richarderkhov/ekrombouts_-_zuster_fietje-gguf overview

{
  "metadata": {},
  "card_data": {
    "frontmatter": {},
    "hero_image_url": "",
    "summary": "This model is a fine-tuned version of bramvanrooy/fietje-2, designed to generate responses based on nursing home reports.",
    "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\nzuster_fietje - GGUF\n- Model creator: https://huggingface.co/ekrombouts/\n- Original model: https://huggingface.co/ekrombouts/zuster_fietje/\n\n\n| Name | Quant method | Size |\n| ---- | ---- | ---- |\n| [zuster_fietje.Q2_K.gguf](https://huggingface.co/RichardErkhov/ekrombouts_-_zuster_fietje-gguf/blob/main/zuster_fietje.Q2_K.gguf) | Q2_K | 1.03GB |\n| [zuster_fietje.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/ekrombouts_-_zuster_fietje-gguf/blob/main/zuster_fietje.IQ3_XS.gguf) | IQ3_XS | 1.12GB |\n| [zuster_fietje.IQ3_S.gguf](https://huggingface.co/RichardErkhov/ekrombouts_-_zuster_fietje-gguf/blob/main/zuster_fietje.IQ3_S.gguf) | IQ3_S | 1.16GB |\n| [zuster_fietje.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/ekrombouts_-_zuster_fietje-gguf/blob/main/zuster_fietje.Q3_K_S.gguf) | Q3_K_S | 1.16GB |\n| [zuster_fietje.IQ3_M.gguf](https://huggingface.co/RichardErkhov/ekrombouts_-_zuster_fietje-gguf/blob/main/zuster_fietje.IQ3_M.gguf) | IQ3_M | 1.23GB |\n| [zuster_fietje.Q3_K.gguf](https://huggingface.co/RichardErkhov/ekrombouts_-_zuster_fietje-gguf/blob/main/zuster_fietje.Q3_K.gguf) | Q3_K | 1.33GB |\n| [zuster_fietje.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/ekrombouts_-_zuster_fietje-gguf/blob/main/zuster_fietje.Q3_K_M.gguf) | Q3_K_M | 1.33GB |\n| [zuster_fietje.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/ekrombouts_-_zuster_fietje-gguf/blob/main/zuster_fietje.Q3_K_L.gguf) | Q3_K_L | 1.46GB |\n| [zuster_fietje.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/ekrombouts_-_zuster_fietje-gguf/blob/main/zuster_fietje.IQ4_XS.gguf) | IQ4_XS | 1.43GB |\n| [zuster_fietje.Q4_0.gguf](https://huggingface.co/RichardErkhov/ekrombouts_-_zuster_fietje-gguf/blob/main/zuster_fietje.Q4_0.gguf) | Q4_0 | 1.49GB |\n| [zuster_fietje.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/ekrombouts_-_zuster_fietje-gguf/blob/main/zuster_fietje.IQ4_NL.gguf) | IQ4_NL | 1.5GB |\n| [zuster_fietje.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/ekrombouts_-_zuster_fietje-gguf/blob/main/zuster_fietje.Q4_K_S.gguf) | Q4_K_S | 1.5GB |\n| [zuster_fietje.Q4_K.gguf](https://huggingface.co/RichardErkhov/ekrombouts_-_zuster_fietje-gguf/blob/main/zuster_fietje.Q4_K.gguf) | Q4_K | 1.62GB |\n| [zuster_fietje.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/ekrombouts_-_zuster_fietje-gguf/blob/main/zuster_fietje.Q4_K_M.gguf) | Q4_K_M | 1.62GB |\n| [zuster_fietje.Q4_1.gguf](https://huggingface.co/RichardErkhov/ekrombouts_-_zuster_fietje-gguf/blob/main/zuster_fietje.Q4_1.gguf) | Q4_1 | 1.64GB |\n| [zuster_fietje.Q5_0.gguf](https://huggingface.co/RichardErkhov/ekrombouts_-_zuster_fietje-gguf/blob/main/zuster_fietje.Q5_0.gguf) | Q5_0 | 1.8GB |\n| [zuster_fietje.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/ekrombouts_-_zuster_fietje-gguf/blob/main/zuster_fietje.Q5_K_S.gguf) | Q5_K_S | 1.8GB |\n| [zuster_fietje.Q5_K.gguf](https://huggingface.co/RichardErkhov/ekrombouts_-_zuster_fietje-gguf/blob/main/zuster_fietje.Q5_K.gguf) | Q5_K | 1.86GB |\n| [zuster_fietje.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/ekrombouts_-_zuster_fietje-gguf/blob/main/zuster_fietje.Q5_K_M.gguf) | Q5_K_M | 1.86GB |\n| [zuster_fietje.Q5_1.gguf](https://huggingface.co/RichardErkhov/ekrombouts_-_zuster_fietje-gguf/blob/main/zuster_fietje.Q5_1.gguf) | Q5_1 | 1.95GB |\n| [zuster_fietje.Q6_K.gguf](https://huggingface.co/RichardErkhov/ekrombouts_-_zuster_fietje-gguf/blob/main/zuster_fietje.Q6_K.gguf) | Q6_K | 2.12GB |\n| [zuster_fietje.Q8_0.gguf](https://huggingface.co/RichardErkhov/ekrombouts_-_zuster_fietje-gguf/blob/main/zuster_fietje.Q8_0.gguf) | Q8_0 | 2.75GB |\n\n\n\n\nOriginal model description:\n---\nlibrary_name: transformers\ntags:\n- medical\nlicense: mit\ndatasets:\n- ekrombouts/Gardenia_instruct_dataset\n- ekrombouts/Olympia_SAMPC_dataset\nlanguage:\n- nl\nbase_model:\n- BramVanroy/fietje-2-instruct\n---\n\n# Model Card for Model ID\nThis model is a fine-tuned version of bramvanrooy/fietje-2, designed to generate responses based on nursing home reports.\n\n## Model Details\n- **Developed by:** Eva Rombouts\n- **Model type:** Causal Language Model\n- **Language(s) (NLP):** Dutch\n- **License:** MIT\n- **Finetuned from model [optional]:** BramVanroy/fietje-2-instruct\n\n### Model Sources\n- **Repository:** https://github.com/ekrombouts/gcai_zuster_fietje\n\n## Uses\n### Direct Use\nGenerating summaries and responses based on nursing home reports.\n\n### Out-of-Scope Use\nNot suitable for generating medical advice or any other critical decision-making processes.\n\n## Bias, Risks, and Limitations\nThe model may generate biased or inaccurate responses. Users should verify the generated content.\n\n## How to Get Started with the Model\nUse the code below to get started with the model.\n\n```python\nfrom transformers import AutoModelForCausalLM, AutoTokenizer\n\nmodel_id = \"ekrombouts/zuster_fietje\"\n\nmodel = AutoModelForCausalLM.from_pretrained(model_id)\ntokenizer = AutoTokenizer.from_pretrained(model_id)\n\nprompt = \"\"\"Rapportages:\nMw was vanmorgen incontinent van urine, bed was ook nat. Mw is volledig verzorgd, bed is verschoond,\nMw. haar kledingkast is opgeruimd.\nMw. zei:\"oooh kind, ik heb zo'n pijn. Mijn benen. Dat gaat nooit meer weg.\" Mw. zat in haar rolstoel en haar gezicht trok weg van de pijn en kreeg traanogen. Mw. werkte goed mee tijdens adl. en was vriendelijk aanwezig. Pijn. Mw. kreeg haar medicatie in de ochtend, waaronder pijnstillers. 1 uur later adl. gegeven.\nMevr. in de ochtend ondersteund met wassen en aankleden. Mevr was rustig aanwezig.\nMw is volledig geholpen met ochtendzorg, mw haar haren zijn gewassen. Mw haar nagels zijn kort geknipt.\nMevr heeft het ontbijt op bed genuttigd. Daarna mocht ik na de tweede poging Mevr ondersteunen met wassen en aankleden.\n\nInstructie:\nBeschrijf de lichamelijke klachten\n\nAntwoord:\n\"\"\"\n\ninput_ids = tokenizer(prompt, return_tensors=\"pt\").input_ids\noutput = model.generate(input_ids, max_new_tokens=1024)\nprint(tokenizer.decode(output[0], skip_special_tokens=True))\n```\n## Training Details\n### Training Data\n- ekrombouts/Gardenia_instruct_dataset\n- ekrombouts/Olympia_SAMPC_dataset\n\n### Training Procedure\n\n#### Training Hyperparameters\n- **Training regime:** fp16 mixed precision\n\n## Evaluation\nEvaluated on a subset of nursing home reports.\n\n#### Metrics\nQualitative assessment of generated responses.\n\n### Results\n\n[More Information Needed]\n\n## Environmental Impact\n- **Hardware Type:** GPU (NVIDIA A100)\n- **Hours used:** 8 hours\n- **Cloud Provider:** Google \n- **Compute Region:** europe-west4 \n- **Carbon Emitted:** 54 kg CO2 eq.\n\n**BibTeX:**\n```bibtex\n@misc{zuster_fietje,\n  author = {Eva Rombouts},\n  title = {Zuster Fietje: A Fine-Tuned Model for Nursing Home Reports},\n  year = {2024},\n  url = {https://huggingface.co/ekrombouts/zuster_fietje},\n}```\n\n",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "endpoints_compatible",
    "region:us",
    "conversational"
  ],
  "likes": 0,
  "downloads": 583,
  "gated": false,
  "private": false,
  "last_modified": "2025-02-28T05:38:30.000Z",
  "created_at": "2025-02-28T04:45:10.000Z",
  "pipeline_tag": "",
  "library_name": ""
}

{
  "_id": "67c13f56d41b98930a5a24aa",
  "id": "RichardErkhov/ekrombouts_-_zuster_fietje-gguf",
  "modelId": "RichardErkhov/ekrombouts_-_zuster_fietje-gguf",
  "sha": "632f15ee0432333a3dadf301f322949ec276ccf4",
  "createdAt": "2025-02-28T04:45:10.000Z",
  "lastModified": "2025-02-28T05:38:30.000Z",
  "author": "RichardErkhov",
  "downloads": 583,
  "likes": 0,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "",
  "siblings_count": 24
}