QuantFactory/llama-3-sqlcoder-8b-GGUF
141.6k
1---2license: cc-by-sa-4.03metrics:4- accuracy5pipeline_tag: text-generation6tags:7- code8base_model: defog/llama-3-sqlcoder-8b9---10 11# QuantFactory/llama-3-sqlcoder-8b-GGUF12This is quantized version of [defog/llama-3-sqlcoder-8b](https://huggingface.co/defog/llama-3-sqlcoder-8b) created using llama.cpp13 14## Model Description15 16A capable language model for text to SQL generation for Postgres, Redshift and Snowflake that is on-par with the most capable generalist frontier models.17 1819 20 21Developed by: Defog, Inc22Model type: [Text to SQL]23License: [CC-by-SA-4.0]24Finetuned from model: [Meta-Llama-3-8B-Instruct]25 26## Demo Page27[https://defog.ai/sqlcoder-demo/](https://defog.ai/sqlcoder-demo/)28 29## Ideal prompt and inference parameters30Set temperature to 0, and do not do sampling.31 32### Prompt33```34<|begin_of_text|><|start_header_id|>user<|end_header_id|>35 36Generate a SQL query to answer this question: `{user_question}`37{instructions}38 39DDL statements:40{create_table_statements}<|eot_id|><|start_header_id|>assistant<|end_header_id|>41 42The following SQL query best answers the question `{user_question}`:43```sql44 45```46 47## Evaluation48This model was evaluated on SQL-Eval, a PostgreSQL based evaluation framework developed by Defog for testing and alignment of model capabilities.49 50You can read more about the methodology behind SQLEval [here](https://defog.ai/blog/open-sourcing-sqleval/).51 52## Contact defog53Contact defog on X at [@defogdata](https://twitter.com/defogdata), or on email at founders@defog.ai