Chinese-Alpaca-2-13B-16K 指令模型 24.7 GB 文件列表 config.json generation_config.json pytorch_model.bin.index.json SHA256.md special_tokens_map.json tokenizer.model tokenizer_config.json pytorch_model-00003-of-00003.bin pytorch_model-00001-of-00003.bin pytorch_model-00002-of-00003.bin config....
Chinese-Alpaca-2-16K (7B/13B) 操作系统 Linux 详细描述问题 在Code Llama中,通过设置rope_theta来让长文本的效果更好,请问当前chinese-alpaca-2-13b-16k训练过程中修改了这个参数吗? "rope_theta": 1000000(https://huggingface.co/codellama/CodeLlama-7b-hf/blob/main/config.json) https://scontent-hk...
Technically speaking,Chinese-Alpaca-2-LoRA-13Binheritsthe weight ofChinese-LLaMA-2-LoRA-13Band perform further instruction tuning. That being said, the base model (meta's llama) has not been changed in training both LLaMA and Alpaca. You should still use Meta's Llama-2 for merging purpose. ...
Chinese-Alpaca-2-LoRA-13B-16K 指令模型 Llama-2-13B-hf 1.5 GB Chinese-Alpaca-2-LoRA-13B-16K 指令模型 Llama-2-13B-hf 1.5 GB 文件列表 chinese-alpaca-2-lora-13b-16k.zip chinese-alpaca-2-lora-13b-16k.zip (1341.95M) 下载 File Name Size Update Time adapter_config.json 471 2023-08-31 12...
v2.0 Release: Chinese-LLaMA-2-13B and Chinese-Alpaca-2-13B (ymcui#118) Browse files main (ymcui/Chinese-LLaMA-Alpaca-2#118) ymcui committed Aug 14, 2023 Verified 2 parents 54d8152 + 2b0c9b8 commit db21c15 Showing 2 changed files with 180 additions and 125 deletions. W...