diff --git a/README.md b/README.md index eb28c89d..789c20ce 100644 --- a/README.md +++ b/README.md @@ -238,6 +238,7 @@ You also can add a custom chat template to [template.py](src/llmtuner/data/templ - [Evol Instruct V2 (en)](https://huggingface.co/datasets/WizardLM/WizardLM_evol_instruct_V2_196k) - [Glaive Function Calling V2 (en)](https://huggingface.co/datasets/glaiveai/glaive-function-calling-v2) - [Cosmopedia (en)](https://huggingface.co/datasets/HuggingFaceTB/cosmopedia) +- [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) - [Alpaca GPT4 (de)](https://huggingface.co/datasets/mayflowergmbh/alpaca-gpt4_de) @@ -257,7 +258,7 @@ You also can add a custom chat template to [template.py](src/llmtuner/data/templ - [GPT-4 Generated Data (en&zh)](https://github.com/Instruction-Tuning-with-GPT-4/GPT-4-LLM) - [Orca DPO (en)](https://huggingface.co/datasets/Intel/orca_dpo_pairs) - [Nectar (en)](https://huggingface.co/datasets/berkeley-nest/Nectar) -- [DPO mix (en&zh)](https://huggingface.co/datasets/hiyouga/DPO-En-Zh-20k) +- [DPO mixed (en&zh)](https://huggingface.co/datasets/hiyouga/DPO-En-Zh-20k) - [Orca DPO (de)](https://huggingface.co/datasets/mayflowergmbh/intel_orca_dpo_pairs_de) diff --git a/README_zh.md b/README_zh.md index bfcf3870..fb02aa95 100644 --- a/README_zh.md +++ b/README_zh.md @@ -238,6 +238,7 @@ https://github.com/hiyouga/LLaMA-Factory/assets/16256802/ec36a9dd-37f4-4f72-81bd - [Evol Instruct V2 (en)](https://huggingface.co/datasets/WizardLM/WizardLM_evol_instruct_V2_196k) - [Glaive Function Calling V2 (en)](https://huggingface.co/datasets/glaiveai/glaive-function-calling-v2) - [Cosmopedia (en)](https://huggingface.co/datasets/HuggingFaceTB/cosmopedia) +- [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) - [Alpaca GPT4 (de)](https://huggingface.co/datasets/mayflowergmbh/alpaca-gpt4_de) @@ -257,7 +258,7 @@ https://github.com/hiyouga/LLaMA-Factory/assets/16256802/ec36a9dd-37f4-4f72-81bd - [GPT-4 Generated Data (en&zh)](https://github.com/Instruction-Tuning-with-GPT-4/GPT-4-LLM) - [Orca DPO (en)](https://huggingface.co/datasets/Intel/orca_dpo_pairs) - [Nectar (en)](https://huggingface.co/datasets/berkeley-nest/Nectar) -- [DPO mix (en&zh)](https://huggingface.co/datasets/hiyouga/DPO-En-Zh-20k) +- [DPO mixed (en&zh)](https://huggingface.co/datasets/hiyouga/DPO-En-Zh-20k) - [Orca DPO (de)](https://huggingface.co/datasets/mayflowergmbh/intel_orca_dpo_pairs_de) diff --git a/data/dataset_info.json b/data/dataset_info.json index 74ec417f..146cf59e 100644 --- a/data/dataset_info.json +++ b/data/dataset_info.json @@ -459,4 +459,4 @@ }, "folder": "python" } -} +} \ No newline at end of file