welyjesch commited on
Commit
2ff617d
·
verified ·
1 Parent(s): 88f0111

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +5 -0
README.md CHANGED
@@ -11,6 +11,10 @@ pinned: false
11
 
12
  This organization is dedicated to the development of high-performance natural language processing (NLP) architectures for the major and regional languages of the Philippines. Our objective is to bridge the digital divide for low-resource languages through state-of-the-art model alignment, knowledge distillation, and the deployment of efficient, edge-ready AI models.
13
 
 
 
 
 
14
  ## Technical Roadmap
15
 
16
  ### Phase 1: Foundation Model Alignment and NMT Parity
@@ -28,6 +32,7 @@ This organization is dedicated to the development of high-performance natural la
28
  * **Technical Detail:** Transitioning from standard Transformers to LFM 2.5 allows for linear scaling and reduced memory footprints. We use the distilled datasets from Phase 2 to train "Student" models that replicate the output distribution of the larger Llama models. Final optimization includes Direct Preference Optimization (DPO) to refine cultural and grammatical nuance for each specific language.
29
  * **Milestone:** A suite of specialized, deployment-ready models (1.2B to 3B parameters) optimized for edge computing and local hardware integration.
30
 
 
31
  ---
32
 
33
  ## Stakeholder Engagement and Collaboration
 
11
 
12
  This organization is dedicated to the development of high-performance natural language processing (NLP) architectures for the major and regional languages of the Philippines. Our objective is to bridge the digital divide for low-resource languages through state-of-the-art model alignment, knowledge distillation, and the deployment of efficient, edge-ready AI models.
13
 
14
+
15
+ <details>
16
+ <summary>Click to view our Technical Roadmap </summary>
17
+
18
  ## Technical Roadmap
19
 
20
  ### Phase 1: Foundation Model Alignment and NMT Parity
 
32
  * **Technical Detail:** Transitioning from standard Transformers to LFM 2.5 allows for linear scaling and reduced memory footprints. We use the distilled datasets from Phase 2 to train "Student" models that replicate the output distribution of the larger Llama models. Final optimization includes Direct Preference Optimization (DPO) to refine cultural and grammatical nuance for each specific language.
33
  * **Milestone:** A suite of specialized, deployment-ready models (1.2B to 3B parameters) optimized for edge computing and local hardware integration.
34
 
35
+ </details>
36
  ---
37
 
38
  ## Stakeholder Engagement and Collaboration