Qi Yang

qiyang's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

New activity in IDEA-CCNL/Ziya-LLaMA-13B-v1.1 almost 2 years ago

tokenizer的vocab_size是39408， 而 config.json 里面的 vocab_size 是 39424， 哪里有问题呢？

1

#5 opened about 2 years ago by

tanguofu

New activity in IDEA-CCNL/Ziya-LLaMA-13B-v1.1 about 2 years ago

跑出来的结果全是乱码，如下：

4

#3 opened about 2 years ago by

lewis110

New activity in IDEA-CCNL/Ziya-LLaMA-13B-v1 about 2 years ago

Step 2 error:The size of tensor a (32000) must match the size of tensor b (39424) at non-singleton dimension 0

1

#25 opened about 2 years ago by

zjtzpanxb

您好，add_token.json内容和models不匹配，这个应该怎么修改

2

#22 opened about 2 years ago by

redauzhang

New activity in IDEA-CCNL/Ziya-LLaMA-13B-Pretrain-v1 about 2 years ago

如何验证合并的权重是否正确？

4

#1 opened about 2 years ago by

puppet1988

New activity in IDEA-CCNL/Ziya-LLaMA-13B-v1 about 2 years ago

Update url of pretrained model

#18 opened about 2 years ago by

qiyang