richarderkhov/ruqiya_-_fine-tuning-gemma-2b-it-for-arabic-gguf overview

{
  "metadata": {},
  "card_data": {
    "frontmatter": {},
    "hero_image_url": "",
    "summary": "This model is a fine-tuned version of google/gemma-2b-it on arbml/CIDAR Arabic dataset. It achieves the following results on the evaluation set: ### Direct Use  ``python !pip install -qU transformers accelerate from transformers import AutoTokenizer import transformers import torch model = \"Ruqiya/Fine-Tuning-Gemma-2b-it-for-Arabic\" messages = [{\"role\": \"user\", \"content\": \"ما هو الذكاء الاصطناعي؟\"}] tokenizer = AutoTokenizer.from_pretrained(model) prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True) pipeline = transformers.pipeline( \"text-generation\", model=model, torch_dtype=torch.float16, device_map=\"auto\", ) outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95) print(outputs[0][\"generated_text\"]) ``",
    "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\nFine-Tuning-Gemma-2b-it-for-Arabic - GGUF\n- Model creator: https://huggingface.co/Ruqiya/\n- Original model: https://huggingface.co/Ruqiya/Fine-Tuning-Gemma-2b-it-for-Arabic/\n\n\n| Name | Quant method | Size |\n| ---- | ---- | ---- |\n| [Fine-Tuning-Gemma-2b-it-for-Arabic.Q2_K.gguf](https://huggingface.co/RichardErkhov/Ruqiya_-_Fine-Tuning-Gemma-2b-it-for-Arabic-gguf/blob/main/Fine-Tuning-Gemma-2b-it-for-Arabic.Q2_K.gguf) | Q2_K | 1.08GB |\n| [Fine-Tuning-Gemma-2b-it-for-Arabic.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/Ruqiya_-_Fine-Tuning-Gemma-2b-it-for-Arabic-gguf/blob/main/Fine-Tuning-Gemma-2b-it-for-Arabic.IQ3_XS.gguf) | IQ3_XS | 1.16GB |\n| [Fine-Tuning-Gemma-2b-it-for-Arabic.IQ3_S.gguf](https://huggingface.co/RichardErkhov/Ruqiya_-_Fine-Tuning-Gemma-2b-it-for-Arabic-gguf/blob/main/Fine-Tuning-Gemma-2b-it-for-Arabic.IQ3_S.gguf) | IQ3_S | 1.2GB |\n| [Fine-Tuning-Gemma-2b-it-for-Arabic.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/Ruqiya_-_Fine-Tuning-Gemma-2b-it-for-Arabic-gguf/blob/main/Fine-Tuning-Gemma-2b-it-for-Arabic.Q3_K_S.gguf) | Q3_K_S | 1.2GB |\n| [Fine-Tuning-Gemma-2b-it-for-Arabic.IQ3_M.gguf](https://huggingface.co/RichardErkhov/Ruqiya_-_Fine-Tuning-Gemma-2b-it-for-Arabic-gguf/blob/main/Fine-Tuning-Gemma-2b-it-for-Arabic.IQ3_M.gguf) | IQ3_M | 1.22GB |\n| [Fine-Tuning-Gemma-2b-it-for-Arabic.Q3_K.gguf](https://huggingface.co/RichardErkhov/Ruqiya_-_Fine-Tuning-Gemma-2b-it-for-Arabic-gguf/blob/main/Fine-Tuning-Gemma-2b-it-for-Arabic.Q3_K.gguf) | Q3_K | 1.29GB |\n| [Fine-Tuning-Gemma-2b-it-for-Arabic.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/Ruqiya_-_Fine-Tuning-Gemma-2b-it-for-Arabic-gguf/blob/main/Fine-Tuning-Gemma-2b-it-for-Arabic.Q3_K_M.gguf) | Q3_K_M | 1.29GB |\n| [Fine-Tuning-Gemma-2b-it-for-Arabic.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/Ruqiya_-_Fine-Tuning-Gemma-2b-it-for-Arabic-gguf/blob/main/Fine-Tuning-Gemma-2b-it-for-Arabic.Q3_K_L.gguf) | Q3_K_L | 1.36GB |\n| [Fine-Tuning-Gemma-2b-it-for-Arabic.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/Ruqiya_-_Fine-Tuning-Gemma-2b-it-for-Arabic-gguf/blob/main/Fine-Tuning-Gemma-2b-it-for-Arabic.IQ4_XS.gguf) | IQ4_XS | 1.4GB |\n| [Fine-Tuning-Gemma-2b-it-for-Arabic.Q4_0.gguf](https://huggingface.co/RichardErkhov/Ruqiya_-_Fine-Tuning-Gemma-2b-it-for-Arabic-gguf/blob/main/Fine-Tuning-Gemma-2b-it-for-Arabic.Q4_0.gguf) | Q4_0 | 1.44GB |\n| [Fine-Tuning-Gemma-2b-it-for-Arabic.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/Ruqiya_-_Fine-Tuning-Gemma-2b-it-for-Arabic-gguf/blob/main/Fine-Tuning-Gemma-2b-it-for-Arabic.IQ4_NL.gguf) | IQ4_NL | 1.45GB |\n| [Fine-Tuning-Gemma-2b-it-for-Arabic.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/Ruqiya_-_Fine-Tuning-Gemma-2b-it-for-Arabic-gguf/blob/main/Fine-Tuning-Gemma-2b-it-for-Arabic.Q4_K_S.gguf) | Q4_K_S | 1.45GB |\n| [Fine-Tuning-Gemma-2b-it-for-Arabic.Q4_K.gguf](https://huggingface.co/RichardErkhov/Ruqiya_-_Fine-Tuning-Gemma-2b-it-for-Arabic-gguf/blob/main/Fine-Tuning-Gemma-2b-it-for-Arabic.Q4_K.gguf) | Q4_K | 1.52GB |\n| [Fine-Tuning-Gemma-2b-it-for-Arabic.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/Ruqiya_-_Fine-Tuning-Gemma-2b-it-for-Arabic-gguf/blob/main/Fine-Tuning-Gemma-2b-it-for-Arabic.Q4_K_M.gguf) | Q4_K_M | 1.52GB |\n| [Fine-Tuning-Gemma-2b-it-for-Arabic.Q4_1.gguf](https://huggingface.co/RichardErkhov/Ruqiya_-_Fine-Tuning-Gemma-2b-it-for-Arabic-gguf/blob/main/Fine-Tuning-Gemma-2b-it-for-Arabic.Q4_1.gguf) | Q4_1 | 1.56GB |\n| [Fine-Tuning-Gemma-2b-it-for-Arabic.Q5_0.gguf](https://huggingface.co/RichardErkhov/Ruqiya_-_Fine-Tuning-Gemma-2b-it-for-Arabic-gguf/blob/main/Fine-Tuning-Gemma-2b-it-for-Arabic.Q5_0.gguf) | Q5_0 | 1.68GB |\n| [Fine-Tuning-Gemma-2b-it-for-Arabic.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/Ruqiya_-_Fine-Tuning-Gemma-2b-it-for-Arabic-gguf/blob/main/Fine-Tuning-Gemma-2b-it-for-Arabic.Q5_K_S.gguf) | Q5_K_S | 1.68GB |\n| [Fine-Tuning-Gemma-2b-it-for-Arabic.Q5_K.gguf](https://huggingface.co/RichardErkhov/Ruqiya_-_Fine-Tuning-Gemma-2b-it-for-Arabic-gguf/blob/main/Fine-Tuning-Gemma-2b-it-for-Arabic.Q5_K.gguf) | Q5_K | 1.71GB |\n| [Fine-Tuning-Gemma-2b-it-for-Arabic.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/Ruqiya_-_Fine-Tuning-Gemma-2b-it-for-Arabic-gguf/blob/main/Fine-Tuning-Gemma-2b-it-for-Arabic.Q5_K_M.gguf) | Q5_K_M | 1.71GB |\n| [Fine-Tuning-Gemma-2b-it-for-Arabic.Q5_1.gguf](https://huggingface.co/RichardErkhov/Ruqiya_-_Fine-Tuning-Gemma-2b-it-for-Arabic-gguf/blob/main/Fine-Tuning-Gemma-2b-it-for-Arabic.Q5_1.gguf) | Q5_1 | 1.79GB |\n| [Fine-Tuning-Gemma-2b-it-for-Arabic.Q6_K.gguf](https://huggingface.co/RichardErkhov/Ruqiya_-_Fine-Tuning-Gemma-2b-it-for-Arabic-gguf/blob/main/Fine-Tuning-Gemma-2b-it-for-Arabic.Q6_K.gguf) | Q6_K | 1.92GB |\n| [Fine-Tuning-Gemma-2b-it-for-Arabic.Q8_0.gguf](https://huggingface.co/RichardErkhov/Ruqiya_-_Fine-Tuning-Gemma-2b-it-for-Arabic-gguf/blob/main/Fine-Tuning-Gemma-2b-it-for-Arabic.Q8_0.gguf) | Q8_0 | 2.49GB |\n\n\n\n\nOriginal model description:\n---\ndatasets:\n- arbml/CIDAR\nbase_model: google/gemma-2b-it\npipeline_tag: text-generation\nlanguage:\n- ar\n- en\n---\n\n# Fine-Tuning-Gemma-2b-it-for-Arabic\n\n<!-- Provide a quick summary of what the model is/does. -->\nThis model is a fine-tuned version of [google/gemma-2b-it](https://huggingface.co/google/gemma-2b-it) on [arbml/CIDAR](https://huggingface.co/datasets/arbml/CIDAR) Arabic dataset.  \n\nIt achieves the following results on the evaluation set:\n- training_loss=2.281057505607605\n\n\n\n### Direct Use\n\n<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->\n```python\n!pip install -qU transformers accelerate\n\nfrom transformers import AutoTokenizer\nimport transformers\nimport torch\n\nmodel = \"Ruqiya/Fine-Tuning-Gemma-2b-it-for-Arabic\"\nmessages = [{\"role\": \"user\", \"content\": \"ما هو الذكاء الاصطناعي؟\"}]\n\ntokenizer = AutoTokenizer.from_pretrained(model)\nprompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)\npipeline = transformers.pipeline(\n    \"text-generation\",\n    model=model,\n    torch_dtype=torch.float16,\n    device_map=\"auto\",\n)\n\noutputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)\nprint(outputs[0][\"generated_text\"])\n```\n\n\n\n",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "endpoints_compatible",
    "region:us",
    "conversational"
  ],
  "likes": 0,
  "downloads": 124,
  "gated": false,
  "private": false,
  "last_modified": "2024-07-22T04:00:38.000Z",
  "created_at": "2024-07-21T22:55:34.000Z",
  "pipeline_tag": "",
  "library_name": ""
}

{
  "_id": "669d91e654725cd6e0f75df9",
  "id": "RichardErkhov/Ruqiya_-_Fine-Tuning-Gemma-2b-it-for-Arabic-gguf",
  "modelId": "RichardErkhov/Ruqiya_-_Fine-Tuning-Gemma-2b-it-for-Arabic-gguf",
  "sha": "d8feda06d425b59a76621f33a3a04a516cc15895",
  "createdAt": "2024-07-21T22:55:34.000Z",
  "lastModified": "2024-07-22T04:00:38.000Z",
  "author": "RichardErkhov",
  "downloads": 124,
  "likes": 0,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "",
  "siblings_count": 24
}