初始化项目,由ModelHub XC社区提供模型

Model: danielpedrozo/sql-zero-3b-gold-control
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-09-11 05:25:16 +08:00
commit 6e5395ac63
13 changed files with 152193 additions and 0 deletions

12
README.md Normal file
View File

@@ -0,0 +1,12 @@
---
license: apache-2.0
base_model: Qwen/Qwen2.5-Coder-3B-Instruct
tags: [text-to-sql, self-play, grpo, sql-zero]
---
# sql-zero-3b-gold-control
Controle: mesmo GRPO nos 8.659 pares humanos do Spider train. Spider 0.731, BIRD 0.357, Syn 0.622.
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).