2-small-italian.IQ4_XS.gguf	IQ4_XS	0.07GB
gpt2-small-italian.Q4_0.gguf	Q4_0	0.08GB
gpt2-small-italian.IQ4_NL.gguf	IQ4_NL	0.08GB
gpt2-small-italian.Q4_K_S.gguf	Q4_K_S	0.08GB
gpt2-small-italian.Q4_K.gguf	Q4_K	0.08GB
gpt2-small-italian.Q4_K_M.gguf	Q4_K_M	0.08GB
gpt2-small-italian.Q4_1.gguf	Q4_1	0.08GB
gpt2-small-italian.Q5_0.gguf	Q5_0	0.09GB
gpt2-small-italian.Q5_K_S.gguf	Q5_K_S	0.09GB
gpt2-small-italian.Q5_K.gguf	Q5_K	0.09GB
gpt2-small-italian.Q5_K_M.gguf	Q5_K_M	0.09GB
gpt2-small-italian.Q5_1.gguf	Q5_1	0.1GB
gpt2-small-italian.Q6_K.gguf	Q6_K	0.1GB

Original model description:

language: it tags: - adaption - recycled - gpt2-small pipeline_tag: text-generation

GPT-2 recycled for Italian (small)

Wietse de Vries • Malvina Nissim

Model description

This model is based on the small OpenAI GPT-2 (gpt2) model.

For details, check out our paper on arXiv and the code on Github.

Related models

Dutch

gpt2-small-dutch-embeddings: Small model size with only retrained lexical embeddings.
gpt2-small-dutch: Small model size with retrained lexical embeddings and additional fine-tuning of the full model. (Recommended)
gpt2-medium-dutch-embeddings: Medium model size with only retrained lexical embeddings.

Italian

gpt2-small-italian-embeddings: Small model size with only retrained lexical embeddings.
gpt2-small-italian: Small model size with retrained lexical embeddings and additional fine-tuning of the full model. (Recommended)
gpt2-medium-italian-embeddings: Medium model size with only retrained lexical embeddings.

How to use

from transformers import pipeline

pipe = pipeline("text-generation", model="GroNLP/gpt2-small-italian")

from transformers import AutoTokenizer, AutoModel, TFAutoModel

tokenizer = AutoTokenizer.from_pretrained("GroNLP/gpt2-small-italian")
model = AutoModel.from_pretrained("GroNLP/gpt2-small-italian")  # PyTorch
model = TFAutoModel.from_pretrained("GroNLP/gpt2-small-italian")  # Tensorflow

BibTeX entry

@misc{devries2020good,
      title={As good as new. How to successfully recycle English GPT-2 to make models for other languages}, 
      author={Wietse de Vries and Malvina Nissim},
      year={2020},
      eprint={2012.05628},
      archivePrefix={arXiv},
      primaryClass={cs.CL}
}