add pokemon dataset

Former-commit-id: 06680158a0f0a1e3c542e77af92ac877fbe357c5
This commit is contained in:
hiyouga 2024-09-02 01:02:25 +08:00
parent b7041c0a11
commit 217d8f7199
3 changed files with 10 additions and 0 deletions

View File

@ -275,6 +275,7 @@ You also can add a custom chat template to [template.py](src/llamafactory/data/t
- [Magpie-Pro-300K-Filtered (en)](https://huggingface.co/datasets/Magpie-Align/Magpie-Pro-300K-Filtered) - [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) - [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) - [LLaVA mixed (en&zh)](https://huggingface.co/datasets/BUAADreamer/llava-en-zh-300k)
- [Pokemon-gpt4o-captions](https://huggingface.co/datasets/jugg1024/pokemon-gpt4o-captions)
- [Open Assistant (de)](https://huggingface.co/datasets/mayflowergmbh/oasst_de) - [Open Assistant (de)](https://huggingface.co/datasets/mayflowergmbh/oasst_de)
- [Dolly 15k (de)](https://huggingface.co/datasets/mayflowergmbh/dolly-15k_de) - [Dolly 15k (de)](https://huggingface.co/datasets/mayflowergmbh/dolly-15k_de)
- [Alpaca GPT4 (de)](https://huggingface.co/datasets/mayflowergmbh/alpaca-gpt4_de) - [Alpaca GPT4 (de)](https://huggingface.co/datasets/mayflowergmbh/alpaca-gpt4_de)

View File

@ -276,6 +276,7 @@ https://github.com/user-attachments/assets/e6ce34b0-52d5-4f3e-a830-592106c4c272
- [Magpie-Pro-300K-Filtered (en)](https://huggingface.co/datasets/Magpie-Align/Magpie-Pro-300K-Filtered) - [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) - [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) - [LLaVA mixed (en&zh)](https://huggingface.co/datasets/BUAADreamer/llava-en-zh-300k)
- [Pokemon-gpt4o-captions](https://huggingface.co/datasets/jugg1024/pokemon-gpt4o-captions)
- [Open Assistant (de)](https://huggingface.co/datasets/mayflowergmbh/oasst_de) - [Open Assistant (de)](https://huggingface.co/datasets/mayflowergmbh/oasst_de)
- [Dolly 15k (de)](https://huggingface.co/datasets/mayflowergmbh/dolly-15k_de) - [Dolly 15k (de)](https://huggingface.co/datasets/mayflowergmbh/dolly-15k_de)
- [Alpaca GPT4 (de)](https://huggingface.co/datasets/mayflowergmbh/alpaca-gpt4_de) - [Alpaca GPT4 (de)](https://huggingface.co/datasets/mayflowergmbh/alpaca-gpt4_de)

View File

@ -340,6 +340,14 @@
"assistant_tag": "assistant" "assistant_tag": "assistant"
} }
}, },
"pokemon_cap": {
"hf_hub_url": "llamafactory/pokemon-gpt4o-captions",
"formatting": "sharegpt",
"columns": {
"messages": "conversations",
"images": "images"
}
},
"mllm_pt_demo": { "mllm_pt_demo": {
"hf_hub_url": "BUAADreamer/mllm_pt_demo", "hf_hub_url": "BUAADreamer/mllm_pt_demo",
"formatting": "sharegpt", "formatting": "sharegpt",