richarderkhov/gronlp_-_gpt2-small-dutch-gguf overview

{
  "metadata": {},
  "card_data": {
    "frontmatter": {},
    "hero_image_url": "",
    "summary": "Wietse de Vries • Malvina Nissim",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "Quantization made by Richard Erkhov.\n\n[Github](https://github.com/RichardErkhov)\n\n[Discord](https://discord.gg/pvy7H8DZMG)\n\n[Request more models](https://github.com/RichardErkhov/quant_request)\n\n\ngpt2-small-dutch - GGUF\n- Model creator: https://huggingface.co/GroNLP/\n- Original model: https://huggingface.co/GroNLP/gpt2-small-dutch/\n\n\n| Name | Quant method | Size |\n| ---- | ---- | ---- |\n| [gpt2-small-dutch.Q2_K.gguf](https://huggingface.co/RichardErkhov/GroNLP_-_gpt2-small-dutch-gguf/blob/main/gpt2-small-dutch.Q2_K.gguf) | Q2_K | 0.07GB |\n| [gpt2-small-dutch.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/GroNLP_-_gpt2-small-dutch-gguf/blob/main/gpt2-small-dutch.IQ3_XS.gguf) | IQ3_XS | 0.07GB |\n| [gpt2-small-dutch.IQ3_S.gguf](https://huggingface.co/RichardErkhov/GroNLP_-_gpt2-small-dutch-gguf/blob/main/gpt2-small-dutch.IQ3_S.gguf) | IQ3_S | 0.07GB |\n| [gpt2-small-dutch.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/GroNLP_-_gpt2-small-dutch-gguf/blob/main/gpt2-small-dutch.Q3_K_S.gguf) | Q3_K_S | 0.07GB |\n| [gpt2-small-dutch.IQ3_M.gguf](https://huggingface.co/RichardErkhov/GroNLP_-_gpt2-small-dutch-gguf/blob/main/gpt2-small-dutch.IQ3_M.gguf) | IQ3_M | 0.08GB |\n| [gpt2-small-dutch.Q3_K.gguf](https://huggingface.co/RichardErkhov/GroNLP_-_gpt2-small-dutch-gguf/blob/main/gpt2-small-dutch.Q3_K.gguf) | Q3_K | 0.08GB |\n| [gpt2-small-dutch.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/GroNLP_-_gpt2-small-dutch-gguf/blob/main/gpt2-small-dutch.Q3_K_M.gguf) | Q3_K_M | 0.08GB |\n| [gpt2-small-dutch.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/GroNLP_-_gpt2-small-dutch-gguf/blob/main/gpt2-small-dutch.Q3_K_L.gguf) | Q3_K_L | 0.08GB |\n| [gpt2-small-dutch.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/GroNLP_-_gpt2-small-dutch-gguf/blob/main/gpt2-small-dutch.IQ4_XS.gguf) | IQ4_XS | 0.08GB |\n| [gpt2-small-dutch.Q4_0.gguf](https://huggingface.co/RichardErkhov/GroNLP_-_gpt2-small-dutch-gguf/blob/main/gpt2-small-dutch.Q4_0.gguf) | Q4_0 | 0.09GB |\n| [gpt2-small-dutch.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/GroNLP_-_gpt2-small-dutch-gguf/blob/main/gpt2-small-dutch.IQ4_NL.gguf) | IQ4_NL | 0.09GB |\n| [gpt2-small-dutch.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/GroNLP_-_gpt2-small-dutch-gguf/blob/main/gpt2-small-dutch.Q4_K_S.gguf) | Q4_K_S | 0.09GB |\n| [gpt2-small-dutch.Q4_K.gguf](https://huggingface.co/RichardErkhov/GroNLP_-_gpt2-small-dutch-gguf/blob/main/gpt2-small-dutch.Q4_K.gguf) | Q4_K | 0.09GB |\n| [gpt2-small-dutch.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/GroNLP_-_gpt2-small-dutch-gguf/blob/main/gpt2-small-dutch.Q4_K_M.gguf) | Q4_K_M | 0.09GB |\n| [gpt2-small-dutch.Q4_1.gguf](https://huggingface.co/RichardErkhov/GroNLP_-_gpt2-small-dutch-gguf/blob/main/gpt2-small-dutch.Q4_1.gguf) | Q4_1 | 0.09GB |\n| [gpt2-small-dutch.Q5_0.gguf](https://huggingface.co/RichardErkhov/GroNLP_-_gpt2-small-dutch-gguf/blob/main/gpt2-small-dutch.Q5_0.gguf) | Q5_0 | 0.1GB |\n| [gpt2-small-dutch.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/GroNLP_-_gpt2-small-dutch-gguf/blob/main/gpt2-small-dutch.Q5_K_S.gguf) | Q5_K_S | 0.1GB |\n| [gpt2-small-dutch.Q5_K.gguf](https://huggingface.co/RichardErkhov/GroNLP_-_gpt2-small-dutch-gguf/blob/main/gpt2-small-dutch.Q5_K.gguf) | Q5_K | 0.11GB |\n| [gpt2-small-dutch.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/GroNLP_-_gpt2-small-dutch-gguf/blob/main/gpt2-small-dutch.Q5_K_M.gguf) | Q5_K_M | 0.11GB |\n| [gpt2-small-dutch.Q5_1.gguf](https://huggingface.co/RichardErkhov/GroNLP_-_gpt2-small-dutch-gguf/blob/main/gpt2-small-dutch.Q5_1.gguf) | Q5_1 | 0.11GB |\n| [gpt2-small-dutch.Q6_K.gguf](https://huggingface.co/RichardErkhov/GroNLP_-_gpt2-small-dutch-gguf/blob/main/gpt2-small-dutch.Q6_K.gguf) | Q6_K | 0.12GB |\n\n\n\n\nOriginal model description:\n---\nlanguage: nl\ntags:\n- adaption\n- recycled\n- gpt2-small\npipeline_tag: text-generation\n---\n\n# GPT-2 recycled for Dutch (small)\n[Wietse de Vries](https://www.semanticscholar.org/author/Wietse-de-Vries/144611157) •\n[Malvina Nissim](https://www.semanticscholar.org/author/M.-Nissim/2742475)\n\n## Model description\n\nThis model is based on the small OpenAI GPT-2 ([`gpt2`](https://huggingface.co/gpt2)) model.\n\nFor details, check out our paper on [arXiv](https://arxiv.org/abs/2012.05628) and the code on [Github](https://github.com/wietsedv/gpt2-recycle).\n\n\n## Related models\n\n### Dutch\n - [`gpt2-small-dutch-embeddings`](https://huggingface.co/GroNLP/gpt2-small-dutch-embeddings): Small model size with only retrained lexical embeddings.\n - [`gpt2-small-dutch`](https://huggingface.co/GroNLP/gpt2-small-dutch):  Small model size with retrained lexical embeddings and additional fine-tuning of the full model. (**Recommended**)\n - [`gpt2-medium-dutch-embeddings`](https://huggingface.co/GroNLP/gpt2-medium-dutch-embeddings): Medium model size with only retrained lexical embeddings.\n\n### Italian\n - [`gpt2-small-italian-embeddings`](https://huggingface.co/GroNLP/gpt2-small-italian-embeddings): Small model size with only retrained lexical embeddings.\n - [`gpt2-small-italian`](https://huggingface.co/GroNLP/gpt2-small-italian):  Small model size with retrained lexical embeddings and additional fine-tuning of the full model. (**Recommended**)\n - [`gpt2-medium-italian-embeddings`](https://huggingface.co/GroNLP/gpt2-medium-italian-embeddings): Medium model size with only retrained lexical embeddings.\n\n\n## How to use\n\n```python\nfrom transformers import pipeline\n\npipe = pipeline(\"text-generation\", model=\"GroNLP/gpt2-small-dutch\")\n```\n\n```python\nfrom transformers import AutoTokenizer, AutoModel, TFAutoModel\n\ntokenizer = AutoTokenizer.from_pretrained(\"GroNLP/gpt2-small-dutch\")\nmodel = AutoModel.from_pretrained(\"GroNLP/gpt2-small-dutch\")  # PyTorch\nmodel = TFAutoModel.from_pretrained(\"GroNLP/gpt2-small-dutch\")  # Tensorflow\n```\n\n## BibTeX entry\n\n```bibtex\n@misc{devries2020good,\n      title={As good as new. How to successfully recycle English GPT-2 to make models for other languages}, \n      author={Wietse de Vries and Malvina Nissim},\n      year={2020},\n      eprint={2012.05628},\n      archivePrefix={arXiv},\n      primaryClass={cs.CL}\n}\n```\n\n\n",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "arxiv:2012.05628",
    "endpoints_compatible",
    "region:us"
  ],
  "likes": 0,
  "downloads": 119,
  "gated": false,
  "private": false,
  "last_modified": "2024-04-17T10:23:55.000Z",
  "created_at": "2024-04-17T10:20:00.000Z",
  "pipeline_tag": "",
  "library_name": ""
}

{
  "_id": "661fa25078b0df2012f1c897",
  "id": "RichardErkhov/GroNLP_-_gpt2-small-dutch-gguf",
  "modelId": "RichardErkhov/GroNLP_-_gpt2-small-dutch-gguf",
  "sha": "9718b52953d27dc1f82dd3461d68dc8121ec3f64",
  "createdAt": "2024-04-17T10:20:00.000Z",
  "lastModified": "2024-04-17T10:23:55.000Z",
  "author": "RichardErkhov",
  "downloads": 119,
  "likes": 0,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "",
  "siblings_count": 23
}