runningSnail
commited on
Commit
•
0efe51a
1
Parent(s):
218a115
update inference code
Browse files
README.md
CHANGED
@@ -6,17 +6,11 @@ license: cc-by-nc-4.0
|
|
6 |
We're thrilled to introduce the Octopus Planner, the latest breakthrough in on-device language models from Nexa AI. Developed for the Planner-Action Agents Framework, Octopus Planner leverages state-of-the-art technology to enhance AI agents' decision-making processes directly on edge devices. By enabling rapid and efficient planning and action execution without the need for cloud connectivity, this model together with [Octopus-V2](https://huggingface.co/NexaAIDev/Octopus-v2) can work on edge devices locally to support AI Agent usages.
|
7 |
|
8 |
### Key Features of Octopus Planner:
|
9 |
-
- **Efficient Planning**: Utilizes
|
10 |
-
- **
|
|
|
11 |
- **On-device Operation**: Designed for edge devices, ensuring fast response times and enhanced privacy by processing data locally.
|
12 |
-
- **Cost-Effective**: Reduces operational costs by minimizing the key-value cache required, which also improves battery life.
|
13 |
-
- **Fine-tuned**: Extensively fine-tuned on specialized tasks to ensure high accuracy and contextual understanding.
|
14 |
|
15 |
-
## Innovative Framework
|
16 |
-
The Octopus Planner introduces a specialized Planner and Action Agents Framework:
|
17 |
-
- **Dual Model Architecture**: Separates planning and action, allowing for specialized optimization and improved scalability.
|
18 |
-
- **Focused Training**: Employs fine-tuning over traditional long prompting, improving efficiency without sacrificing accuracy.
|
19 |
-
- **Comprehensive Benchmarking**: Includes rigorous in-domain testing to validate the model's effectiveness in real-world scenarios.
|
20 |
|
21 |
## Example Usage
|
22 |
Below is a code snippet to use Octopus Planner:
|
|
|
6 |
We're thrilled to introduce the Octopus Planner, the latest breakthrough in on-device language models from Nexa AI. Developed for the Planner-Action Agents Framework, Octopus Planner leverages state-of-the-art technology to enhance AI agents' decision-making processes directly on edge devices. By enabling rapid and efficient planning and action execution without the need for cloud connectivity, this model together with [Octopus-V2](https://huggingface.co/NexaAIDev/Octopus-v2) can work on edge devices locally to support AI Agent usages.
|
7 |
|
8 |
### Key Features of Octopus Planner:
|
9 |
+
- **Efficient Planning**: Utilizes fine-tuned plan model based on Phi-3 Mini (3.8 billion parameters) for high efficiency and low power consumption.
|
10 |
+
- **Agent Framework**: Separates planning and action, allowing for specialized optimization and improved scalability.
|
11 |
+
- **Enhanced Accuracy**: Achieves a planning success rate of 97% on benchmark dataset, providing reliable and effective performance.
|
12 |
- **On-device Operation**: Designed for edge devices, ensuring fast response times and enhanced privacy by processing data locally.
|
|
|
|
|
13 |
|
|
|
|
|
|
|
|
|
|
|
14 |
|
15 |
## Example Usage
|
16 |
Below is a code snippet to use Octopus Planner:
|
logo.png
ADDED