metadata
license: mit
datasets:
- nvidia/OpenCodeReasoning
- nvidia/OpenMathReasoning
- nvidia/Llama-Nemotron-Post-Training-Dataset
language:
- fr
metrics:
- bleu
base_model:
- meta-llama/Llama-4-Scout-17B-16E-Instruct
- deepseek-ai/DeepSeek-V3-0324
- Qwen/Qwen2.5-Omni-7B
- agentica-org/DeepCoder-14B-Preview
new_version: deepseek-ai/DeepSeek-Prover-V2-671B
pipeline_tag: reinforcement-learning
library_name: adapter-transformers
tags:
- not-for-all-audiences
- chemistry
- biology
- music
- climate
- medical
- text-generation-inference
- merge