Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
datasets:
|
| 4 |
+
- TuringsSolutions/GlobalFunctionCallingTrainingSetLarge
|
| 5 |
+
---
|
| 6 |
+
Trained for 45 minutes (3 Epochs on single T4 GPU)
|
| 7 |
+
|
| 8 |
+
Sample Inputs and Outputs
|
| 9 |
+
|
| 10 |
+
Instruction: Book me a flight from New York to Los Angeles next Tuesday
|
| 11 |
+
|
| 12 |
+
for a business trip."
|
| 13 |
+
### Rationale 1: Search for flights from New York to Los Angeles on the specified date.
|
| 14 |
+
### Action 1: invoke_flight_search
|
| 15 |
+
### Observation 1: {"flights": [{"departure_city": "New York", "arrival_city": "Los Angeles", "departure_date": "2022-02-10", "arrival_date": "2022-02-12", "price": "$500"}, {"departure_city": "New York", "arrival_city": "Los Angeles", "departure_date": "2022-02-11", "arrival_date": "2022-02-13", "price": "$550"}]}
|
| 16 |
+
### Rationale 2: Two flight options found, let's compare them.
|
| 17 |
+
### Action 2: Display flight options
|
| 18 |
+
### Observation
|
| 19 |
+
|
| 20 |
+
My computer is running slowly. Can you help me fix it?
|
| 21 |
+
|
| 22 |
+
It's affecting my work."
|
| 23 |
+
### Rationale 1: Assess the computer's performance and identify potential issues.
|
| 24 |
+
### Action 1: invoke_computer_diagnostics
|
| 25 |
+
### Observation 1: {"diagnostics": ["Overheating", "Memory Leaks"]}
|
| 26 |
+
### Rationale 2: Overheating and memory leaks detected.
|
| 27 |
+
### Action 2: suggest_cooling_tips
|
| 28 |
+
### Observation 2: {"tips": ["Clean the cooling fans", "Update the operating system"]}
|
| 29 |
+
### Answer: "To improve your computer's performance, I recommend cleaning the cooling fans and updating the operating system. Let me know if you need further assistance."
|
| 30 |
+
### Observation 3: User follows the tips
|
| 31 |
+
### Rationale 3: User's computer performance improves
|
| 32 |
+
### Action 3: confirm_improvement
|
| 33 |
+
### Observation 3: {"improvement_confirmed": true}
|
| 34 |
+
### Answer: "I'm
|
| 35 |
+
|
| 36 |
+
"What's the traffic like on my way to work?"
|
| 37 |
+
|
| 38 |
+
We need to plan our commute accordingly," suggested Sarah.
|
| 39 |
+
### Rationale 1: Checking the traffic conditions to plan the commute.
|
| 40 |
+
### Action 1: invoke_traffic_api
|
| 41 |
+
### Observation 1: {"traffic_status": "Heavy", "congestion_level": "High"}
|
| 42 |
+
### Rationale 2: Heavy traffic, congestion level is high.
|
| 43 |
+
### Action 2: Suggest alternative routes
|
| 44 |
+
### Observation 2: {"alternative_routes": ["Take the expressway", "Use the back roads"]}
|
| 45 |
+
### Answer: I suggest taking the expressway or using the back roads to avoid heavy traffic. Would you like me to provide directions?
|
| 46 |
+
### Observation 3: User selects "Use the back roads"
|
| 47 |
+
### Answer: Great choice! The back roads will help you bypass the heavy traffic. Let me know if you need further assistance.
|
| 48 |
+
### Rationale 3: User selects
|