diff --git a/README.md b/README.md index 81097819..0ef472b3 100644 --- a/README.md +++ b/README.md @@ -188,7 +188,16 @@ Please refer to [constants.py](src/llmtuner/extras/constants.py) for a full list - [LMSYS Chat 1M (en)](https://huggingface.co/datasets/lmsys/lmsys-chat-1m) - [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) - +- [Open Assistant (de)](https://huggingface.co/datasets/mayflowergmbh/oasst_de) +- [Dolly 15k (de)](https://huggingface.co/datasets/mayflowergmbh/dolly-15k_de) +- [FreedomIntelligence Alpaca GPT4 (de)](https://huggingface.co/datasets/mayflowergmbh/alpaca-gpt4_de) +- [LeoLM/OpenSchnabeltier (de)](https://huggingface.co/datasets/mayflowergmbh/openschnabeltier_de) +- [FreedomIntelligence/evol-instruct-deutsch (de)](https://huggingface.co/datasets/mayflowergmbh/evol-instruct_de) +- [wiki_qa (de)](https://huggingface.co/datasets/wiki_qa) +- [cognitivecomputations/dolphin (de)](https://huggingface.co/datasets/mayflowergmbh/dolphin_de) +- [booksum (de)](https://huggingface.co/datasets/mayflowergmbh/booksum_de) +- [jondurbin/airoboros-3.0 (de)](https://huggingface.co/datasets/mayflowergmbh/airoboros-3.0_de) +- [stingning/ultrachat (de)](https://huggingface.co/datasets/mayflowergmbh/ultra-chat_de)
Preference datasets @@ -197,6 +206,7 @@ Please refer to [constants.py](src/llmtuner/extras/constants.py) for a full list - [Open Assistant (multilingual)](https://huggingface.co/datasets/OpenAssistant/oasst1) - [GPT-4 Generated Data (en&zh)](https://github.com/Instruction-Tuning-with-GPT-4/GPT-4-LLM) - [Nectar (en)](https://huggingface.co/datasets/berkeley-nest/Nectar) +- [Intel/orca_dpo_pairs (de)](https://huggingface.co/datasets/mayflowergmbh/intel_orca_dpo_pairs_de)
diff --git a/data/dataset_info.json b/data/dataset_info.json index ceb3ec2c..9b69f9a1 100644 --- a/data/dataset_info.json +++ b/data/dataset_info.json @@ -15,6 +15,9 @@ "file_name": "alpaca_gpt4_data_zh.json", "file_sha1": "3eaa3bda364ccdd59925d7448a698256c31ef845" }, + "alpaca-gpt4_de": { + "hf_hub_url": "mayflowergmbh/alpaca-gpt4_de" + }, "self_cognition": { "file_name": "self_cognition.json", "file_sha1": "6287a730ada924fc5d9eadc6d8f865e01b7a6f67" @@ -39,6 +42,9 @@ "history": "history" } }, + "oasst_de": { + "hf_hub_url": "mayflowergmbh/oasst_de" + }, "lima": { "file_name": "lima.json", "file_sha1": "9db59f6b7007dc4b17529fc63379b9cd61640f37", @@ -120,6 +126,31 @@ "system": "system_prompt" } }, + "intel_orca_dpo_pairs_de" : { + "hf_hub_url": "mayflowergmbh/intel_orca_dpo_pairs_de", + "ranking": true + }, + "airoboros-3.0_de": { + "hf_hub_url": "mayflowergmbh/airoboros-3.0_de" + }, + "booksum_de": { + "hf_hub_url": "mayflowergmbh/booksum_de" + }, + "dolphin_de": { + "hf_hub_url": "mayflowergmbh/dolphin_de" + }, + "wiki_qa_de": { + "hf_hub_url": "mayflowergmbh/wiki_qa_de" + }, + "evol-instruct_de": { + "hf_hub_url": "mayflowergmbh/evol-instruct_de" + }, + "openschnabeltier_de": { + "hf_hub_url": "mayflowergmbh/openschnabeltier_de" + }, + "dolly-15k_de": { + "hf_hub_url": "mayflowergmbh/dolly-15k_de" + }, "mathinstruct": { "hf_hub_url": "TIGER-Lab/MathInstruct", "ms_hub_url": "AI-ModelScope/MathInstruct", @@ -184,6 +215,9 @@ }, "formatting": "sharegpt" }, + "ultrachat_chat_de": { + "hf_hub_url": "mayflowergmbh/ultra-chat_de" + }, "agent_instruct": { "hf_hub_url": "THUDM/AgentInstruct", "ms_hub_url": "ZhipuAI/AgentInstruct", diff --git a/src/llmtuner/data/template.py b/src/llmtuner/data/template.py index cf4c6d53..00a005dc 100644 --- a/src/llmtuner/data/template.py +++ b/src/llmtuner/data/template.py @@ -515,6 +515,16 @@ register_template( register_template(name="vanilla") +register_template( + name="chatml_de", + 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_separator=EmptyFormatter(slots=["\n"]), + default_system="Du bist ein freundlicher und hilfsbereiter KI-Assistent.", + stop_words=["<|im_end|>"], + replace_eos=True, +) + register_template( name="vicuna",