richarderkhov/defog_-_llama-3-sqlcoder-8b-gguf overview

{
  "metadata": {},
  "card_data": {
    "frontmatter": {},
    "hero_image_url": "https://cdn-uploads.huggingface.co/production/uploads/603bbad3fd770a9997b57cb6/h52Z_OKYBaDDQMFZyU5pF.png",
    "summary": "Quantization made by Richard Erkhov. Github Discord Request more models llama-3-sqlcoder-8b - GGUF | Name | Quant method | Size | | ---- | ---- | ---- | | llama-3-sqlcoder-8b.Q2_K.gguf | Q2_K | 2.96GB | | llama-3-sqlcoder-8b.IQ3_XS.gguf | IQ3_XS | 3.28GB | | llama-3-sqlcoder-8b.IQ3_S.gguf | IQ3_S | 3.43GB | | llama-3-sqlcoder-8b.Q3_K_S.gguf | Q3_K_S | 3.41GB | | llama-3-sqlcoder-8b.IQ3_M.gguf | IQ3_M | 3.52GB | | llama-3-sqlcoder-8b.Q3_K.gguf | Q3_K | 3.74GB | | llama-3-sqlcoder-8b.Q3_K_M.gguf | Q3_K_M | 3.74GB | | llama-3-sqlcoder-8b.Q3_K_L.gguf | Q3_K_L | 4.03GB | | llama-3-sqlcoder-8b.IQ4_XS.gguf | IQ4_XS | 4.18GB | | llama-3-sqlcoder-8b.Q4_0.gguf | Q4_0 | 4.34GB | | llama-3-sqlcoder-8b.IQ4_NL.gguf | IQ4_NL | 4.38GB | | llama-3-sqlcoder-8b.Q4_K_S.gguf | Q4_K_S | 4.37GB | | llama-3-sqlcoder-8b.Q4_K.gguf | Q4_K | 4.58GB | | llama-3-sqlcoder-8b.Q4_K_M.gguf | Q4_K_M | 4.58GB | | llama-3-sqlcoder-8b.Q4_1.gguf | Q4_1 | 4.78GB | | llama-3-sqlcoder-8b.Q5_0.gguf | Q5_0 | 5.21GB | | llama-3-sqlcoder-8b.Q5_K_S.gguf | Q5_K_S | 5.21GB | | llama-3-sqlcoder-8b.Q5_K.gguf | Q5_K | 5.34GB | | llama-3-sqlcoder-8b.Q5_K_M.gguf | Q5_K_M | 5.34GB | | llama-3-sqlcoder-8b.Q5_1.gguf | Q5_1 | 5.65GB | | llama-3-sqlcoder-8b.Q6_K.gguf | Q6_K | 6.14GB | | llama-3-sqlcoder-8b.Q8_0.gguf | Q8_0 | 7.95GB | Original model description: --- license: cc-by-sa-4.0 metrics: pipeline_tag: text-generation tags: --- A capable language model for text to SQL generation for Postgres, Redshift and Snowflake that is on-par with the most capable generalist frontier models. !image/png",
    "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\nllama-3-sqlcoder-8b - GGUF\n- Model creator: https://huggingface.co/defog/\n- Original model: https://huggingface.co/defog/llama-3-sqlcoder-8b/\n\n\n| Name | Quant method | Size |\n| ---- | ---- | ---- |\n| [llama-3-sqlcoder-8b.Q2_K.gguf](https://huggingface.co/RichardErkhov/defog_-_llama-3-sqlcoder-8b-gguf/blob/main/llama-3-sqlcoder-8b.Q2_K.gguf) | Q2_K | 2.96GB |\n| [llama-3-sqlcoder-8b.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/defog_-_llama-3-sqlcoder-8b-gguf/blob/main/llama-3-sqlcoder-8b.IQ3_XS.gguf) | IQ3_XS | 3.28GB |\n| [llama-3-sqlcoder-8b.IQ3_S.gguf](https://huggingface.co/RichardErkhov/defog_-_llama-3-sqlcoder-8b-gguf/blob/main/llama-3-sqlcoder-8b.IQ3_S.gguf) | IQ3_S | 3.43GB |\n| [llama-3-sqlcoder-8b.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/defog_-_llama-3-sqlcoder-8b-gguf/blob/main/llama-3-sqlcoder-8b.Q3_K_S.gguf) | Q3_K_S | 3.41GB |\n| [llama-3-sqlcoder-8b.IQ3_M.gguf](https://huggingface.co/RichardErkhov/defog_-_llama-3-sqlcoder-8b-gguf/blob/main/llama-3-sqlcoder-8b.IQ3_M.gguf) | IQ3_M | 3.52GB |\n| [llama-3-sqlcoder-8b.Q3_K.gguf](https://huggingface.co/RichardErkhov/defog_-_llama-3-sqlcoder-8b-gguf/blob/main/llama-3-sqlcoder-8b.Q3_K.gguf) | Q3_K | 3.74GB |\n| [llama-3-sqlcoder-8b.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/defog_-_llama-3-sqlcoder-8b-gguf/blob/main/llama-3-sqlcoder-8b.Q3_K_M.gguf) | Q3_K_M | 3.74GB |\n| [llama-3-sqlcoder-8b.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/defog_-_llama-3-sqlcoder-8b-gguf/blob/main/llama-3-sqlcoder-8b.Q3_K_L.gguf) | Q3_K_L | 4.03GB |\n| [llama-3-sqlcoder-8b.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/defog_-_llama-3-sqlcoder-8b-gguf/blob/main/llama-3-sqlcoder-8b.IQ4_XS.gguf) | IQ4_XS | 4.18GB |\n| [llama-3-sqlcoder-8b.Q4_0.gguf](https://huggingface.co/RichardErkhov/defog_-_llama-3-sqlcoder-8b-gguf/blob/main/llama-3-sqlcoder-8b.Q4_0.gguf) | Q4_0 | 4.34GB |\n| [llama-3-sqlcoder-8b.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/defog_-_llama-3-sqlcoder-8b-gguf/blob/main/llama-3-sqlcoder-8b.IQ4_NL.gguf) | IQ4_NL | 4.38GB |\n| [llama-3-sqlcoder-8b.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/defog_-_llama-3-sqlcoder-8b-gguf/blob/main/llama-3-sqlcoder-8b.Q4_K_S.gguf) | Q4_K_S | 4.37GB |\n| [llama-3-sqlcoder-8b.Q4_K.gguf](https://huggingface.co/RichardErkhov/defog_-_llama-3-sqlcoder-8b-gguf/blob/main/llama-3-sqlcoder-8b.Q4_K.gguf) | Q4_K | 4.58GB |\n| [llama-3-sqlcoder-8b.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/defog_-_llama-3-sqlcoder-8b-gguf/blob/main/llama-3-sqlcoder-8b.Q4_K_M.gguf) | Q4_K_M | 4.58GB |\n| [llama-3-sqlcoder-8b.Q4_1.gguf](https://huggingface.co/RichardErkhov/defog_-_llama-3-sqlcoder-8b-gguf/blob/main/llama-3-sqlcoder-8b.Q4_1.gguf) | Q4_1 | 4.78GB |\n| [llama-3-sqlcoder-8b.Q5_0.gguf](https://huggingface.co/RichardErkhov/defog_-_llama-3-sqlcoder-8b-gguf/blob/main/llama-3-sqlcoder-8b.Q5_0.gguf) | Q5_0 | 5.21GB |\n| [llama-3-sqlcoder-8b.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/defog_-_llama-3-sqlcoder-8b-gguf/blob/main/llama-3-sqlcoder-8b.Q5_K_S.gguf) | Q5_K_S | 5.21GB |\n| [llama-3-sqlcoder-8b.Q5_K.gguf](https://huggingface.co/RichardErkhov/defog_-_llama-3-sqlcoder-8b-gguf/blob/main/llama-3-sqlcoder-8b.Q5_K.gguf) | Q5_K | 5.34GB |\n| [llama-3-sqlcoder-8b.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/defog_-_llama-3-sqlcoder-8b-gguf/blob/main/llama-3-sqlcoder-8b.Q5_K_M.gguf) | Q5_K_M | 5.34GB |\n| [llama-3-sqlcoder-8b.Q5_1.gguf](https://huggingface.co/RichardErkhov/defog_-_llama-3-sqlcoder-8b-gguf/blob/main/llama-3-sqlcoder-8b.Q5_1.gguf) | Q5_1 | 5.65GB |\n| [llama-3-sqlcoder-8b.Q6_K.gguf](https://huggingface.co/RichardErkhov/defog_-_llama-3-sqlcoder-8b-gguf/blob/main/llama-3-sqlcoder-8b.Q6_K.gguf) | Q6_K | 6.14GB |\n| [llama-3-sqlcoder-8b.Q8_0.gguf](https://huggingface.co/RichardErkhov/defog_-_llama-3-sqlcoder-8b-gguf/blob/main/llama-3-sqlcoder-8b.Q8_0.gguf) | Q8_0 | 7.95GB |\n\n\n\n\nOriginal model description:\n---\nlicense: cc-by-sa-4.0\nmetrics:\n- accuracy\npipeline_tag: text-generation\ntags:\n- code\n---\n\nA capable language model for text to SQL generation for Postgres, Redshift and Snowflake that is on-par with the most capable generalist frontier models.\n\n![image/png](https://cdn-uploads.huggingface.co/production/uploads/603bbad3fd770a9997b57cb6/h52Z_OKYBaDDQMFZyU5pF.png)\n\n## Model Description\n\nDeveloped by: Defog, Inc\nModel type: [Text to SQL]\nLicense: [CC-by-SA-4.0]\nFinetuned from model: [Meta-Llama-3-8B-Instruct]\n\n## Demo Page\n[https://defog.ai/sqlcoder-demo/](https://defog.ai/sqlcoder-demo/)\n\n## Ideal prompt and inference parameters\nSet temperature to 0, and do not do sampling.\n\n### Prompt\n```\n<|begin_of_text|><|start_header_id|>user<|end_header_id|>\n\nGenerate a SQL query to answer this question: `{user_question}`\n{instructions}\n\nDDL statements:\n{create_table_statements}<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\nThe following SQL query best answers the question `{user_question}`:\n```sql\n\n```\n\n## Evaluation\nThis model was evaluated on SQL-Eval, a PostgreSQL based evaluation framework developed by Defog for testing and alignment of model capabilities.\n\nYou can read more about the methodology behind SQLEval [here](https://defog.ai/blog/open-sourcing-sqleval/).\n\n## Contact\nContact us on X at [@defogdata](https://twitter.com/defogdata), or on email at founders@defog.ai\n\n",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "endpoints_compatible",
    "region:us",
    "conversational"
  ],
  "likes": 0,
  "downloads": 251,
  "gated": false,
  "private": false,
  "last_modified": "2024-06-14T19:21:33.000Z",
  "created_at": "2024-06-14T18:49:35.000Z",
  "pipeline_tag": "",
  "library_name": ""
}

{
  "_id": "666c90bf3b570f44d7f69369",
  "id": "RichardErkhov/defog_-_llama-3-sqlcoder-8b-gguf",
  "modelId": "RichardErkhov/defog_-_llama-3-sqlcoder-8b-gguf",
  "sha": "6735e418c74a1e7fb4b41d70606dc97e43dd8c8f",
  "createdAt": "2024-06-14T18:49:35.000Z",
  "lastModified": "2024-06-14T19:21:33.000Z",
  "author": "RichardErkhov",
  "downloads": 251,
  "likes": 0,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "",
  "siblings_count": 24
}