zake7749/kyara-chinese-preference-rl-dpo-s0-30K download history

zake7749/kyara-chinese-preference-rl-dpo-s0-30K is a dataset on the Hugging Face Hub. In the last 30 days it was downloaded 23 times (3 in the last 7 days), and 861 times in total. It ranks #338,096 among datasets by monthly downloads.

Kyara: Knowledge Yielding Adaptive Retrieval Augmentation for LLM Fine-tuning 🤗 Hugging Face  ｜ 🚀Github  ｜  📑 Paper  ｜  📖 English  ｜  📖 Chinese This is a dataset for training Kyara. We extracted Chinese Prompts from Magpie-Align/Magpie-Qwen2-Pro-200K-Chinese, hfl/stem_zh_instr

Models trained on kyara-chinese-preference-rl-dpo-s0-30K

12 models list it as training data.

• mradermacher/Mistral-Nemo-NT-Ko-12B-dpo-i1-GGUF 1.5K downloads in 30 days
• mradermacher/Qwen2.5-Taiwan-7B-Instruct-i1-GGUF 1.1K downloads in 30 days
• zake7749/gemma-2-2b-it-chinese-kyara-dpo 486 downloads in 30 days
• mradermacher/Qwen2.5-Taiwan-1.5B-Instruct-GGUF 418 downloads in 30 days
• mradermacher/Qwen2.5-Taiwan-7B-Instruct-GGUF 311 downloads in 30 days
• mradermacher/Qwen2.5-Taiwan-3B-Instruct-GGUF 307 downloads in 30 days
• mradermacher/Mistral-Nemo-NT-Ko-12B-dpo-GGUF 266 downloads in 30 days
• werty1248/Mistral-Nemo-NT-Ko-12B-dpo-GGUF 55 downloads in 30 days
• benchang1110/Qwen2.5-Taiwan-7B-Instruct 44 downloads in 30 days
• benchang1110/Qwen2.5-Taiwan-1.5B-Instruct 28 downloads in 30 days
• benchang1110/Qwen2.5-Taiwan-3B-Instruct 16 downloads in 30 days
• werty1248/Mistral-Nemo-NT-Ko-12B-dpo 13 downloads in 30 days

Open zake7749/kyara-chinese-preference-rl-dpo-s0-30K on Hugging Face

Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.