Instructions to use TuringsSolutions/PhiGlobalFineTunedAgent with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use TuringsSolutions/PhiGlobalFineTunedAgent with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="TuringsSolutions/PhiGlobalFineTunedAgent", trust_remote_code=True)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("TuringsSolutions/PhiGlobalFineTunedAgent", trust_remote_code=True) model = AutoModelForCausalLM.from_pretrained("TuringsSolutions/PhiGlobalFineTunedAgent", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use TuringsSolutions/PhiGlobalFineTunedAgent with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "TuringsSolutions/PhiGlobalFineTunedAgent" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "TuringsSolutions/PhiGlobalFineTunedAgent", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/TuringsSolutions/PhiGlobalFineTunedAgent
- SGLang
How to use TuringsSolutions/PhiGlobalFineTunedAgent with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "TuringsSolutions/PhiGlobalFineTunedAgent" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "TuringsSolutions/PhiGlobalFineTunedAgent", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "TuringsSolutions/PhiGlobalFineTunedAgent" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "TuringsSolutions/PhiGlobalFineTunedAgent", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use TuringsSolutions/PhiGlobalFineTunedAgent with Docker Model Runner:
docker model run hf.co/TuringsSolutions/PhiGlobalFineTunedAgent
metadata
license: mit
datasets:
- TuringsSolutions/GlobalFunctionCallingTrainingSetLarge
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.