richarderkhov/hplt_-_sft-fpft-es-bloom-560m-gguf overview

{
  "metadata": {},
  "card_data": {
    "frontmatter": {},
    "hero_image_url": "",
    "summary": "Quantization made by Richard Erkhov. Github Discord Request more models sft-fpft-es-bloom-560m - GGUF | Name | Quant method | Size | | ---- | ---- | ---- | | sft-fpft-es-bloom-560m.Q2_K.gguf | Q2_K | 0.39GB | | sft-fpft-es-bloom-560m.IQ3_XS.gguf | IQ3_XS | 0.43GB | | sft-fpft-es-bloom-560m.IQ3_S.gguf | IQ3_S | 0.43GB | | sft-fpft-es-bloom-560m.Q3_K_S.gguf | Q3_K_S | 0.43GB | | sft-fpft-es-bloom-560m.IQ3_M.gguf | IQ3_M | 0.45GB | | sft-fpft-es-bloom-560m.Q3_K.gguf | Q3_K | 0.46GB | | sft-fpft-es-bloom-560m.Q3_K_M.gguf | Q3_K_M | 0.46GB | | sft-fpft-es-bloom-560m.Q3_K_L.gguf | Q3_K_L | 0.47GB | | sft-fpft-es-bloom-560m.IQ4_XS.gguf | IQ4_XS | 0.49GB | | sft-fpft-es-bloom-560m.Q4_0.gguf | Q4_0 | 0.5GB | | sft-fpft-es-bloom-560m.IQ4_NL.gguf | IQ4_NL | 0.5GB | | sft-fpft-es-bloom-560m.Q4_K_S.gguf | Q4_K_S | 0.5GB | | sft-fpft-es-bloom-560m.Q4_K.gguf | Q4_K | 0.52GB | | sft-fpft-es-bloom-560m.Q4_K_M.gguf | Q4_K_M | 0.52GB | | sft-fpft-es-bloom-560m.Q4_1.gguf | Q4_1 | 0.53GB | | sft-fpft-es-bloom-560m.Q5_0.gguf | Q5_0 | 0.57GB | | sft-fpft-es-bloom-560m.Q5_K_S.gguf | Q5_K_S | 0.57GB | | sft-fpft-es-bloom-560m.Q5_K.gguf | Q5_K | 0.58GB | | sft-fpft-es-bloom-560m.Q5_K_M.gguf | Q5_K_M | 0.58GB | | sft-fpft-es-bloom-560m.Q5_1.gguf | Q5_1 | 0.6GB | | sft-fpft-es-bloom-560m.Q6_K.gguf | Q6_K | 0.64GB | | sft-fpft-es-bloom-560m.Q8_0.gguf | Q8_0 | 0.82GB | Original model description: --- language: tags: license: cc-by-nc-4.0 --- ###  Model Description This HF repository contains base LLMs instruction tuned (SFT) with full-parameter fine-tuning and then used to study whether monolingual or multilingual instruction tuning is more favourable. * GitHub * Paper #### Instruction tuning details * Base model: bloom-560m * Instruction tuning language: Spanish * Training method: full-parameter fine-tuning. * Best checkpoint: best cross-entropy on a validation set, trained for 3 epochs. * Dataset: machine-translated from yahma/alpaca-cleaned. You can download our data HERE. #### Usage The model checkpoint should be loaded using transformers library. Please refer to our Github repository HERE for inference and training instructions. #### Citation `` @inproceedings{chen-etal-2024-monolingual, title=\"Monolingual or multilingual instruction tuning: Which makes a better {Alpaca}\", author=\"Pinzhen Chen and Shaoxiong Ji and Nikolay Bogoychev and Andrey Kutuzov and Barry Haddow and Kenneth Heafield\", year=\"2024\", booktitle = \"Findings of the Association for Computational Linguistics: EACL 2024\", } ``",
    "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\nsft-fpft-es-bloom-560m - GGUF\n- Model creator: https://huggingface.co/HPLT/\n- Original model: https://huggingface.co/HPLT/sft-fpft-es-bloom-560m/\n\n\n| Name | Quant method | Size |\n| ---- | ---- | ---- |\n| [sft-fpft-es-bloom-560m.Q2_K.gguf](https://huggingface.co/RichardErkhov/HPLT_-_sft-fpft-es-bloom-560m-gguf/blob/main/sft-fpft-es-bloom-560m.Q2_K.gguf) | Q2_K | 0.39GB |\n| [sft-fpft-es-bloom-560m.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/HPLT_-_sft-fpft-es-bloom-560m-gguf/blob/main/sft-fpft-es-bloom-560m.IQ3_XS.gguf) | IQ3_XS | 0.43GB |\n| [sft-fpft-es-bloom-560m.IQ3_S.gguf](https://huggingface.co/RichardErkhov/HPLT_-_sft-fpft-es-bloom-560m-gguf/blob/main/sft-fpft-es-bloom-560m.IQ3_S.gguf) | IQ3_S | 0.43GB |\n| [sft-fpft-es-bloom-560m.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/HPLT_-_sft-fpft-es-bloom-560m-gguf/blob/main/sft-fpft-es-bloom-560m.Q3_K_S.gguf) | Q3_K_S | 0.43GB |\n| [sft-fpft-es-bloom-560m.IQ3_M.gguf](https://huggingface.co/RichardErkhov/HPLT_-_sft-fpft-es-bloom-560m-gguf/blob/main/sft-fpft-es-bloom-560m.IQ3_M.gguf) | IQ3_M | 0.45GB |\n| [sft-fpft-es-bloom-560m.Q3_K.gguf](https://huggingface.co/RichardErkhov/HPLT_-_sft-fpft-es-bloom-560m-gguf/blob/main/sft-fpft-es-bloom-560m.Q3_K.gguf) | Q3_K | 0.46GB |\n| [sft-fpft-es-bloom-560m.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/HPLT_-_sft-fpft-es-bloom-560m-gguf/blob/main/sft-fpft-es-bloom-560m.Q3_K_M.gguf) | Q3_K_M | 0.46GB |\n| [sft-fpft-es-bloom-560m.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/HPLT_-_sft-fpft-es-bloom-560m-gguf/blob/main/sft-fpft-es-bloom-560m.Q3_K_L.gguf) | Q3_K_L | 0.47GB |\n| [sft-fpft-es-bloom-560m.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/HPLT_-_sft-fpft-es-bloom-560m-gguf/blob/main/sft-fpft-es-bloom-560m.IQ4_XS.gguf) | IQ4_XS | 0.49GB |\n| [sft-fpft-es-bloom-560m.Q4_0.gguf](https://huggingface.co/RichardErkhov/HPLT_-_sft-fpft-es-bloom-560m-gguf/blob/main/sft-fpft-es-bloom-560m.Q4_0.gguf) | Q4_0 | 0.5GB |\n| [sft-fpft-es-bloom-560m.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/HPLT_-_sft-fpft-es-bloom-560m-gguf/blob/main/sft-fpft-es-bloom-560m.IQ4_NL.gguf) | IQ4_NL | 0.5GB |\n| [sft-fpft-es-bloom-560m.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/HPLT_-_sft-fpft-es-bloom-560m-gguf/blob/main/sft-fpft-es-bloom-560m.Q4_K_S.gguf) | Q4_K_S | 0.5GB |\n| [sft-fpft-es-bloom-560m.Q4_K.gguf](https://huggingface.co/RichardErkhov/HPLT_-_sft-fpft-es-bloom-560m-gguf/blob/main/sft-fpft-es-bloom-560m.Q4_K.gguf) | Q4_K | 0.52GB |\n| [sft-fpft-es-bloom-560m.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/HPLT_-_sft-fpft-es-bloom-560m-gguf/blob/main/sft-fpft-es-bloom-560m.Q4_K_M.gguf) | Q4_K_M | 0.52GB |\n| [sft-fpft-es-bloom-560m.Q4_1.gguf](https://huggingface.co/RichardErkhov/HPLT_-_sft-fpft-es-bloom-560m-gguf/blob/main/sft-fpft-es-bloom-560m.Q4_1.gguf) | Q4_1 | 0.53GB |\n| [sft-fpft-es-bloom-560m.Q5_0.gguf](https://huggingface.co/RichardErkhov/HPLT_-_sft-fpft-es-bloom-560m-gguf/blob/main/sft-fpft-es-bloom-560m.Q5_0.gguf) | Q5_0 | 0.57GB |\n| [sft-fpft-es-bloom-560m.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/HPLT_-_sft-fpft-es-bloom-560m-gguf/blob/main/sft-fpft-es-bloom-560m.Q5_K_S.gguf) | Q5_K_S | 0.57GB |\n| [sft-fpft-es-bloom-560m.Q5_K.gguf](https://huggingface.co/RichardErkhov/HPLT_-_sft-fpft-es-bloom-560m-gguf/blob/main/sft-fpft-es-bloom-560m.Q5_K.gguf) | Q5_K | 0.58GB |\n| [sft-fpft-es-bloom-560m.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/HPLT_-_sft-fpft-es-bloom-560m-gguf/blob/main/sft-fpft-es-bloom-560m.Q5_K_M.gguf) | Q5_K_M | 0.58GB |\n| [sft-fpft-es-bloom-560m.Q5_1.gguf](https://huggingface.co/RichardErkhov/HPLT_-_sft-fpft-es-bloom-560m-gguf/blob/main/sft-fpft-es-bloom-560m.Q5_1.gguf) | Q5_1 | 0.6GB |\n| [sft-fpft-es-bloom-560m.Q6_K.gguf](https://huggingface.co/RichardErkhov/HPLT_-_sft-fpft-es-bloom-560m-gguf/blob/main/sft-fpft-es-bloom-560m.Q6_K.gguf) | Q6_K | 0.64GB |\n| [sft-fpft-es-bloom-560m.Q8_0.gguf](https://huggingface.co/RichardErkhov/HPLT_-_sft-fpft-es-bloom-560m-gguf/blob/main/sft-fpft-es-bloom-560m.Q8_0.gguf) | Q8_0 | 0.82GB |\n\n\n\n\nOriginal model description:\n\n---\nlanguage:\n- es\ntags:\n- generation\n- question answering\n- instruction tuning\nlicense: cc-by-nc-4.0\n---\n\n###  Model Description\n\nThis HF repository contains base LLMs instruction tuned (SFT) with full-parameter fine-tuning and then used to study whether monolingual or multilingual instruction tuning is more favourable.\n* [GitHub](https://github.com/hplt-project/monolingual-multilingual-instruction-tuning/tree/main)\n* [Paper](https://arxiv.org/abs/2309.08958)\n\n#### Instruction tuning details\n* Base model: [bloom-560m](https://huggingface.co/bloom-560m)\n* Instruction tuning language: Spanish\n* Training method: full-parameter fine-tuning.\n* Best checkpoint: best cross-entropy on a validation set, trained for 3 epochs.\n* Dataset: machine-translated from [yahma/alpaca-cleaned](https://huggingface.co/datasets/yahma/alpaca-cleaned). You can download our data [HERE](https://github.com/hplt-project/monolingual-multilingual-instruction-tuning/tree/main/training-data).\n\n#### Usage\nThe model checkpoint should be loaded using `transformers` library.\n\nPlease refer to our Github repository [HERE](https://github.com/hplt-project/monolingual-multilingual-instruction-tuning/tree/main/fpft) for inference and training instructions.\n\n#### Citation\n```\n@inproceedings{chen-etal-2024-monolingual,\n  title=\"Monolingual or multilingual instruction tuning: Which makes a better {Alpaca}\",\n  author=\"Pinzhen Chen and Shaoxiong Ji and Nikolay Bogoychev and Andrey Kutuzov and Barry Haddow and Kenneth Heafield\",\n  year=\"2024\",\n  booktitle = \"Findings of the Association for Computational Linguistics: EACL 2024\",\n}\n```\n\n\n\n",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "arxiv:2309.08958",
    "endpoints_compatible",
    "region:us"
  ],
  "likes": 0,
  "downloads": 151,
  "gated": false,
  "private": false,
  "last_modified": "2025-02-22T12:18:49.000Z",
  "created_at": "2025-02-22T12:01:55.000Z",
  "pipeline_tag": "",
  "library_name": ""
}

{
  "_id": "67b9bcb33a36632ee1216647",
  "id": "RichardErkhov/HPLT_-_sft-fpft-es-bloom-560m-gguf",
  "modelId": "RichardErkhov/HPLT_-_sft-fpft-es-bloom-560m-gguf",
  "sha": "6697747c9840b653eb68e3eec5786a4a968d698c",
  "createdAt": "2025-02-22T12:01:55.000Z",
  "lastModified": "2025-02-22T12:18:49.000Z",
  "author": "RichardErkhov",
  "downloads": 151,
  "likes": 0,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "",
  "siblings_count": 24
}