Runtime error
3
๐
Fatih C. Akyon
fcakyon
AI & ML interests
multi-modal learning, video understanding
Recent Activity
new activity
4 days ago
fcakyon/timesformer-hr-finetuned-k600:Adding `safetensors` variant of this model
new activity
4 days ago
fcakyon/timesformer-base-finetuned-k400:Adding `safetensors` variant of this model
new activity
4 days ago
fcakyon/timesformer-large-finetuned-k400:Adding `safetensors` variant of this model
Organizations
fcakyon's activity
Adding `safetensors` variant of this model
#1 opened 17 days ago
by
SFconvertbot
Adding `safetensors` variant of this model
#1 opened 7 days ago
by
SFconvertbot
Adding `safetensors` variant of this model
#1 opened 4 days ago
by
SFconvertbot
confidence score
2
#24 opened 14 days ago
by
fcakyon
List of All Supported Languages
#76 opened 12 days ago
by
fcakyon
๐ฉ Report: Not working
#1 opened 14 days ago
by
fcakyon
liked
a
Space
14 days ago
reacted to
joaogante's
post with ๐ค
14 days ago
Post
3108
New sampling strategy dropped in ๐ค transformers -- Min P sampling ๐ฅ
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
๐ High probability token present -> aggressive filter (we don't want to miss on that high-probability case and risk derailing generation)
๐ 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 ๐ฅ 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! ๐
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! ๐ฅฌMin 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?๐ High probability token present -> aggressive filter (we don't want to miss on that high-probability case and risk derailing generation)
๐ 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 ๐ฅ 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! ๐
reacted to
joaogante's
post with ๐ฅ
14 days ago
Post
2690
Adding a long prompt can help you fight LLM hallucinations. However, if you know exactly how you want your LLM output constrained, there are much better strategies! ๐ช
Did you know you can force your LLM to ALWAYS generate a valid JSON file? Or to follow a well-defined answer template? You can do that and more with the ๐ค transformers-compatible
It doesn't only allow you to master your LLM -- your text generation application will also become faster! ๐ฅ The more constrained your text generation is, the bigger speedups you'll see!
Follow @remi and other
Did you know you can force your LLM to ALWAYS generate a valid JSON file? Or to follow a well-defined answer template? You can do that and more with the ๐ค transformers-compatible
outlines library.It doesn't only allow you to master your LLM -- your text generation application will also become faster! ๐ฅ The more constrained your text generation is, the bigger speedups you'll see!
Follow @remi and other
outlines folks to stay on top of the constrained generation game ๐ง
add_confidence_score
3
#56 opened 6 months ago
by
haipingwu
updated
a
model
14 days ago
add confidence scores for `od` and `description_with_bboxes` tasks
#25 opened 14 days ago
by
fcakyon
Enable download stats
1
#2 opened 16 days ago
by
merve
Enable download stats
1
#1 opened 16 days ago
by
merve
Update library name
1
#1 opened 16 days ago
by
merve
upvoted
a
paper
18 days ago
๐ฉ Report: Not working
2
#1 opened 25 days ago
by
fcakyon
liked
a
Space
25 days ago
broken link in the model card
1
#99 opened 25 days ago
by
fcakyon
reacted to
merve's
post with ๐ค
30 days ago
Post
3392
Apollo is a new family of open-source video language models by Meta, where 3B model outperforms most 7B models and 7B outperforms most 30B models ๐งถ
โจ the models come in 1.5B https://huggingface.co/Apollo-LMMs/Apollo-1_5B-t32, 3B https://huggingface.co/Apollo-LMMs/Apollo-3B-t32 and 7B https://huggingface.co/Apollo-LMMs/Apollo-7B-t32 with A2.0 license, based on Qwen1.5 & Qwen2
โจ the authors also release a benchmark dataset https://huggingface.co/spaces/Apollo-LMMs/ApolloBench
The paper has a lot of experiments (they trained 84 models!) about what makes the video LMs work โฏ๏ธ
Try the demo for best setup here https://huggingface.co/spaces/Apollo-LMMs/Apollo-3B
they evaluate sampling strategies, scaling laws for models and datasets, video representation and more!
> The authors find out that whatever design decision was applied to small models also scale properly when the model and dataset are scaled ๐ scaling dataset has diminishing returns for smaller models
> They evaluate frame sampling strategies, and find that FPS sampling is better than uniform sampling, and they find 8-32 tokens per frame optimal
> They also compare image encoders, they try a variation of models from shape optimized SigLIP to DINOv2
they find google/siglip-so400m-patch14-384 to be most powerful ๐ฅ
> they also compare freezing different parts of models, training all stages with some frozen parts give the best yield
They eventually release three models, where Apollo-3B outperforms most 7B models and Apollo 7B outperforms 30B models ๐ฅ
โจ the models come in 1.5B https://huggingface.co/Apollo-LMMs/Apollo-1_5B-t32, 3B https://huggingface.co/Apollo-LMMs/Apollo-3B-t32 and 7B https://huggingface.co/Apollo-LMMs/Apollo-7B-t32 with A2.0 license, based on Qwen1.5 & Qwen2
โจ the authors also release a benchmark dataset https://huggingface.co/spaces/Apollo-LMMs/ApolloBench
The paper has a lot of experiments (they trained 84 models!) about what makes the video LMs work โฏ๏ธ
Try the demo for best setup here https://huggingface.co/spaces/Apollo-LMMs/Apollo-3B
they evaluate sampling strategies, scaling laws for models and datasets, video representation and more!
> The authors find out that whatever design decision was applied to small models also scale properly when the model and dataset are scaled ๐ scaling dataset has diminishing returns for smaller models
> They evaluate frame sampling strategies, and find that FPS sampling is better than uniform sampling, and they find 8-32 tokens per frame optimal
> They also compare image encoders, they try a variation of models from shape optimized SigLIP to DINOv2
they find google/siglip-so400m-patch14-384 to be most powerful ๐ฅ
> they also compare freezing different parts of models, training all stages with some frozen parts give the best yield
They eventually release three models, where Apollo-3B outperforms most 7B models and Apollo 7B outperforms 30B models ๐ฅ
-
- 6 replies