num_key_value_heads=16 instead of 8 in the original model
#21 opened 3 days ago
by
Melody32768
Fix eos_token and model_max_length in tokenizer_config
#20 opened 24 days ago
by
AshtonIsNotHere
Update README.md
#19 opened 2 months ago
by
MironVeryanskiy
Update tokenizer_config.json
#18 opened 3 months ago
by
sbranco
Running on multi-node infrastructure
#17 opened 3 months ago
by
pvalois
Update generation_config
3
#16 opened 3 months ago
by
DeepStack
error when quantizing my finetuned 405b model using autoawq
16
#13 opened 3 months ago
by
Atomheart-Father
Any chance of an AWQ version of the 405B base model?
2
#12 opened 3 months ago
by
lodrick-the-lafted
Cuda failure 1 'invalid argument'
#8 opened 4 months ago
by
JulianGerhard