diff --git a/README.md b/README.md index be1fadd0c..84d468e19 100644 --- a/README.md +++ b/README.md @@ -434,6 +434,7 @@ You also can add a custom chat template to [template.py](src/llamafactory/data/t - [Chinese-DeepSeek-R1-Distill (zh)](https://huggingface.co/datasets/Congliu/Chinese-DeepSeek-R1-Distill-data-110k-SFT) - [LLaVA mixed (en&zh)](https://huggingface.co/datasets/BUAADreamer/llava-en-zh-300k) - [Pokemon-gpt4o-captions (en&zh)](https://huggingface.co/datasets/jugg1024/pokemon-gpt4o-captions) +- [DLR-Web (en)](https://huggingface.co/datasets/Attention1115/DLR-Web) - [Open Assistant (de)](https://huggingface.co/datasets/mayflowergmbh/oasst_de) - [Dolly 15k (de)](https://huggingface.co/datasets/mayflowergmbh/dolly-15k_de) - [Alpaca GPT4 (de)](https://huggingface.co/datasets/mayflowergmbh/alpaca-gpt4_de) diff --git a/README_zh.md b/README_zh.md index ed42041d1..3af79201c 100644 --- a/README_zh.md +++ b/README_zh.md @@ -436,6 +436,7 @@ https://github.com/user-attachments/assets/43b700c6-a178-41db-b1f8-8190a5d3fcfc - [Chinese-DeepSeek-R1-Distill (zh)](https://huggingface.co/datasets/Congliu/Chinese-DeepSeek-R1-Distill-data-110k-SFT) - [LLaVA mixed (en&zh)](https://huggingface.co/datasets/BUAADreamer/llava-en-zh-300k) - [Pokemon-gpt4o-captions (en&zh)](https://huggingface.co/datasets/jugg1024/pokemon-gpt4o-captions) +- [DLR-Web (en)](https://huggingface.co/datasets/Attention1115/DLR-Web) - [Open Assistant (de)](https://huggingface.co/datasets/mayflowergmbh/oasst_de) - [Dolly 15k (de)](https://huggingface.co/datasets/mayflowergmbh/dolly-15k_de) - [Alpaca GPT4 (de)](https://huggingface.co/datasets/mayflowergmbh/alpaca-gpt4_de) diff --git a/data/dataset_info.json b/data/dataset_info.json index 3615952cd..4a823133b 100644 --- a/data/dataset_info.json +++ b/data/dataset_info.json @@ -471,6 +471,14 @@ "ultrachat_de": { "hf_hub_url": "mayflowergmbh/ultra-chat_de" }, + "dlr_web": { + "hf_hub_url": "Attention1115/DLR-Web", + "split": "full", + "columns": { + "prompt": "question", + "response": "response" + } + }, "dpo_en_demo": { "file_name": "dpo_en_demo.json", "ranking": true,