Image-Text-to-Text
PEFT
Safetensors
lora
egocentric-video
proactive-assistant
streaming-video
eccv-2026
wearable-ai
video-qa
conversational
Instructions to use ambient-intelligence-labs/egoproactive-2b-lora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use ambient-intelligence-labs/egoproactive-2b-lora with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3.5-2B") model = PeftModel.from_pretrained(base_model, "ambient-intelligence-labs/egoproactive-2b-lora") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -9,12 +9,15 @@ tags:
|
|
| 9 |
- egocentric-video
|
| 10 |
- proactive-assistant
|
| 11 |
- streaming-video
|
|
|
|
|
|
|
|
|
|
| 12 |
---
|
| 13 |
|
| 14 |
# EgoProactive 2B — proactive assistant verbalizer (LoRA)
|
| 15 |
|
| 16 |
LoRA adapter for **Qwen/Qwen3.5-2B**, from Team Ambient's entry to the **EgoProactive** track of the
|
| 17 |
-
[Wearable AI Challenge @ ECCV 2026](https://wearable-ai-workshop.github.io/) — **2nd place, ≤2B division**.
|
| 18 |
|
| 19 |
| | |
|
| 20 |
|---|---|
|
|
@@ -85,4 +88,4 @@ gradient checkpointing, 1 epoch.
|
|
| 85 |
institution = {Team Ambient},
|
| 86 |
note = {Wearable AI Challenge @ ECCV 2026, EgoProactive track}
|
| 87 |
}
|
| 88 |
-
```
|
|
|
|
| 9 |
- egocentric-video
|
| 10 |
- proactive-assistant
|
| 11 |
- streaming-video
|
| 12 |
+
- eccv-2026
|
| 13 |
+
- wearable-ai
|
| 14 |
+
- video-qa
|
| 15 |
---
|
| 16 |
|
| 17 |
# EgoProactive 2B — proactive assistant verbalizer (LoRA)
|
| 18 |
|
| 19 |
LoRA adapter for **Qwen/Qwen3.5-2B**, from Team Ambient's entry to the **EgoProactive** track of the
|
| 20 |
+
[Wearable AI Challenge @ ECCV 2026](https://wearable-ai-workshop.github.io/) — 🥈 **2nd place, ≤2B division**.
|
| 21 |
|
| 22 |
| | |
|
| 23 |
|---|---|
|
|
|
|
| 88 |
institution = {Team Ambient},
|
| 89 |
note = {Wearable AI Challenge @ ECCV 2026, EgoProactive track}
|
| 90 |
}
|
| 91 |
+
```
|