Update README.md
Browse files
README.md
CHANGED
|
@@ -18,6 +18,11 @@ Greetings from GEM Space, the heart of innovation behind our upcoming paper, "FR
|
|
| 18 |
|
| 19 |
The deployment of On-Device Language Models (ODLMs) on resource-constrained edge devices demands a delicate balance of efficiency, memory, power, and linguistic skill across diverse tasks. In "FRAGILE MASTERY", we explore the trade-offs between domain-specific optimization and cross-domain robustness, introducing the Generalized Edge Model (GEM). GEM integrates specialization and generalization using a Sparse Cross-Attention Router (SCAR), achieving a cross-domain F1 score of 0.89 with sub-100ms latency on platforms like Raspberry Pi 4 and Pixel 6. Across 47 benchmarks spanning eight domains—healthcare, legal, finance, STEM, and more—GEM boosts general-task performance by 7% over GPT-4 Lite while matching domain-specific results. With new metrics like the Domain Specialization Index (DSI) and a balanced distillation framework cutting catastrophic forgetting by 43%, this work offers a robust foundation for edge AI. [Paper link coming soon!]
|
| 20 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 21 |
***Our Vision***:
|
| 22 |
|
| 23 |
At GEM Space, we’re on a mission to revolutionize edge intelligence. We’re striving to build On-Device Language Models that:
|
|
|
|
| 18 |
|
| 19 |
The deployment of On-Device Language Models (ODLMs) on resource-constrained edge devices demands a delicate balance of efficiency, memory, power, and linguistic skill across diverse tasks. In "FRAGILE MASTERY", we explore the trade-offs between domain-specific optimization and cross-domain robustness, introducing the Generalized Edge Model (GEM). GEM integrates specialization and generalization using a Sparse Cross-Attention Router (SCAR), achieving a cross-domain F1 score of 0.89 with sub-100ms latency on platforms like Raspberry Pi 4 and Pixel 6. Across 47 benchmarks spanning eight domains—healthcare, legal, finance, STEM, and more—GEM boosts general-task performance by 7% over GPT-4 Lite while matching domain-specific results. With new metrics like the Domain Specialization Index (DSI) and a balanced distillation framework cutting catastrophic forgetting by 43%, this work offers a robust foundation for edge AI. [Paper link coming soon!]
|
| 20 |
|
| 21 |
+
***Architecture***:
|
| 22 |
+
<div align="center">
|
| 23 |
+
<img src="" width="500px">
|
| 24 |
+
<p><b>Fig: </b><i>Our Architecture simplified</i></p>
|
| 25 |
+
</div>
|
| 26 |
***Our Vision***:
|
| 27 |
|
| 28 |
At GEM Space, we’re on a mission to revolutionize edge intelligence. We’re striving to build On-Device Language Models that:
|