Hugging Face's logo

p208p2002
/
llama-chinese-81M

Text Generation Transformers PyTorch Safetensors
Chinese English llama chinese english Inference Endpoints text-generation-inference
Model card Files Community
2
Edit model card

LLaMA Chinese 81M

一個小型中英文(雙語)預訓練語言模型。

Training Dataset

  • 中文維基百科(20230601)
  • 英文維基百科(20230601)

Tokenizer

使用重新在中英文語料上訓練的 BPE Tokenizer，擁有較佳的分詞效果與邊解碼效率。

https://github.com/p208p2002/BPE-tokenizer-from-zh-wiki

Downloads last month
872
Safetensors
Model size
81M params
Tensor type
F32
·

Dataset used to train p208p2002/llama-chinese-81M

Collection including p208p2002/llama-chinese-81M