Zhang Jingyao's picture

7

Zhang Jingyao

zjyhf

·

AI & ML interests

None yet

Organizations

zjyhf's activity

New activity in nvidia/Llama3-ChatQA-1.5-8B 7 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.

#17 opened 7 months ago by

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

#16 opened 7 months ago by

New activity in nvidia/Llama3-ChatQA-1.5-70B 7 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 7 months ago by

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

#12 opened 7 months ago by

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

#11 opened 7 months ago by

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

#10 opened 7 months ago by

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

#9 opened 7 months ago by

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

#9 opened 7 months ago by

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

#10 opened 7 months ago by

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

#10 opened 7 months ago by

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

#9 opened 7 months ago by