Request failed. - Benjamin

[lipere123]

Hello.

Request failed. Retry
Traceback (most recent call last):
File "/usr/local/petalscli-backend/websocket_api.py", line 48, in ws_api_generate
raise ValueError("extra_stop_sequences require stop_sequence length to be exactly 1 token")
ValueError: extra_stop_sequences require stop_sequence length to be exactly 1 token

After installed the chatbot.
I get this.
On two differents computer.
One CPU, and one that should be GPU.

Thanks in advance.
Best Regards.
Benjamin.

[jeremyzhangsq]

I also met this issue.
I started a private swarm with two GPU servers and built this web chat on another CPU node.

[jeremyzhangsq]

@lipere123 Hi, may I ask if you have figured this out?

[lipere123]

Petals network is difficult to communicate with. So basicaly, no, and we are alone. For now, I changed for the exo project where Alex is really active and accessible. So I hope that it will be easier to contribute. ++ Le jeu. 3 oct. 2024, 11:53, SQ ***@***.***> a écrit :

…

@lipere123 <https://github.com/lipere123> Hi, may I ask if you have figured this out? — Reply to this email directly, view it on GitHub <#59 (comment)>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/AS5AND2D23R25T3NGMKVD63ZZUHYRAVCNFSM6AAAAABO6EAOY2VHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMZDGOJQHE4TGMJTGM> . You are receiving this because you were mentioned.Message ID: ***@***.***>