Zhang Jingyao

zjyhf's activity

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

New activity in nvidia/Llama3-ChatQA-1.5-8B 6 months ago

generation_config.json adds a mapping with the special token '<|im_end|>' to solve the problem of non-stop generation when <|im_end|> is encountered.

3

#17 opened 6 months ago by zjyhf

The tokenizer adds a special token '<|im_end|>' to solve the problem of non-stop generation when encountering <|im_end|>.

1

#16 opened 6 months ago by zjyhf

New activity in nvidia/Llama3-ChatQA-1.5-70B 6 months ago

generation_config.json adds a mapping with the special token '<|im_end|>' to solve the problem of non-stop generation when <|im_end|> is encountered.

#13 opened 6 months ago by zjyhf

The tokenizer adds a special token '<|im_end|>' to solve the problem of non-stop generation when encountering <|im_end|>.

#12 opened 6 months ago by zjyhf

This is a wrong solution, a new PR has been submitted, sorry...

#11 opened 6 months ago by zjyhf

This is a wrong solution, a new PR has been submitted, sorry...

#10 opened 6 months ago by zjyhf

This is a wrong solution, a new PR has been submitted, sorry...

#9 opened 6 months ago by zjyhf

This is a wrong solution, a new PR has been submitted, sorry...

#9 opened 6 months ago by zjyhf

This is a wrong solution, a new PR has been submitted, sorry...

#10 opened 6 months ago by zjyhf

This is a wrong solution, a new PR has been submitted, sorry...

#10 opened 6 months ago by zjyhf

This is a wrong solution, a new PR has been submitted, sorry...

#9 opened 6 months ago by zjyhf