Benjamin Warner
bwarner
AI & ML interests
None yet
Organizations
bwarner's activity
Inference fails on CPU: `ValueError: Pointer argument (at 0) cannot be accessed from Triton (cpu tensor?)`
8
#10 opened 3 months ago
by
umarbutler

ValueError: The checkpoint you are trying to load has model type `modernbert`
2
#37 opened 3 months ago
by
Sengil

Set tokenizer "model_max_length" property to 8192
#39 opened 3 months ago
by
NohTow

Set tokenizer "model_max_length" property to 8192
#9 opened 3 months ago
by
NohTow

Mention that users should use transformers v4.48.0
#12 opened 3 months ago
by
tomaarsen

Mention that users should use transformers v4.48.0
#50 opened 3 months ago
by
tomaarsen

Error while finetuning using Aut Train
1
#45 opened 3 months ago
by
sk4444
Speed Benchmarks with MPS Backend
1
#47 opened 3 months ago
by
mlburnham
Is this model meant for full bfloat16, AMP bfloat16 or no bfloat16?
2
#7 opened 3 months ago
by
umarbutler

Upload re.zip
#7 opened 3 months ago
by
Amyww

Update README.md
1
#35 opened 3 months ago
by
solankibhargav

Create test
#25 opened 3 months ago
by
battleman0526
any
#26 opened 3 months ago
by
battleman0526
Upload re.zip
#28 opened 3 months ago
by
Amyww

Precisions about the config properties wrt the paper
1
#5 opened 3 months ago
by
TomSchelsen
512 max positional embeddings, but 8192 context length
1
#2 opened 3 months ago
by
Fizzarolli
