ReViSQL-Qwen3-4B

ReViSQL-Qwen3-4B

LoRA adapter trained directly from Qwen/Qwen3-4B-Instruct-2507 with RLVR on expert-verified BIRD-Platinum data. This is the validation-selected step 1,300 adapter from the bird-text2sql-rl project.

Results

Greedy uses temperature 0. SC-16 samples 16 candidates at temperature 1 and selects the majority execution result. The model is evaluated as a SQL agent with up to five rounds of read-only database interaction; see the source repository for the exact prompt, environment, and evaluation contract.

Loading the adapter

from peft import PeftModel
from transformers import AutoModelForCausalLM, AutoTokenizer

base_model_id = "Qwen/Qwen3-4B-Instruct-2507"
adapter_id = "ximosss/ReViSQL-Qwen3-4B"

tokenizer = AutoTokenizer.from_pretrained(base_model_id)
base_model = AutoModelForCausalLM.from_pretrained(
    base_model_id,
    torch_dtype="auto",
    device_map="auto",
)
model = PeftModel.from_pretrained(base_model, adapter_id)

The adapter alone does not reproduce the benchmark protocol. Use the database tool environment and prompts in the source repository for evaluation.

Training details

• Objective: CISPO with execution, VeriEQL, and evidence-process rewards
• LoRA: rank 32, alpha 64; attention and MLP linear layers
• Learning rate: 1e-5
• Rollout temperature: 0.8
• Training batch / group size: 64 / 16

References

• Yuxuan Zhu, Tengjun Jin, Yoojin Choi, and Daniel Kang. 2026. Human-Level Text-to-SQL via Reinforcement Learning on Verified Data, Without Pipeline Engineering.
• Yuxuan Zhu, Tengjun Jin, Yoojin Choi, and Daniel Kang. 2026. Putting Task Expertise into RL Achieves State-of-the-Art Performance on Text-to-SQL.