Update README.md
Browse files
README.md
CHANGED
|
@@ -11,7 +11,7 @@ pipeline_tag: text-generation
|
|
| 11 |
|
| 12 |
<h1>Llama-3.2-1B-CyberFrog - An Optimized Model for Task Execution Planning in Robotics</h1>
|
| 13 |
|
| 14 |
-
Llama-3.2-1B-CyberFrog is an advanced, lightweight model specifically optimized for task execution planning in robotics. With 1 billion parameters, CyberFrog excels in translating complex natural language instructions into actionable robotic tasks with high efficiency and precision.
|
| 15 |
|
| 16 |
<h2>Strengths:</h2>
|
| 17 |
|
|
@@ -21,7 +21,7 @@ Llama-3.2-1B-CyberFrog is an advanced, lightweight model specifically optimized
|
|
| 21 |
|
| 22 |
<h2>Intended Use:</h2>
|
| 23 |
|
| 24 |
-
<
|
| 25 |
|
| 26 |
+ **Objective** : Allow users to give complex instructions in a single sentence or conversation and have the robot understand and break down the steps autonomously.
|
| 27 |
+ **How it works**: When given a complex instruction like "Get the ingredients for a sandwich and start making it," the LLM can:
|
|
@@ -32,7 +32,7 @@ Llama-3.2-1B-CyberFrog is an advanced, lightweight model specifically optimized
|
|
| 32 |
+ **Use Case**: Warehouse robots, where a user might instruct, "Pick up all items on Shelf B and bring them to Packing Area 2."
|
| 33 |
|
| 34 |
|
| 35 |
-
<
|
| 36 |
|
| 37 |
+ **Objective**: Translate high-level tasks from human language into detailed, actionable robot plans.
|
| 38 |
+ **How it works**: Given a task like "Clean the kitchen," the LLM interprets it by using contextual knowledge to generate subtasks:
|
|
@@ -56,7 +56,7 @@ Llama-3.2-1B-CyberFrog is an advanced, lightweight model specifically optimized
|
|
| 56 |
|
| 57 |
<h2> Usage Examples </h2>
|
| 58 |
|
| 59 |
-
<
|
| 60 |
|
| 61 |
```python
|
| 62 |
from transformers import AutoModelForCausalLM, AutoTokenizer
|
|
|
|
| 11 |
|
| 12 |
<h1>Llama-3.2-1B-CyberFrog - An Optimized Model for Task Execution Planning in Robotics</h1>
|
| 13 |
|
| 14 |
+
***Llama-3.2-1B-CyberFrog*** is an advanced, lightweight model specifically optimized for task execution planning in robotics. With 1 billion parameters, CyberFrog excels in translating complex natural language instructions into actionable robotic tasks with high efficiency and precision.
|
| 15 |
|
| 16 |
<h2>Strengths:</h2>
|
| 17 |
|
|
|
|
| 21 |
|
| 22 |
<h2>Intended Use:</h2>
|
| 23 |
|
| 24 |
+
<h4>Instruction Parsing</h4>
|
| 25 |
|
| 26 |
+ **Objective** : Allow users to give complex instructions in a single sentence or conversation and have the robot understand and break down the steps autonomously.
|
| 27 |
+ **How it works**: When given a complex instruction like "Get the ingredients for a sandwich and start making it," the LLM can:
|
|
|
|
| 32 |
+ **Use Case**: Warehouse robots, where a user might instruct, "Pick up all items on Shelf B and bring them to Packing Area 2."
|
| 33 |
|
| 34 |
|
| 35 |
+
<h4>Task Planning Translation</h4>
|
| 36 |
|
| 37 |
+ **Objective**: Translate high-level tasks from human language into detailed, actionable robot plans.
|
| 38 |
+ **How it works**: Given a task like "Clean the kitchen," the LLM interprets it by using contextual knowledge to generate subtasks:
|
|
|
|
| 56 |
|
| 57 |
<h2> Usage Examples </h2>
|
| 58 |
|
| 59 |
+
<h4> with Huggingface's transformers </h4>
|
| 60 |
|
| 61 |
```python
|
| 62 |
from transformers import AutoModelForCausalLM, AutoTokenizer
|