423A35C7/LLaMA-Factory
1
0
Fork 0
mirror of https://github.com/hiyouga/LLaMA-Factory.git synced 2025-10-14 23:58:11 +08:00
Code Issues Packages Projects Releases Wiki Activity

Merge pull request #2423 from mayflower/main

Browse Source 
Support for german sft and dpo

Former-commit-id: 8e282e4e6bee6493b1bd38ba239ca49a6a840a92
This commit is contained in:
hoshi-hiyouga 2024-02-07 15:58:20 +08:00 committed by GitHub
commit 2c3ef480a6
2 changed files with 21 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
README.md
View File

@ -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)
</details>
<details><summary>Preference datasets</summary>
@ -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)
</details>

10
src/llmtuner/data/template.py
View File

@ -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",