Ultralytics/YOLO11
Updated
ā¢
2.56k
ā¢
47
Fatih C. Akyon
fcakyon
AI & ML interests
multi-modal learning, video understanding
Recent Activity
updated
a model
3 days ago
Ultralytics/YOLO11
new activity
3 days ago
hf-vision/object_detection_leaderboard:How to add new model results?
new activity
18 days ago
An-619/FastSAM:Which Ultralytics is being used?
Organizations
fcakyon's activity
updated
a
model
3 days ago
How to add new model results?
#6 opened 3 days ago
by
fcakyon
Which Ultralytics is being used?
#7 opened 20 days ago
by
fcakyon
liked
a
model
19 days ago
liked
a
Space
20 days ago
fix runtime error by adding missing lines
1
#11 opened 20 days ago
by
fcakyon
updated
a
Space
20 days ago
dont clear selected points until `Clear points` button is pressed or input image is changed
#10 opened 20 days ago
by
fcakyon
update to latest gradio for improved ui performance
#9 opened 20 days ago
by
fcakyon
Remove non-used redundant ultralytics folder
#8 opened 20 days ago
by
fcakyon
š© Report: Not working
2
#6 opened 21 days ago
by
fcakyon
Adding `safetensors` variant of this model
#1 opened 29 days ago
by
SFconvertbot
Adding `safetensors` variant of this model
#1 opened 2 months ago
by
SFconvertbot
Adding `safetensors` variant of this model
#1 opened about 2 months ago
by
SFconvertbot
Adding `safetensors` variant of this model
#1 opened about 2 months ago
by
SFconvertbot
confidence score
2
#24 opened about 2 months ago
by
fcakyon
List of All Supported Languages
#76 opened about 2 months ago
by
fcakyon
š© Report: Not working
#1 opened about 2 months ago
by
fcakyon
liked
a
Space
about 2 months ago
reacted to
joaogante's
post with š¤
about 2 months ago
Post
3334
New sampling strategy dropped in š¤ transformers -- Min P sampling š„
Are you tired of having
Min P consists of a dynamic token filter -- as opposed to Top K, which keeps the K most likely tokens, and Top P, which keeps the most likely tokens up to a fixed cumulative probability, both static filters. Min P takes a base probability (defined in the
š High probability token present -> aggressive filter (we don't want to miss on that high-probability case and risk derailing generation)
š No high probability token present -> relaxed filter (there are many continuation possibilities that the model finds plausible)
You should set
Kudos to @kalomaze and @menhguin for creating this technique š„ Read their discussion in the original issue for benchmarks (https://github.com/huggingface/transformers/issues/27670)
Copy-pasteable version of the example in the image below here: https://pastebin.com/VqXNtuxd
Have fun experimenting! š
Are you tired of having
top_k arbitrarily discarding high-quality continuations? Or top_p forgetting to exclude low-probability tokens, derailing your generation? Try out the new min_p flag in generate, fresh from a PR merged today! š„¬Min P consists of a dynamic token filter -- as opposed to Top K, which keeps the K most likely tokens, and Top P, which keeps the most likely tokens up to a fixed cumulative probability, both static filters. Min P takes a base probability (defined in the
min_p flag) and multiplies it by the probability of the most likely token in the distribution for the next token. All tokens less likely than the resulting value are filtered. What happens with this strategy?š High probability token present -> aggressive filter (we don't want to miss on that high-probability case and risk derailing generation)
š No high probability token present -> relaxed filter (there are many continuation possibilities that the model finds plausible)
You should set
min_p to a low value, between 0.05 and 0.1. It behaves particularly well for creative text generation when paired up with temperature > 1.Kudos to @kalomaze and @menhguin for creating this technique š„ Read their discussion in the original issue for benchmarks (https://github.com/huggingface/transformers/issues/27670)
Copy-pasteable version of the example in the image below here: https://pastebin.com/VqXNtuxd
Have fun experimenting! š