add magpie ultra dataset

This commit is contained in:
hiyouga 2024-08-09 20:28:55 +08:00
parent dc770efb14
commit c75b5b83c4
3 changed files with 9 additions and 0 deletions

View File

@ -265,6 +265,7 @@ You also can add a custom chat template to [template.py](src/llamafactory/data/t
- [Neo-sft (zh)](https://huggingface.co/datasets/m-a-p/neo_sft_phase2)
- [WebInstructSub (en)](https://huggingface.co/datasets/TIGER-Lab/WebInstructSub)
- [Magpie-Pro-300K-Filtered (en)](https://huggingface.co/datasets/Magpie-Align/Magpie-Pro-300K-Filtered)
- [Magpie-ultra-v0.1 (en)](https://huggingface.co/datasets/argilla/magpie-ultra-v0.1)
- [LLaVA mixed (en&zh)](https://huggingface.co/datasets/BUAADreamer/llava-en-zh-300k)
- [Open Assistant (de)](https://huggingface.co/datasets/mayflowergmbh/oasst_de)
- [Dolly 15k (de)](https://huggingface.co/datasets/mayflowergmbh/dolly-15k_de)

View File

@ -265,6 +265,7 @@ https://github.com/user-attachments/assets/e6ce34b0-52d5-4f3e-a830-592106c4c272
- [Neo-sft (zh)](https://huggingface.co/datasets/m-a-p/neo_sft_phase2)
- [WebInstructSub (en)](https://huggingface.co/datasets/TIGER-Lab/WebInstructSub)
- [Magpie-Pro-300K-Filtered (en)](https://huggingface.co/datasets/Magpie-Align/Magpie-Pro-300K-Filtered)
- [Magpie-ultra-v0.1 (en)](https://huggingface.co/datasets/argilla/magpie-ultra-v0.1)
- [LLaVA mixed (en&zh)](https://huggingface.co/datasets/BUAADreamer/llava-en-zh-300k)
- [Open Assistant (de)](https://huggingface.co/datasets/mayflowergmbh/oasst_de)
- [Dolly 15k (de)](https://huggingface.co/datasets/mayflowergmbh/dolly-15k_de)

View File

@ -266,6 +266,13 @@
"hf_hub_url": "Magpie-Align/Magpie-Pro-300K-Filtered",
"formatting": "sharegpt"
},
"magpie_ultra": {
"hf_hub_url": "argilla/magpie-ultra-v0.1",
"columns": {
"prompt": "instruction",
"response": "response"
}
},
"web_instruct": {
"hf_hub_url": "TIGER-Lab/WebInstructSub",
"columns": {