Flint
A 30B model fine-tuned for less repetition. As frontier LLMs have very little output diversity even for open ended queries.
Reactions (1)
Similar products
by description similarity
Improve Text-to-SQL Accuracy with LLM
github.comA repository that contains models, datasets, and fine-tuning techniques for DB-GPT, with the purpose of enhancing model performance in Text-to-SQL
Crespo
github.comTree-sitter AST blueprints instead of raw code for LLMs
Metarank
demo.metarank.aiopen-source hybrid search with LLMs
LLM fine-tuning without infra or ML expertise
tinytune.xyzPrela
prela-lang.orgA Compositional and Controllable Query Language