Raj Mehta
rjmehta
AI & ML interests
None yet
Organizations
None yet
Amazing model. FP8 Support please.
2
#10 opened 2 months ago
by
rjmehta
Use the correct way of initializing using latest transformers latest branch v5.0.0
1
#58 opened 3 months ago
by
rjmehta
Supported language list
๐ 1
4
#1 opened 5 months ago
by
rjmehta
FP8 Quants Please
โ 1
#18 opened 8 months ago
by
rjmehta
Doesnt work with sglang
1
#4 opened 9 months ago
by
rjmehta
Unable to load with SG_Lang
2
#1 opened 9 months ago
by
MurtazaNasir
"head_dim": 80
5
#2 opened 9 months ago
by
rjmehta
FP8 Quants please
#5 opened 9 months ago
by
rjmehta
FP8 Quants please
3
#3 opened 9 months ago
by
rjmehta
Fp8 Quants please
#3 opened 9 months ago
by
rjmehta
FP8 Quant Please
#11 opened 9 months ago
by
rjmehta
YaRN block required?
3
#5 opened over 1 year ago
by
robbiemu
What's the instruction you added for each task in training?
4
#3 opened over 1 year ago
by
nachtsky1077
Model weights release?
3
#1 opened over 1 year ago
by
rbhatia46
i tested the q8 in lm studio( getting wrong output)
8
#9 opened over 1 year ago
by
gopi87
There really seems to be some problem with the tokenizer or the ggufs
๐ 1
6
#12 opened over 1 year ago
by
Smorty100
Suggestion
#3 opened almost 2 years ago
by
rjmehta
Exl Quants please
1
#5 opened almost 2 years ago
by
rjmehta
exl quants please
2
#3 opened almost 2 years ago
by
rjmehta