423A35C7/LLaMA-Factory
1
0
Fork 0
mirror of https://github.com/hiyouga/LLaMA-Factory.git synced 2025-11-05 10:22:15 +08:00
Code Issues Packages Projects Releases Wiki Activity

add neo-sft dataset

Browse Source 
Former-commit-id: 34863fa7cb641ceca92e3a2eec914126db537b62
This commit is contained in:
hiyouga 2024-06-13 01:00:56 +08:00
parent f4c9555760
commit 39e3d3fed6
3 changed files with 6 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
README.md
View File

@ -259,6 +259,7 @@ You also can add a custom chat template to [template.py](src/llamafactory/data/t
- [Cosmopedia (en)](https://huggingface.co/datasets/HuggingFaceTB/cosmopedia) - [Cosmopedia (en)](https://huggingface.co/datasets/HuggingFaceTB/cosmopedia)
- [STEM (zh)](https://huggingface.co/datasets/hfl/stem_zh_instruction) - [STEM (zh)](https://huggingface.co/datasets/hfl/stem_zh_instruction)
- [Ruozhiba (zh)](https://huggingface.co/datasets/hfl/ruozhiba_gpt4_turbo) - [Ruozhiba (zh)](https://huggingface.co/datasets/hfl/ruozhiba_gpt4_turbo)
- [Neo-sft (zh)](https://huggingface.co/datasets/m-a-p/neo_sft_phase2)
- [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)
- [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)

1
README_zh.md
View File

@ -259,6 +259,7 @@ https://github.com/hiyouga/LLaMA-Factory/assets/16256802/ec36a9dd-37f4-4f72-81bd
- [Cosmopedia (en)](https://huggingface.co/datasets/HuggingFaceTB/cosmopedia) - [Cosmopedia (en)](https://huggingface.co/datasets/HuggingFaceTB/cosmopedia)
- [STEM (zh)](https://huggingface.co/datasets/hfl/stem_zh_instruction) - [STEM (zh)](https://huggingface.co/datasets/hfl/stem_zh_instruction)
- [Ruozhiba (zh)](https://huggingface.co/datasets/hfl/ruozhiba_gpt4_turbo) - [Ruozhiba (zh)](https://huggingface.co/datasets/hfl/ruozhiba_gpt4_turbo)
- [Neo-sft (zh)](https://huggingface.co/datasets/m-a-p/neo_sft_phase2)
- [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)
- [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)

4
data/dataset_info.json
View File

@ -248,6 +248,10 @@
"ruozhiba_gpt4": { "ruozhiba_gpt4": {
"hf_hub_url": "hfl/ruozhiba_gpt4_turbo" "hf_hub_url": "hfl/ruozhiba_gpt4_turbo"
}, },
"neo_sft": {
"hf_hub_url": "m-a-p/neo_sft_phase2",
"formatting": "sharegpt"
},
"llava_1k_en": { "llava_1k_en": {
"hf_hub_url": "BUAADreamer/llava-en-zh-2k", "hf_hub_url": "BUAADreamer/llava-en-zh-2k",
"subset": "en", "subset": "en",