Access request FAQ

pinned

#10 opened 5 months ago by

samuelselvan

set "pad_token" to "<|finetune_right_pad_id|>"

#31 opened 24 days ago by

wukaixingxp

cannot get 405B-model to run

#30 opened about 1 month ago by

hAI-hades

Llama 3.1 models continuously unavailable

#28 opened 4 months ago by

HugoMartin

potential of 405b model

#27 opened 4 months ago by

nskumar

Update tokenizer_config.json

#26 opened 4 months ago by

Rocketknight1

Model inference giving 503 error

#25 opened 4 months ago by

DeepTreeTeam

Num KV heads changed from 16 to 8?

#21 opened 5 months ago by

keremturgutlu

This repo is huge!

#19 opened 5 months ago by

JohnnieB

Please reply, why am I not allowed to apply for approval? Aren't you open-source?

#18 opened 5 months ago by

guangqi

Inference Endpoint (dedicated) not available

#16 opened 5 months ago by

janhornych

why "num_key_value_heads": 16,

#14 opened 5 months ago by

xiaoxiawu123

GGUF version request

#13 opened 5 months ago by

Keionsa

🚀 LMDeploy support Llama3.1 and its Tool Calling. An example of calling "Wolfram Alpha" to perform complex mathematical calculations can be found from here!

#11 opened 5 months ago by

vansin

TGI available only for pro subscriptions?

#7 opened 5 months ago by

avfranco

Max output tokens for Llama 3.1

#6 opened 5 months ago by

abhirup-sainapse

Please move PTH/original into new model/repo.

#5 opened 5 months ago by

Qubitium