Can support the new model about Llama3

[1737686924]

Can support the new model about Llama3

[namespace-Pt]

+1 here. Especially the chat template

[March-7]

Guys, is it the same as llama2?

[1737686924]

伙计们，它和 llama2 一样吗？

I have not tested it myself, but I saw the evaluation results on meta, which are better and more advanced than llama2, and I heard that the open source Llama for 400B is being prepared, which should be better than GPT4

[sohelzerdoumi]

+1

They are 3 pending pull request
#3257 #3256 #3259

[March-7]

Guys, when will the conversation template for new models like llama3 be updated to main？

[hongyinjie]

Change the file tokenizer_config.json:
eos_token: end_of_text ==> eot_id

it work!

[Oscarjia]

@hongyinjie What change are you referring to? does this can fix llama3 can't stop problem? https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct/discussions/4