Faster Text Generation with Self-Speculative Decoding
•
58
AI at Meta
Enterprise
company
Verified
AI & ML interests
None defined yet.
Recent Activity
Articles
facebook's activity
levineds2
updated
2
models
about 18 hours ago
zulissimeta
updated
a
Space
1 day ago
clefourrier
posted
an
update
20 days ago
Post
614
Always surprised that so few people actually read the FineTasks blog, on
✨how to select training evals with the highest signal✨
If you're serious about training models without wasting compute on shitty runs, you absolutely should read it!!
An high signal eval actually tells you precisely, during training, how wel & what your model is learning, allowing you to discard the bad runs/bad samplings/...!
The blog covers in depth prompt choice, metrics, dataset, across languages/capabilities, and my fave section is "which properties should evals have"👌
(to know on your use case how to select the best evals for you)
Blog: HuggingFaceFW/blogpost-fine-tasks
✨how to select training evals with the highest signal✨
If you're serious about training models without wasting compute on shitty runs, you absolutely should read it!!
An high signal eval actually tells you precisely, during training, how wel & what your model is learning, allowing you to discard the bad runs/bad samplings/...!
The blog covers in depth prompt choice, metrics, dataset, across languages/capabilities, and my fave section is "which properties should evals have"👌
(to know on your use case how to select the best evals for you)
Blog: HuggingFaceFW/blogpost-fine-tasks
-
- 2 replies
Tianlu
authored
a
paper
22 days ago
PereLluis13
authored
a
paper
about 1 month ago
mmaaz60
authored
5
papers
about 2 months ago
SwiftFormer: Efficient Additive Attention for Transformer-based Real-time Mobile Vision Applications
Paper
•
2303.15446
•
Published
•
1
EdgeNeXt: Efficiently Amalgamated CNN-Transformer Architecture for Mobile Vision Applications
Paper
•
2206.10589
•
Published
MaPLe: Multi-modal Prompt Learning
Paper
•
2210.03117
•
Published
VideoGPT+: Integrating Image and Video Encoders for Enhanced Video Understanding
Paper
•
2406.09418
•
Published
•
1
Fine-tuned CLIP Models are Efficient Video Learners
Paper
•
2212.03640
•
Published
•
1
tennant
authored
a
paper
about 2 months ago
mmaaz60
authored
2
papers
about 2 months ago
tennant
authored
a
paper
about 2 months ago
Benjamin-eecs
authored
a
paper
about 2 months ago
oliu-io
authored
a
paper
2 months ago
Tianlu
authored
a
paper
2 months ago
tshenaa
authored
a
paper
3 months ago
mghazvininejad
authored
a
paper
3 months ago