richarderkhov/4yo1_-_llama3-eng-ko-8b-sl3-gguf overview

{
  "metadata": {},
  "card_data": {
    "frontmatter": {},
    "hero_image_url": "",
    "summary": "Quantization made by Richard Erkhov. Github Discord Request more models llama3-eng-ko-8b-sl3 - GGUF | Name | Quant method | Size | | ---- | ---- | ---- | | llama3-eng-ko-8b-sl3.Q2_K.gguf | Q2_K | 2.96GB | | llama3-eng-ko-8b-sl3.IQ3_XS.gguf | IQ3_XS | 3.28GB | | llama3-eng-ko-8b-sl3.IQ3_S.gguf | IQ3_S | 3.43GB | | llama3-eng-ko-8b-sl3.Q3_K_S.gguf | Q3_K_S | 3.41GB | | llama3-eng-ko-8b-sl3.IQ3_M.gguf | IQ3_M | 3.52GB | | llama3-eng-ko-8b-sl3.Q3_K.gguf | Q3_K | 3.74GB | | llama3-eng-ko-8b-sl3.Q3_K_M.gguf | Q3_K_M | 3.74GB | | llama3-eng-ko-8b-sl3.Q3_K_L.gguf | Q3_K_L | 4.03GB | | llama3-eng-ko-8b-sl3.IQ4_XS.gguf | IQ4_XS | 4.18GB | | llama3-eng-ko-8b-sl3.Q4_0.gguf | Q4_0 | 4.34GB | | llama3-eng-ko-8b-sl3.IQ4_NL.gguf | IQ4_NL | 4.38GB | | llama3-eng-ko-8b-sl3.Q4_K_S.gguf | Q4_K_S | 4.37GB | | llama3-eng-ko-8b-sl3.Q4_K.gguf | Q4_K | 4.58GB | | llama3-eng-ko-8b-sl3.Q4_K_M.gguf | Q4_K_M | 4.58GB | | llama3-eng-ko-8b-sl3.Q4_1.gguf | Q4_1 | 4.78GB | | llama3-eng-ko-8b-sl3.Q5_0.gguf | Q5_0 | 5.21GB | | llama3-eng-ko-8b-sl3.Q5_K_S.gguf | Q5_K_S | 5.21GB | | llama3-eng-ko-8b-sl3.Q5_K.gguf | Q5_K | 5.34GB | | llama3-eng-ko-8b-sl3.Q5_K_M.gguf | Q5_K_M | 5.34GB | | llama3-eng-ko-8b-sl3.Q5_1.gguf | Q5_1 | 5.65GB | | llama3-eng-ko-8b-sl3.Q6_K.gguf | Q6_K | 6.14GB | | llama3-eng-ko-8b-sl3.Q8_0.gguf | Q8_0 | 7.95GB | Original model description: --- library_name: transformers language: pipeline_tag: translation tags: license: mit datasets: --- ### Model Card for Model ID ### Model Details Model Card: LLaMA3-ENG-KO-8B-SL3 with Fine-Tuning Model Overview Model Name: LLaMA3-ENG-KO-8B-SL3 Model Type: Transformer-based Language Model Model Size: 8 billion parameters by: 4yo1 Languages: English and Korean ### Model Description LLaMA3-ENG-KO-8B-SL3 is a language model pre-trained on a diverse corpus of English and Korean texts. This fine-tuning approach allows the model to adapt to specific tasks or datasets with a minimal number of additional parameters, making it efficient and effective for specialized applications. ### how to use - sample code ``python from transformers import AutoConfig, AutoModel, AutoTokenizer config = AutoConfig.from_pretrained(\"4yo1/llama3-eng-ko-80-sl3\") model = AutoModel.from_pretrained(\"4yo1/llama3-eng-ko-8b-sl3\") tokenizer = AutoTokenizer.from_pretrained(\"4yo1/llama3-eng-ko-8b-sl3\") `` datasets: license: mit",
    "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\nllama3-eng-ko-8b-sl3 - GGUF\n- Model creator: https://huggingface.co/4yo1/\n- Original model: https://huggingface.co/4yo1/llama3-eng-ko-8b-sl3/\n\n\n| Name | Quant method | Size |\n| ---- | ---- | ---- |\n| [llama3-eng-ko-8b-sl3.Q2_K.gguf](https://huggingface.co/RichardErkhov/4yo1_-_llama3-eng-ko-8b-sl3-gguf/blob/main/llama3-eng-ko-8b-sl3.Q2_K.gguf) | Q2_K | 2.96GB |\n| [llama3-eng-ko-8b-sl3.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/4yo1_-_llama3-eng-ko-8b-sl3-gguf/blob/main/llama3-eng-ko-8b-sl3.IQ3_XS.gguf) | IQ3_XS | 3.28GB |\n| [llama3-eng-ko-8b-sl3.IQ3_S.gguf](https://huggingface.co/RichardErkhov/4yo1_-_llama3-eng-ko-8b-sl3-gguf/blob/main/llama3-eng-ko-8b-sl3.IQ3_S.gguf) | IQ3_S | 3.43GB |\n| [llama3-eng-ko-8b-sl3.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/4yo1_-_llama3-eng-ko-8b-sl3-gguf/blob/main/llama3-eng-ko-8b-sl3.Q3_K_S.gguf) | Q3_K_S | 3.41GB |\n| [llama3-eng-ko-8b-sl3.IQ3_M.gguf](https://huggingface.co/RichardErkhov/4yo1_-_llama3-eng-ko-8b-sl3-gguf/blob/main/llama3-eng-ko-8b-sl3.IQ3_M.gguf) | IQ3_M | 3.52GB |\n| [llama3-eng-ko-8b-sl3.Q3_K.gguf](https://huggingface.co/RichardErkhov/4yo1_-_llama3-eng-ko-8b-sl3-gguf/blob/main/llama3-eng-ko-8b-sl3.Q3_K.gguf) | Q3_K | 3.74GB |\n| [llama3-eng-ko-8b-sl3.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/4yo1_-_llama3-eng-ko-8b-sl3-gguf/blob/main/llama3-eng-ko-8b-sl3.Q3_K_M.gguf) | Q3_K_M | 3.74GB |\n| [llama3-eng-ko-8b-sl3.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/4yo1_-_llama3-eng-ko-8b-sl3-gguf/blob/main/llama3-eng-ko-8b-sl3.Q3_K_L.gguf) | Q3_K_L | 4.03GB |\n| [llama3-eng-ko-8b-sl3.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/4yo1_-_llama3-eng-ko-8b-sl3-gguf/blob/main/llama3-eng-ko-8b-sl3.IQ4_XS.gguf) | IQ4_XS | 4.18GB |\n| [llama3-eng-ko-8b-sl3.Q4_0.gguf](https://huggingface.co/RichardErkhov/4yo1_-_llama3-eng-ko-8b-sl3-gguf/blob/main/llama3-eng-ko-8b-sl3.Q4_0.gguf) | Q4_0 | 4.34GB |\n| [llama3-eng-ko-8b-sl3.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/4yo1_-_llama3-eng-ko-8b-sl3-gguf/blob/main/llama3-eng-ko-8b-sl3.IQ4_NL.gguf) | IQ4_NL | 4.38GB |\n| [llama3-eng-ko-8b-sl3.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/4yo1_-_llama3-eng-ko-8b-sl3-gguf/blob/main/llama3-eng-ko-8b-sl3.Q4_K_S.gguf) | Q4_K_S | 4.37GB |\n| [llama3-eng-ko-8b-sl3.Q4_K.gguf](https://huggingface.co/RichardErkhov/4yo1_-_llama3-eng-ko-8b-sl3-gguf/blob/main/llama3-eng-ko-8b-sl3.Q4_K.gguf) | Q4_K | 4.58GB |\n| [llama3-eng-ko-8b-sl3.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/4yo1_-_llama3-eng-ko-8b-sl3-gguf/blob/main/llama3-eng-ko-8b-sl3.Q4_K_M.gguf) | Q4_K_M | 4.58GB |\n| [llama3-eng-ko-8b-sl3.Q4_1.gguf](https://huggingface.co/RichardErkhov/4yo1_-_llama3-eng-ko-8b-sl3-gguf/blob/main/llama3-eng-ko-8b-sl3.Q4_1.gguf) | Q4_1 | 4.78GB |\n| [llama3-eng-ko-8b-sl3.Q5_0.gguf](https://huggingface.co/RichardErkhov/4yo1_-_llama3-eng-ko-8b-sl3-gguf/blob/main/llama3-eng-ko-8b-sl3.Q5_0.gguf) | Q5_0 | 5.21GB |\n| [llama3-eng-ko-8b-sl3.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/4yo1_-_llama3-eng-ko-8b-sl3-gguf/blob/main/llama3-eng-ko-8b-sl3.Q5_K_S.gguf) | Q5_K_S | 5.21GB |\n| [llama3-eng-ko-8b-sl3.Q5_K.gguf](https://huggingface.co/RichardErkhov/4yo1_-_llama3-eng-ko-8b-sl3-gguf/blob/main/llama3-eng-ko-8b-sl3.Q5_K.gguf) | Q5_K | 5.34GB |\n| [llama3-eng-ko-8b-sl3.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/4yo1_-_llama3-eng-ko-8b-sl3-gguf/blob/main/llama3-eng-ko-8b-sl3.Q5_K_M.gguf) | Q5_K_M | 5.34GB |\n| [llama3-eng-ko-8b-sl3.Q5_1.gguf](https://huggingface.co/RichardErkhov/4yo1_-_llama3-eng-ko-8b-sl3-gguf/blob/main/llama3-eng-ko-8b-sl3.Q5_1.gguf) | Q5_1 | 5.65GB |\n| [llama3-eng-ko-8b-sl3.Q6_K.gguf](https://huggingface.co/RichardErkhov/4yo1_-_llama3-eng-ko-8b-sl3-gguf/blob/main/llama3-eng-ko-8b-sl3.Q6_K.gguf) | Q6_K | 6.14GB |\n| [llama3-eng-ko-8b-sl3.Q8_0.gguf](https://huggingface.co/RichardErkhov/4yo1_-_llama3-eng-ko-8b-sl3-gguf/blob/main/llama3-eng-ko-8b-sl3.Q8_0.gguf) | Q8_0 | 7.95GB |\n\n\n\n\nOriginal model description:\n---\nlibrary_name: transformers\nlanguage:\n- en\n- ko\npipeline_tag: translation\ntags:\n- llama-3-ko\nlicense: mit\ndatasets:\n- 4yo1/llama3_test1\n---\n\n### Model Card for Model ID\n### Model Details\n\nModel Card: LLaMA3-ENG-KO-8B-SL3 with Fine-Tuning\nModel Overview\nModel Name: LLaMA3-ENG-KO-8B-SL3\n\nModel Type: Transformer-based Language Model\n\nModel Size: 8 billion parameters\n\nby: 4yo1\n\nLanguages: English and Korean\n\n### Model Description\nLLaMA3-ENG-KO-8B-SL3 is a language model pre-trained on a diverse corpus of English and Korean texts.\nThis fine-tuning approach allows the model to adapt to specific tasks or datasets with a minimal number of additional parameters, making it efficient and effective for specialized applications.\n\n### how to use - sample code\n\n```python\nfrom transformers import AutoConfig, AutoModel, AutoTokenizer\n\nconfig = AutoConfig.from_pretrained(\"4yo1/llama3-eng-ko-80-sl3\")\nmodel = AutoModel.from_pretrained(\"4yo1/llama3-eng-ko-8b-sl3\")\ntokenizer = AutoTokenizer.from_pretrained(\"4yo1/llama3-eng-ko-8b-sl3\")\n```\ndatasets:\n- 4yo1/llama3_test1\n  \nlicense: mit\n\n",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "endpoints_compatible",
    "region:us",
    "conversational"
  ],
  "likes": 0,
  "downloads": 183,
  "gated": false,
  "private": false,
  "last_modified": "2024-08-22T18:11:19.000Z",
  "created_at": "2024-08-22T16:19:20.000Z",
  "pipeline_tag": "",
  "library_name": ""
}

{
  "_id": "66c76508c2c99f2d04665658",
  "id": "RichardErkhov/4yo1_-_llama3-eng-ko-8b-sl3-gguf",
  "modelId": "RichardErkhov/4yo1_-_llama3-eng-ko-8b-sl3-gguf",
  "sha": "3486b6ea6697d9baa4270ad338263a0acd07e9f9",
  "createdAt": "2024-08-22T16:19:20.000Z",
  "lastModified": "2024-08-22T18:11:19.000Z",
  "author": "RichardErkhov",
  "downloads": 183,
  "likes": 0,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "",
  "siblings_count": 24
}