---
datasets:
- seyyedaliayati/solidity-dataset
- Royal-lobster/Slither-Audited-Solidity-QA
- braindao/solidity-base
- Quangnguyen711/solidity_re_entrancy_dataset
- braindao/solidity-bettergpt-base-v2-preference-enriched
- braindao/solidity-bettergpt-base-v2-preference
- nguyenminh871/reentrancy_solidity_function
- braindao/solidity-bettergpt-base-v2-prompts
- msc-smart-contract-auditing/audits-with-reasons
- andstor/smart_contracts
- AlfredPros/smart-contracts-instructions
- braindao/smart-contracts-instructions-cleaned
- jainabh/smart_contracts_malicious
- Ruschio/smart-contracts-source
- nitt/smartcontracts
- nayankur/paired-smart-contracts
- fasdfasdffasdfas/verified_smart_contracts
language:
- en
metrics:
- accuracy
- code_eval
base_model:
- deepseek-ai/DeepSeek-R1-Zero
- deepseek-ai/DeepSeek-R1
- deepseek-ai/Janus-Pro-7B
new_version: deepseek-ai/DeepSeek-R1-Distill-Llama-8B
pipeline_tag: reinforcement-learning
---