richarderkhov/emillykkejensen_-_phi-3-mini-4k-instruct-dansk-gguf overview

{
  "metadata": {},
  "card_data": {
    "frontmatter": {},
    "hero_image_url": "https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg",
    "summary": "This model is a fine-tuned version of microsoft/Phi-3-mini-4k-instruct on the kobprof/skolegpt-instruct dataset. It achieves the following results on the evaluation set:",
    "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\nPhi-3-mini-4k-instruct-dansk - GGUF\n- Model creator: https://huggingface.co/emillykkejensen/\n- Original model: https://huggingface.co/emillykkejensen/Phi-3-mini-4k-instruct-dansk/\n\n\n| Name | Quant method | Size |\n| ---- | ---- | ---- |\n| [Phi-3-mini-4k-instruct-dansk.Q2_K.gguf](https://huggingface.co/RichardErkhov/emillykkejensen_-_Phi-3-mini-4k-instruct-dansk-gguf/blob/main/Phi-3-mini-4k-instruct-dansk.Q2_K.gguf) | Q2_K | 1.32GB |\n| [Phi-3-mini-4k-instruct-dansk.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/emillykkejensen_-_Phi-3-mini-4k-instruct-dansk-gguf/blob/main/Phi-3-mini-4k-instruct-dansk.IQ3_XS.gguf) | IQ3_XS | 1.51GB |\n| [Phi-3-mini-4k-instruct-dansk.IQ3_S.gguf](https://huggingface.co/RichardErkhov/emillykkejensen_-_Phi-3-mini-4k-instruct-dansk-gguf/blob/main/Phi-3-mini-4k-instruct-dansk.IQ3_S.gguf) | IQ3_S | 1.57GB |\n| [Phi-3-mini-4k-instruct-dansk.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/emillykkejensen_-_Phi-3-mini-4k-instruct-dansk-gguf/blob/main/Phi-3-mini-4k-instruct-dansk.Q3_K_S.gguf) | Q3_K_S | 1.57GB |\n| [Phi-3-mini-4k-instruct-dansk.IQ3_M.gguf](https://huggingface.co/RichardErkhov/emillykkejensen_-_Phi-3-mini-4k-instruct-dansk-gguf/blob/main/Phi-3-mini-4k-instruct-dansk.IQ3_M.gguf) | IQ3_M | 1.73GB |\n| [Phi-3-mini-4k-instruct-dansk.Q3_K.gguf](https://huggingface.co/RichardErkhov/emillykkejensen_-_Phi-3-mini-4k-instruct-dansk-gguf/blob/main/Phi-3-mini-4k-instruct-dansk.Q3_K.gguf) | Q3_K | 1.82GB |\n| [Phi-3-mini-4k-instruct-dansk.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/emillykkejensen_-_Phi-3-mini-4k-instruct-dansk-gguf/blob/main/Phi-3-mini-4k-instruct-dansk.Q3_K_M.gguf) | Q3_K_M | 1.82GB |\n| [Phi-3-mini-4k-instruct-dansk.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/emillykkejensen_-_Phi-3-mini-4k-instruct-dansk-gguf/blob/main/Phi-3-mini-4k-instruct-dansk.Q3_K_L.gguf) | Q3_K_L | 1.94GB |\n| [Phi-3-mini-4k-instruct-dansk.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/emillykkejensen_-_Phi-3-mini-4k-instruct-dansk-gguf/blob/main/Phi-3-mini-4k-instruct-dansk.IQ4_XS.gguf) | IQ4_XS | 1.93GB |\n| [Phi-3-mini-4k-instruct-dansk.Q4_0.gguf](https://huggingface.co/RichardErkhov/emillykkejensen_-_Phi-3-mini-4k-instruct-dansk-gguf/blob/main/Phi-3-mini-4k-instruct-dansk.Q4_0.gguf) | Q4_0 | 2.03GB |\n| [Phi-3-mini-4k-instruct-dansk.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/emillykkejensen_-_Phi-3-mini-4k-instruct-dansk-gguf/blob/main/Phi-3-mini-4k-instruct-dansk.IQ4_NL.gguf) | IQ4_NL | 2.04GB |\n| [Phi-3-mini-4k-instruct-dansk.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/emillykkejensen_-_Phi-3-mini-4k-instruct-dansk-gguf/blob/main/Phi-3-mini-4k-instruct-dansk.Q4_K_S.gguf) | Q4_K_S | 2.04GB |\n| [Phi-3-mini-4k-instruct-dansk.Q4_K.gguf](https://huggingface.co/RichardErkhov/emillykkejensen_-_Phi-3-mini-4k-instruct-dansk-gguf/blob/main/Phi-3-mini-4k-instruct-dansk.Q4_K.gguf) | Q4_K | 2.23GB |\n| [Phi-3-mini-4k-instruct-dansk.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/emillykkejensen_-_Phi-3-mini-4k-instruct-dansk-gguf/blob/main/Phi-3-mini-4k-instruct-dansk.Q4_K_M.gguf) | Q4_K_M | 2.23GB |\n| [Phi-3-mini-4k-instruct-dansk.Q4_1.gguf](https://huggingface.co/RichardErkhov/emillykkejensen_-_Phi-3-mini-4k-instruct-dansk-gguf/blob/main/Phi-3-mini-4k-instruct-dansk.Q4_1.gguf) | Q4_1 | 2.24GB |\n| [Phi-3-mini-4k-instruct-dansk.Q5_0.gguf](https://huggingface.co/RichardErkhov/emillykkejensen_-_Phi-3-mini-4k-instruct-dansk-gguf/blob/main/Phi-3-mini-4k-instruct-dansk.Q5_0.gguf) | Q5_0 | 2.46GB |\n| [Phi-3-mini-4k-instruct-dansk.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/emillykkejensen_-_Phi-3-mini-4k-instruct-dansk-gguf/blob/main/Phi-3-mini-4k-instruct-dansk.Q5_K_S.gguf) | Q5_K_S | 2.46GB |\n| [Phi-3-mini-4k-instruct-dansk.Q5_K.gguf](https://huggingface.co/RichardErkhov/emillykkejensen_-_Phi-3-mini-4k-instruct-dansk-gguf/blob/main/Phi-3-mini-4k-instruct-dansk.Q5_K.gguf) | Q5_K | 2.62GB |\n| [Phi-3-mini-4k-instruct-dansk.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/emillykkejensen_-_Phi-3-mini-4k-instruct-dansk-gguf/blob/main/Phi-3-mini-4k-instruct-dansk.Q5_K_M.gguf) | Q5_K_M | 2.62GB |\n| [Phi-3-mini-4k-instruct-dansk.Q5_1.gguf](https://huggingface.co/RichardErkhov/emillykkejensen_-_Phi-3-mini-4k-instruct-dansk-gguf/blob/main/Phi-3-mini-4k-instruct-dansk.Q5_1.gguf) | Q5_1 | 2.68GB |\n| [Phi-3-mini-4k-instruct-dansk.Q6_K.gguf](https://huggingface.co/RichardErkhov/emillykkejensen_-_Phi-3-mini-4k-instruct-dansk-gguf/blob/main/Phi-3-mini-4k-instruct-dansk.Q6_K.gguf) | Q6_K | 2.92GB |\n| [Phi-3-mini-4k-instruct-dansk.Q8_0.gguf](https://huggingface.co/RichardErkhov/emillykkejensen_-_Phi-3-mini-4k-instruct-dansk-gguf/blob/main/Phi-3-mini-4k-instruct-dansk.Q8_0.gguf) | Q8_0 | 3.78GB |\n\n\n\n\nOriginal model description:\n---\nlicense: mit\nbase_model: microsoft/Phi-3-mini-4k-instruct\ntags:\n- trl\n- sft\n- generated_from_trainer\n- danish\ndatasets:\n- kobprof/skolegpt-instruct\nmodel-index:\n- name: Phi-3-mini-4k-instruct-dansk\n  results: []\n---\n\n<!-- This model card has been generated automatically according to the information the Trainer had access to. You\nshould probably proofread and complete it, then remove this comment. -->\n\n[<img src=\"https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg\" alt=\"Visualize in Weights & Biases\" width=\"200\" height=\"32\"/>](https://wandb.ai/emillykkejensen/LLM-instruct/runs/do7hs1j9)\n# Phi-3-mini-4k-instruct-dansk\n\nThis model is a fine-tuned version of [microsoft/Phi-3-mini-4k-instruct](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct) on the [kobprof/skolegpt-instruct](https://huggingface.co/datasets/kobprof/skolegpt-instruct) dataset.\nIt achieves the following results on the evaluation set:\n- Loss: 1.5493\n\n## Model description\n\nMore information needed\n\n## Intended uses & limitations\n\nMore information needed\n\n## Training and evaluation data\n\nMore information needed\n\n## Training procedure\n\n### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 2e-05\n- train_batch_size: 4\n- eval_batch_size: 4\n- seed: 42\n- distributed_type: multi-GPU\n- num_devices: 4\n- total_train_batch_size: 16\n- total_eval_batch_size: 16\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: cosine\n- lr_scheduler_warmup_ratio: 0.2\n- num_epochs: 1\n\n### Training results\n\n\n\n### Framework versions\n\n- Transformers 4.41.0.dev0\n- Pytorch 2.2.0\n- Datasets 2.19.0\n- Tokenizers 0.19.1\n\n\n",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "endpoints_compatible",
    "region:us",
    "conversational"
  ],
  "likes": 0,
  "downloads": 93,
  "gated": false,
  "private": false,
  "last_modified": "2024-10-07T02:14:21.000Z",
  "created_at": "2024-10-07T00:54:07.000Z",
  "pipeline_tag": "",
  "library_name": ""
}

{
  "_id": "6703312f9938e2da5837339e",
  "id": "RichardErkhov/emillykkejensen_-_Phi-3-mini-4k-instruct-dansk-gguf",
  "modelId": "RichardErkhov/emillykkejensen_-_Phi-3-mini-4k-instruct-dansk-gguf",
  "sha": "0ffe4b1a1ae87623358e08acb71e513605879cf1",
  "createdAt": "2024-10-07T00:54:07.000Z",
  "lastModified": "2024-10-07T02:14:21.000Z",
  "author": "RichardErkhov",
  "downloads": 93,
  "likes": 0,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "",
  "siblings_count": 24
}