David Xue
davidxmle
AI & ML interests
NLP
Organizations
davidxmle's activity
Not able to generate answer from astronomer/Llama-3-8B-Instruct-GPTQ-4-Bit
1
#1 opened 6 months ago
by
ceefour
Changing Reserve token names
1
#3 opened 6 months ago
by
vburb
No BOS token added: upstream fix not implemented
2
#2 opened 7 months ago
by
riskybiscuit
transformers text gen: probability tensor contains either `inf`, `nan` or element < 0, or gibberish output
5
#5 opened 7 months ago
by
CookieMaster
Missing pytorch_model.bin, tf_model.h5, model.ckpt or flax_model.msgpack
3
#2 opened 7 months ago
by
RainmakerP
Thank you Astronomer!
1
#4 opened 7 months ago
by
CleanCoder123
Thank you.
4
#1 opened 7 months ago
by
MB7977
Is the 8-bit gptq of 8b base model available?
3
#3 opened 7 months ago
by
AshTaurus
Hardware requirement
2
#1 opened 7 months ago
by
Dtree07
load error
7
#3 opened about 1 year ago
by
kl1996
Update/Fix incorrect model_max_length to 1024 tokens
#8 opened 8 months ago
by
davidxmle
Update/Fix incorrect model_max_length to 1024 tokens
#8 opened 8 months ago
by
davidxmle