llmsql-bench/llmsql-benchmark-lm-evaluation-harness
Viewer
•
Updated
•
80.3k
•
116
AI & ML interests
None defined yet.
Recent Activity
View all activity
Organization Card
LLMSQL Organization on Hugging Face
Description:
For now we provide patched and improved version of WikiSQL for Text-to-SQL tasks.
Provides datasets and tools for inference, evaluation, and fine-tuning of LLMs.
Highlights:
- Full benchmark: questions, tables, train/val/test splits (llmsql-bench/llmsql-benchmark)
- Ready-to-use evaluation scripts (https://github.com/LLMSQL/llmsql-benchmark)
- Compatible with Hugging Face causal LMs
- Tools for finetuning via
trl.SFTTrainer
Follow us:
models
0
None public yet