--- license: mit tags: - trl - sft - text-generation-inference language: - en base_model: - meta-llama/Llama-3.2-3B-Instruct - deepseek-ai/DeepSeek-V3 - NousResearch/Hermes-3-Llama-3.2-3B metrics: - rouge - bleu - brier_score library_name: transformers ---