bench-labs/slop-classification
Viewer • Updated • 320 • 215 • 10
AI & ML interests
Exploring artificial intelligence together. Open source
Recent Activity
wop
updated a
dataset about 15 hours ago
wop
updated a
model about 15 hours ago
TobiasLogic
updated a
collection about 20 hours ago
TobiasLogic
updated 2
Spaces about 20 hours ago
TobiasLogic
updated a
model about 21 hours ago
TobiasLogic
published a
model about 21 hours ago
Update the Complexity ML partner logo
👍👀 2
#2 opened 1 day ago
by 
Pacific-i64
Update the Complexity ML partner logo
👀👍 2
#2 opened 1 day ago
by Pacific-i64
wop
updated 4
collections 2 days ago
wop
updated a
Space 4 days ago
Post
2145
bench-labs/GCTokenizer-v1 , a multilingual tokenizer which does not require a training corpus
bench-labs developed **GCTokenizer-v1**, which is a multi-lingual tokenizer
Available in four sizes: 32K, 65K, 131K and 262K tokens "S, M, L, XL"
It utilizes an encoding scheme which allows it to handle characters in any language around the world
General (multi lingual)
Consensus (from multiple model tokenizers consensus)
Tokenizer
We included an implementation script too,
built like BPE- it can encode arbitrary text, most of the time, efficiently
Available in four sizes: 32K, 65K, 131K and 262K tokens "S, M, L, XL"
It utilizes an encoding scheme which allows it to handle characters in any language around the world
General (multi lingual)
Consensus (from multiple model tokenizers consensus)
Tokenizer
We included an implementation script too,
built like BPE- it can encode arbitrary text, most of the time, efficiently
wop
updated a
collection 4 days ago
wop
updated a
Space 4 days ago
wop
published a
model 4 days ago
wop
updated a
model 4 days ago
Post
2315
all models now also run on zerogpu!
BenchLabs/Demo-FAST
Speed measurements:
image ~5s (pixelmodel v5 ~0.5s)
3D ~2s
audio ~3s +(upload)
insane.
Yes, we made a new model: bench-labs/AudioModel-v1
BIG thanks to @TobiasLogic
BenchLabs/Demo-FAST
Speed measurements:
image ~5s (pixelmodel v5 ~0.5s)
3D ~2s
audio ~3s +(upload)
insane.
Yes, we made a new model: bench-labs/AudioModel-v1
BIG thanks to @TobiasLogic