add marco-o1 and openo1 dataset

Former-commit-id: 17afb7d4103499a9a090a6624896cfa123e9e1d6
This commit is contained in:
hiyouga 2024-11-27 04:20:23 +00:00
parent 6cd90efb82
commit ab3782b0fa
5 changed files with 38 additions and 2 deletions

View File

@ -290,9 +290,10 @@ You also can add a custom chat template to [template.py](src/llamafactory/data/t
- [STEM (zh)](https://huggingface.co/datasets/hfl/stem_zh_instruction)
- [Ruozhiba (zh)](https://huggingface.co/datasets/hfl/ruozhiba_gpt4_turbo)
- [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)
- [WebInstructSub (en)](https://huggingface.co/datasets/TIGER-Lab/WebInstructSub)
- [OpenO1-SFT (en&zh)](https://huggingface.co/datasets/O1-OPEN/OpenO1-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)
- [Open Assistant (de)](https://huggingface.co/datasets/mayflowergmbh/oasst_de)

View File

@ -290,9 +290,10 @@ https://github.com/user-attachments/assets/e6ce34b0-52d5-4f3e-a830-592106c4c272
- [STEM (zh)](https://huggingface.co/datasets/hfl/stem_zh_instruction)
- [Ruozhiba (zh)](https://huggingface.co/datasets/hfl/ruozhiba_gpt4_turbo)
- [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)
- [WebInstructSub (en)](https://huggingface.co/datasets/TIGER-Lab/WebInstructSub)
- [OpenO1-SFT (en&zh)](https://huggingface.co/datasets/O1-OPEN/OpenO1-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)
- [Open Assistant (de)](https://huggingface.co/datasets/mayflowergmbh/oasst_de)

View File

@ -296,6 +296,13 @@
"response": "answer"
}
},
"openo1_sft": {
"hf_hub_url": "O1-OPEN/OpenO1-SFT",
"columns": {
"prompt": "prompt",
"response": "response"
}
},
"llava_1k_en": {
"hf_hub_url": "BUAADreamer/llava-en-zh-2k",
"subset": "en",

View File

@ -901,6 +901,22 @@ _register_template(
)
_register_template(
name="marco",
format_user=StringFormatter(slots=["<|im_start|>user\n{{content}}<|im_end|>\n<|im_start|>assistant\n"]),
format_system=StringFormatter(slots=["<|im_start|>system\n{{content}}<|im_end|>\n"]),
format_observation=StringFormatter(slots=["<|im_start|>tool\n{{content}}<|im_end|>\n<|im_start|>assistant\n"]),
format_separator=EmptyFormatter(slots=["\n"]),
default_system=(
"你是一个经过良好训练的AI助手你的名字是Marco-o1.由阿里国际数字商业集团的AI Business创造.\n## 重要!!!!!\n"
"当你回答问题时,你的思考应该在<Thought>内完成,<Output>内输出你的结果。\n"
"<Thought>应该尽可能是英文但是有2个特例一个是对原文中的引用另一个是是数学应该使用markdown格式<Output>内的输出需要遵循用户输入的语言。\n"
),
stop_words=["<|im_end|>"],
replace_eos=True,
)
_register_template(
name="mistral",
format_user=StringFormatter(slots=["[INST] {{content}} [/INST]"]),

View File

@ -998,6 +998,17 @@ register_model_group(
)
register_model_group(
models={
"Marco-o1-Chat": {
DownloadSource.DEFAULT: "AIDC-AI/Marco-o1",
DownloadSource.MODELSCOPE: "AIDC-AI/Marco-o1",
},
},
template="marco",
)
register_model_group(
models={
"MiniCPM-2B-SFT-Chat": {