| license: apache-2.0 | |
| datasets: | |
| - fka/awesome-chatgpt-prompts | |
| - HumanLLMs/Human-Like-DPO-Dataset | |
| - cognitivecomputations/dolphin-r1 | |
| - DAMO-NLP-SG/multimodal_textbook | |
| language: | |
| - en | |
| - hi | |
| metrics: | |
| - accuracy | |
| - Aye10032/loss_metric | |
| base_model: | |
| - microsoft/phi-4 | |
| - deepseek-ai/DeepSeek-R1 | |
| - meta-llama/Llama-2-7b-chat-hf | |
| new_version: deepseek-ai/DeepSeek-R1 | |
| pipeline_tag: reinforcement-learning | |
| library_name: adapter-transformers | |
| tags: | |
| - legal | |