sql-zero-3b-solver-iter2-s100

Solver 3B iter2 c/ repetition penalty, checkpoint canonico (best-dev s100/139). Spider 0.728, BIRD 0.376.

Parte do projeto SQL-Zero (self-play zero-anotacao para Text-to-SQL, adaptacao do Dr. Zero). Protocolo de avaliacao: greedy@1, schema completo (DDL+3 rows), execution accuracy. Treinado com verl (GRPO); reward de execucao 3-tier (1.0/0.1/0.0).

Downloads last month
47
Safetensors
Model size
3B params
Tensor type
BF16
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for danielpedrozo/sql-zero-3b-solver-iter2

Base model

Qwen/Qwen2.5-3B
Finetuned
(129)
this model