Hugging Face's logo

ai2sql
/
ai2sql_mistral_7b

Text Generation
PEFT
Safetensors
English
mistral-7b
lora
Model card Files Community
1
ai2sql_mistral_7b / README.md
mergisi's picture
mergisi
Update README.md
ee30513
preview code
|
raw
history blame
1.78 kB
metadata
library_name: peft
base_model: mistralai/Mistral-7B-v0.1
pipeline_tag: text-generation
datasets:
  - wikisql
language:
  - en
tags:
  - mistral-7b
  - lora

AI2sql

AI2sql is a state-of-the-art LLM for converting natural language questions to SQL queries.

Model Details

Model Description

This model card presents the finetuning of the Mistral-7b model using the PEFT library and bitsandbytes for loading large models in 4-bit. The notebook demonstrates finetuning with Low Rank Adapters (LoRA), allowing only the adapters to be finetuned instead of the entire model. This specialized model offers a powerful tool for database querying and analysis, streamlining the process of extracting information from databases using conversational inputs.

  • Developed by: [More Information Needed]
  • Funded by [optional]: [More Information Needed]
  • Shared by [optional]: [More Information Needed]
  • Model type: [More Information Needed]
  • Language(s) (NLP): [More Information Needed]
  • License: [More Information Needed]
  • Finetuned from model [optional]: [More Information Needed]

Model Sources [optional]

  • Repository: [More Information Needed]
  • Paper [optional]: [More Information Needed]
  • Demo [optional]: [More Information Needed]

Training procedure

The following bitsandbytes quantization config was used during training:

  • quant_method: bitsandbytes
  • load_in_8bit: False
  • load_in_4bit: True
  • llm_int8_threshold: 6.0
  • llm_int8_skip_modules: None
  • llm_int8_enable_fp32_cpu_offload: False
  • llm_int8_has_fp16_weight: False
  • bnb_4bit_quant_type: nf4
  • bnb_4bit_use_double_quant: True
  • bnb_4bit_compute_dtype: bfloat16

Framework versions

  • PEFT 0.6.3.dev0