Edit model card

Trained for 45 minutes (3 Epochs on single T4 GPU)

Sample Inputs and Outputs

Instruction: Book me a flight from New York to Los Angeles next Tuesday

for a business trip."

Rationale 1: Search for flights from New York to Los Angeles on the specified date.

Action 1: invoke_flight_search

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"}]}

Rationale 2: Two flight options found, let's compare them.

Action 2: Display flight options

Observation

My computer is running slowly. Can you help me fix it?

It's affecting my work."

Rationale 1: Assess the computer's performance and identify potential issues.

Action 1: invoke_computer_diagnostics

Observation 1: {"diagnostics": ["Overheating", "Memory Leaks"]}

Rationale 2: Overheating and memory leaks detected.

Action 2: suggest_cooling_tips

Observation 2: {"tips": ["Clean the cooling fans", "Update the operating system"]}

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."

Observation 3: User follows the tips

Rationale 3: User's computer performance improves

Action 3: confirm_improvement

Observation 3: {"improvement_confirmed": true}

Answer: "I'm

"What's the traffic like on my way to work?"

We need to plan our commute accordingly," suggested Sarah.

Rationale 1: Checking the traffic conditions to plan the commute.

Action 1: invoke_traffic_api

Observation 1: {"traffic_status": "Heavy", "congestion_level": "High"}

Rationale 2: Heavy traffic, congestion level is high.

Action 2: Suggest alternative routes

Observation 2: {"alternative_routes": ["Take the expressway", "Use the back roads"]}

Answer: I suggest taking the expressway or using the back roads to avoid heavy traffic. Would you like me to provide directions?

Observation 3: User selects "Use the back roads"

Answer: Great choice! The back roads will help you bypass the heavy traffic. Let me know if you need further assistance.

Rationale 3: User selects

Downloads last month
20
Safetensors
Model size
2.78B params
Tensor type
FP16
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Dataset used to train TuringsSolutions/PhiGlobalFineTunedAgent