metadata
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