Resources

View closed (3)

Interview request: genAI evaluation & documentation

#21 opened about 2 months ago by

evatang

RuntimeError: CUDA error: invalid configuration argument - how to tackle that?

#20 opened 4 months ago by

guentert

the model is supported by TGI

#19 opened 4 months ago by

MoritzLaurer

Availability of Mixtral-8x22B-Instruct-v0.1-GPTQ

#18 opened 6 months ago by

SSW512

Error: This model's maximum context length is 2000 token

#17 opened 7 months ago by

joanp

fix config.json, "modules_in_block_to_quantize" array close syntax

#16 opened 7 months ago by

sandeshrajx

update chat_template to allow system prompt

#15 opened 8 months ago by

SebastienFA

Sagemaker deployment

#14 opened 9 months ago by

vibranium

Model card should require transformers >=4.37.0, since <=4.36.2 does not work with this model

#12 opened 10 months ago by

ymurenko

AeertionError

#11 opened 10 months ago by

Marseus

Sequence/Context Length

#10 opened 10 months ago by

Birdman13

Is working with 2xRTX4090 and GPTQ but extremly slow

#9 opened 11 months ago by

mullerse

AWQ support

#8 opened 11 months ago by

Prasanna-IQ

Is GPTQ working locally on MAC (mps)

#7 opened 11 months ago by

mox

Does not seem to work with TGI sharding

#6 opened 11 months ago by

nazrak-atlassian

I can't get it running in text-generation-webui

#3 opened 11 months ago by

mamsds

The official AutoGPTQ library now supports Mixtral.

#2 opened 11 months ago by

inkor

Did anyone get it to run?

#1 opened 11 months ago by

dimaischenko