Resources

View closed (5)

Adding `safetensors` variant of this model

#24 opened 9 months ago by

SFconvertbot

When I using the model, I got a information like that and the program stop.

#22 opened over 1 year ago by

Rosher

Update tokenizer_config.json

#21 opened over 1 year ago by

usoni1

[HELP!!] question about special_tokens_map.json

#20 opened over 1 year ago by

zzz96

Unpickling Error when loading model with lightning transformers

#19 opened over 1 year ago by

cyrus0120

Add support for batched generation

#18 opened over 1 year ago by

jacobthebanana

Error when generating multiple outputs using hugging face generation

#16 opened over 1 year ago by

DongfuJiang

how to ues it？

#14 opened over 1 year ago by

lklklk

Generation is great, but begins to miss spaces between words

#13 opened almost 2 years ago by

SirWaffle

Question about the command used

#12 opened almost 2 years ago by

8bit-coder

What script/repo you used exactly to train?

#11 opened almost 2 years ago by

francis2tm

Finetuning in different languages

#10 opened almost 2 years ago by

k0ntra

Will this work on an RTX 3080 10gb?

#8 opened almost 2 years ago by

TheAIGuyz

api-inference is not working

#6 opened almost 2 years ago by

baby1

Can we get a 4bit quantized version?

#5 opened almost 2 years ago by

yehiaserag

Quality seems to be different from the official demo

#4 opened almost 2 years ago by

kz919

FYI: LLaMA PR was merged into huggingface/transformers

#3 opened almost 2 years ago by

unojcn9f

Can't convert the model

#2 opened almost 2 years ago by

the

fantastic

#1 opened almost 2 years ago by

Yoshiii