运行脚本generate_chatllama.py后，tokenizer报错

[tianmala]

Traceback (most recent call last): File "scripts/generate_chatllama.py", line 82, in args.tokenizer = str2tokenizerargs.tokenizer File "/home/mo/llama/TencentPretrain/tencentpretrain/utils/tokenizers.py", line 255, in init super().init(args, is_src) File "/home/mo/llama/TencentPretrain/tencentpretrain/utils/tokenizers.py", line 30, in init self.sp_model.Load(spm_model_path) File "/home/mo/miniconda3/envs/llm_env/lib/python3.8/site-packages/sentencepiece/init.py", line 905, in Load return self.LoadFromFile(model_file) File "/home/mo/miniconda3/envs/llm_env/lib/python3.8/site-packages/sentencepiece/init.py", line 310, in LoadFromFile return _sentencepiece.SentencePieceProcessor_LoadFromFile(self, arg) RuntimeError: Internal: src/sentencepiece_processor.cc(1101) [model_proto->ParseFromArray(serialized.data(), serialized.size())]

我运行脚本后报错了，请问这个问题有谁遇到过嘛

[davikl]

我也是求教

[rayguo01]

同样出错

[guanlinz]

subscribe this issue as meet the same issue

[lylcst]

同样问题，怎么解决

[2775919186]

spm_model_file = '../ChatLLaMA-zh-7B/tokenizer.model'这个分词模型是不是损坏了？

[Data2Me]

同样出错

[ydli-ai]

spm_model_file = '../ChatLLaMA-zh-7B/tokenizer.model'这个分词模型是不是损坏了？

我测试了没有遇到这个问题，检查一下Sentencepiece版本？ 我这里是0.1.97

[Data2Me]

spm_model_file = '../ChatLLaMA-zh-7B/tokenizer.model'这个分词模型是不是损坏了？

我测试了没有遇到这个问题，检查一下Sentencepiece版本？ 我这里是0.1.97

我这边Sentencepiece版本也是0.1.97，刚试了还是报错： File "/opt/conda/lib/python3.10/site-packages/sentencepiece/init.py", line 310, in LoadFromFile return _sentencepiece.SentencePieceProcessor_LoadFromFile(self, arg) RuntimeError: Internal: src/sentencepiece_processor.cc(1101) [model_proto->ParseFromArray(serialized.data(), serialized.size())]

[Data2Me]

spm_model_file = '../ChatLLaMA-zh-7B/tokenizer.model'这个分词模型是不是损坏了？

我测试了没有遇到这个问题，检查一下Sentencepiece版本？ 我这里是0.1.97

我这边Sentencepiece版本也是0.1.97，刚试了还是报错： File "/opt/conda/lib/python3.10/site-packages/sentencepiece/init.py", line 310, in LoadFromFile return _sentencepiece.SentencePieceProcessor_LoadFromFile(self, arg) RuntimeError: Internal: src/sentencepiece_processor.cc(1101) [model_proto->ParseFromArray(serialized.data(), serialized.size())]

已解决，重新下载模型权重文件。git clone时要安装git lfs

[YYForReal]

spm_model_file = '../ChatLLaMA-zh-7B/tokenizer.model'这个分词模型是不是损坏了？

我测试了没有遇到这个问题，检查一下Sentencepiece版本？ 我这里是0.1.97

我这边Sentencepiece版本也是0.1.97，刚试了还是报错： File "/opt/conda/lib/python3.10/site-packages/sentencepiece/init.py", line 310, in LoadFromFile return _sentencepiece.SentencePieceProcessor_LoadFromFile(self, arg) RuntimeError: Internal: src/sentencepiece_processor.cc(1101) [model_proto->ParseFromArray(serialized.data(), serialized.size())]

已解决，重新下载模型权重文件。git clone时要安装git lfs

安装之后下载模型权重文件速度太慢了，有什么好方法吗？