richarderkhov/ruqiya_-_merge-gemma-2b-it-with-a-fine-tuned-one-for-arabic-gguf overview

{
  "metadata": {},
  "card_data": {
    "frontmatter": {},
    "hero_image_url": "",
    "summary": "It is a merge of the following models using LazyMergekit: * Ruqiya/Fine-Tuning-Gemma-2b-it-for-Arabic",
    "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\nMerge-Gemma-2b-it-with-a-Fine-Tuned-one-for-Arabic - GGUF\n- Model creator: https://huggingface.co/Ruqiya/\n- Original model: https://huggingface.co/Ruqiya/Merge-Gemma-2b-it-with-a-Fine-Tuned-one-for-Arabic/\n\n\n| Name | Quant method | Size |\n| ---- | ---- | ---- |\n| [Merge-Gemma-2b-it-with-a-Fine-Tuned-one-for-Arabic.Q2_K.gguf](https://huggingface.co/RichardErkhov/Ruqiya_-_Merge-Gemma-2b-it-with-a-Fine-Tuned-one-for-Arabic-gguf/blob/main/Merge-Gemma-2b-it-with-a-Fine-Tuned-one-for-Arabic.Q2_K.gguf) | Q2_K | 1.08GB |\n| [Merge-Gemma-2b-it-with-a-Fine-Tuned-one-for-Arabic.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/Ruqiya_-_Merge-Gemma-2b-it-with-a-Fine-Tuned-one-for-Arabic-gguf/blob/main/Merge-Gemma-2b-it-with-a-Fine-Tuned-one-for-Arabic.Q3_K_S.gguf) | Q3_K_S | 1.2GB |\n| [Merge-Gemma-2b-it-with-a-Fine-Tuned-one-for-Arabic.Q3_K.gguf](https://huggingface.co/RichardErkhov/Ruqiya_-_Merge-Gemma-2b-it-with-a-Fine-Tuned-one-for-Arabic-gguf/blob/main/Merge-Gemma-2b-it-with-a-Fine-Tuned-one-for-Arabic.Q3_K.gguf) | Q3_K | 1.29GB |\n| [Merge-Gemma-2b-it-with-a-Fine-Tuned-one-for-Arabic.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/Ruqiya_-_Merge-Gemma-2b-it-with-a-Fine-Tuned-one-for-Arabic-gguf/blob/main/Merge-Gemma-2b-it-with-a-Fine-Tuned-one-for-Arabic.Q3_K_M.gguf) | Q3_K_M | 1.29GB |\n| [Merge-Gemma-2b-it-with-a-Fine-Tuned-one-for-Arabic.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/Ruqiya_-_Merge-Gemma-2b-it-with-a-Fine-Tuned-one-for-Arabic-gguf/blob/main/Merge-Gemma-2b-it-with-a-Fine-Tuned-one-for-Arabic.Q3_K_L.gguf) | Q3_K_L | 1.36GB |\n| [Merge-Gemma-2b-it-with-a-Fine-Tuned-one-for-Arabic.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/Ruqiya_-_Merge-Gemma-2b-it-with-a-Fine-Tuned-one-for-Arabic-gguf/blob/main/Merge-Gemma-2b-it-with-a-Fine-Tuned-one-for-Arabic.IQ4_XS.gguf) | IQ4_XS | 1.4GB |\n| [Merge-Gemma-2b-it-with-a-Fine-Tuned-one-for-Arabic.Q4_0.gguf](https://huggingface.co/RichardErkhov/Ruqiya_-_Merge-Gemma-2b-it-with-a-Fine-Tuned-one-for-Arabic-gguf/blob/main/Merge-Gemma-2b-it-with-a-Fine-Tuned-one-for-Arabic.Q4_0.gguf) | Q4_0 | 1.44GB |\n| [Merge-Gemma-2b-it-with-a-Fine-Tuned-one-for-Arabic.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/Ruqiya_-_Merge-Gemma-2b-it-with-a-Fine-Tuned-one-for-Arabic-gguf/blob/main/Merge-Gemma-2b-it-with-a-Fine-Tuned-one-for-Arabic.IQ4_NL.gguf) | IQ4_NL | 1.45GB |\n| [Merge-Gemma-2b-it-with-a-Fine-Tuned-one-for-Arabic.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/Ruqiya_-_Merge-Gemma-2b-it-with-a-Fine-Tuned-one-for-Arabic-gguf/blob/main/Merge-Gemma-2b-it-with-a-Fine-Tuned-one-for-Arabic.Q4_K_S.gguf) | Q4_K_S | 1.45GB |\n| [Merge-Gemma-2b-it-with-a-Fine-Tuned-one-for-Arabic.Q4_K.gguf](https://huggingface.co/RichardErkhov/Ruqiya_-_Merge-Gemma-2b-it-with-a-Fine-Tuned-one-for-Arabic-gguf/blob/main/Merge-Gemma-2b-it-with-a-Fine-Tuned-one-for-Arabic.Q4_K.gguf) | Q4_K | 1.52GB |\n| [Merge-Gemma-2b-it-with-a-Fine-Tuned-one-for-Arabic.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/Ruqiya_-_Merge-Gemma-2b-it-with-a-Fine-Tuned-one-for-Arabic-gguf/blob/main/Merge-Gemma-2b-it-with-a-Fine-Tuned-one-for-Arabic.Q4_K_M.gguf) | Q4_K_M | 1.52GB |\n| [Merge-Gemma-2b-it-with-a-Fine-Tuned-one-for-Arabic.Q4_1.gguf](https://huggingface.co/RichardErkhov/Ruqiya_-_Merge-Gemma-2b-it-with-a-Fine-Tuned-one-for-Arabic-gguf/blob/main/Merge-Gemma-2b-it-with-a-Fine-Tuned-one-for-Arabic.Q4_1.gguf) | Q4_1 | 1.56GB |\n| [Merge-Gemma-2b-it-with-a-Fine-Tuned-one-for-Arabic.Q5_0.gguf](https://huggingface.co/RichardErkhov/Ruqiya_-_Merge-Gemma-2b-it-with-a-Fine-Tuned-one-for-Arabic-gguf/blob/main/Merge-Gemma-2b-it-with-a-Fine-Tuned-one-for-Arabic.Q5_0.gguf) | Q5_0 | 1.68GB |\n| [Merge-Gemma-2b-it-with-a-Fine-Tuned-one-for-Arabic.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/Ruqiya_-_Merge-Gemma-2b-it-with-a-Fine-Tuned-one-for-Arabic-gguf/blob/main/Merge-Gemma-2b-it-with-a-Fine-Tuned-one-for-Arabic.Q5_K_S.gguf) | Q5_K_S | 1.68GB |\n| [Merge-Gemma-2b-it-with-a-Fine-Tuned-one-for-Arabic.Q5_K.gguf](https://huggingface.co/RichardErkhov/Ruqiya_-_Merge-Gemma-2b-it-with-a-Fine-Tuned-one-for-Arabic-gguf/blob/main/Merge-Gemma-2b-it-with-a-Fine-Tuned-one-for-Arabic.Q5_K.gguf) | Q5_K | 1.71GB |\n| [Merge-Gemma-2b-it-with-a-Fine-Tuned-one-for-Arabic.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/Ruqiya_-_Merge-Gemma-2b-it-with-a-Fine-Tuned-one-for-Arabic-gguf/blob/main/Merge-Gemma-2b-it-with-a-Fine-Tuned-one-for-Arabic.Q5_K_M.gguf) | Q5_K_M | 1.71GB |\n| [Merge-Gemma-2b-it-with-a-Fine-Tuned-one-for-Arabic.Q5_1.gguf](https://huggingface.co/RichardErkhov/Ruqiya_-_Merge-Gemma-2b-it-with-a-Fine-Tuned-one-for-Arabic-gguf/blob/main/Merge-Gemma-2b-it-with-a-Fine-Tuned-one-for-Arabic.Q5_1.gguf) | Q5_1 | 1.79GB |\n| [Merge-Gemma-2b-it-with-a-Fine-Tuned-one-for-Arabic.Q6_K.gguf](https://huggingface.co/RichardErkhov/Ruqiya_-_Merge-Gemma-2b-it-with-a-Fine-Tuned-one-for-Arabic-gguf/blob/main/Merge-Gemma-2b-it-with-a-Fine-Tuned-one-for-Arabic.Q6_K.gguf) | Q6_K | 1.92GB |\n| [Merge-Gemma-2b-it-with-a-Fine-Tuned-one-for-Arabic.Q8_0.gguf](https://huggingface.co/RichardErkhov/Ruqiya_-_Merge-Gemma-2b-it-with-a-Fine-Tuned-one-for-Arabic-gguf/blob/main/Merge-Gemma-2b-it-with-a-Fine-Tuned-one-for-Arabic.Q8_0.gguf) | Q8_0 | 2.49GB |\n\n\n\n\nOriginal model description:\n---\ntags:\n- merge\n- mergekit\n- lazymergekit\n- Ruqiya/Fine-Tuning-Gemma-2b-it-for-Arabic\nbase_model:\n- Ruqiya/Fine-Tuning-Gemma-2b-it-for-Arabic\n---\n\n# Merge-Gemma-2b-it-with-a-Fine-Tuned-one-for-Arabic\n\nIt is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):\n* [Ruqiya/Fine-Tuning-Gemma-2b-it-for-Arabic](https://huggingface.co/Ruqiya/Fine-Tuning-Gemma-2b-it-for-Arabic)\n\n## 🧩 Configuration\n\n```yaml\nmodels:\n  - model: google/gemma-2b-it\n    # No parameters necessary for base model\n  - model: Ruqiya/Fine-Tuning-Gemma-2b-it-for-Arabic\n    parameters:\n      density: 0.53\n      weight: 0.45\nmerge_method: dare_ties\nbase_model: google/gemma-2b-it\nparameters:\n  int8_mask: true\ndtype: bfloat16\nrandom_seed: 0\n```\n\n## 💻 Usage\n\n```python\n!pip install -qU transformers accelerate\n\nfrom transformers import AutoTokenizer\nimport transformers\nimport torch\n\nmodel = \"Ruqiya/Merge-Gemma-2b-it-with-a-Fine-Tuned-one-for-Arabic\"\nmessages = [{\"role\": \"user\", \"content\": \"What is a large language model?\"}]\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",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "endpoints_compatible",
    "region:us",
    "conversational"
  ],
  "likes": 0,
  "downloads": 94,
  "gated": false,
  "private": false,
  "last_modified": "2024-10-29T22:22:55.000Z",
  "created_at": "2024-10-29T20:25:51.000Z",
  "pipeline_tag": "",
  "library_name": ""
}

{
  "_id": "672144cfacad6a37f2c503cc",
  "id": "RichardErkhov/Ruqiya_-_Merge-Gemma-2b-it-with-a-Fine-Tuned-one-for-Arabic-gguf",
  "modelId": "RichardErkhov/Ruqiya_-_Merge-Gemma-2b-it-with-a-Fine-Tuned-one-for-Arabic-gguf",
  "sha": "103c6b5ff4431e7efbc4230650e8ea1615503d6a",
  "createdAt": "2024-10-29T20:25:51.000Z",
  "lastModified": "2024-10-29T22:22:55.000Z",
  "author": "RichardErkhov",
  "downloads": 94,
  "likes": 0,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "",
  "siblings_count": 21
}