Resources

Colab no pytorch_model.bin, tf_model.h5, model.ckpt or flax_model.msgpack file

#27 opened 10 months ago by

Danis457845

how long does it take for split_long_conversation.py ?

#26 opened 12 months ago by

maxkarl

Question about The roles are still USER and ASSISTANT. Early stopping tokens bug.

#24 opened about 1 year ago by

Goldenblood56

v230502 Testing and Discussion

#23 opened about 1 year ago by deleted

You may want to add an "act-order" GPTQ quantization.

#22 opened about 1 year ago by

xzuyn

text-generation-webui: AttributeError: 'Offload_LlamaModel' object has no attribute 'preload', when trying to generate text

#21 opened about 1 year ago by

hpnyaggerman

Fix for slow speed

#20 opened about 1 year ago by

CyberTimon

Do I just copy over the config, tokenizer_config, and tokenizer.model from another 13B Vicuna Model to get this working in ooba? I am getting error.

#17 opened about 1 year ago by

Goldenblood56

Some test

#16 opened about 1 year ago by

yugihu

V4.3 Early Testing.

109

#15 opened about 1 year ago by deleted

Question about this Ai's identity (Solved)

#14 opened about 1 year ago by

waynekenney

oobabooga model loading help? Thank you!

#12 opened about 1 year ago by

waynekenney

The V4 is here

#11 opened about 1 year ago by

TheYuriLover

USE 1.1 vicuna since it no longer has the issue of feedback / talkijng to its self?

#10 opened about 1 year ago by

nucleardiffusion

Why does it insert so many unsolicited http-links?

#9 opened about 1 year ago by

ai2p

talks to its self after answering the question

#8 opened about 1 year ago by

nucleardiffusion

Is the q4 version in ggml format?

#4 opened about 1 year ago by

ai2p

Thank you

#3 opened about 1 year ago by

anon8231489123

Any chance we can get a 7B version?

#2 opened about 1 year ago by

PushTheBrAIkes