Instructions to use DataKensei/phi-2-function-calling with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use DataKensei/phi-2-function-calling with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="DataKensei/phi-2-function-calling")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("DataKensei/phi-2-function-calling")
model = AutoModelForCausalLM.from_pretrained("DataKensei/phi-2-function-calling")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use DataKensei/phi-2-function-calling with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "DataKensei/phi-2-function-calling"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "DataKensei/phi-2-function-calling",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/DataKensei/phi-2-function-calling

SGLang

How to use DataKensei/phi-2-function-calling 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 "DataKensei/phi-2-function-calling" \
    --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": "DataKensei/phi-2-function-calling",
		"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 "DataKensei/phi-2-function-calling" \
        --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": "DataKensei/phi-2-function-calling",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use DataKensei/phi-2-function-calling with Docker Model Runner:
```
docker model run hf.co/DataKensei/phi-2-function-calling
```

cgrodrigues commited on Aug 18, 2024

Commit

06cae33

verified ·

1 Parent(s): 83501d4

Update README.md

Browse files

Files changed (1) hide show

README.md +6 -8

README.md CHANGED Viewed

@@ -165,25 +165,22 @@ The model was evaluated using a separate test set, comprising 10% of the origina
 <!-- Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). -->
-\usepackage{hyperref}
-\subsection{CO2 Emission Related to Experiments}
 Experiments were conducted using a private infrastructure, which has a carbon efficiency of 0.432 kgCO$_2$eq/kWh. A cumulative of 10 hours of computation was performed on hardware of type GTX 1080 (TDP of 180W).
-Total emissions are estimated to be 0.78 kgCO$_2$eq of which 0 percents were directly offset.
-%Uncomment if you bought additional offsets:
-%XX kg CO2eq were manually offset through \href{link}{Offset Provider}.
-Estimations were conducted using the \href{https://mlco2.github.io/impact#compute}{MachineLearning Impact calculator} presented in \cite{lacoste2019quantifying}.
 @article{lacoste2019quantifying,
   title={Quantifying the Carbon Emissions of Machine Learning},
   author={Lacoste, Alexandre and Luccioni, Alexandra and Schmidt, Victor and Dandres, Thomas},
   journal={arXiv preprint arXiv:1910.09700},
   year={2019}
 }
 - **Hardware Type:** NVIDIA GPUs (GTX 1080)
@@ -214,7 +211,7 @@ The training used PyTorch and the Hugging Face Transformers library, with additi
 <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
 **BibTeX:**
 @misc{phi2functioncalling,
   title={phi-2-function-calling},
   author={Carlos Rodrigues},
@@ -222,6 +219,7 @@ The training used PyTorch and the Hugging Face Transformers library, with additi
   publisher={Hugging Face},
   howpublished={\url{https://huggingface.co/DataKensei/phi-2-function-calling}},
 }
 ## Model Card Contact

 <!-- Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). -->
 Experiments were conducted using a private infrastructure, which has a carbon efficiency of 0.432 kgCO$_2$eq/kWh. A cumulative of 10 hours of computation was performed on hardware of type GTX 1080 (TDP of 180W).
+Total emissions are estimated to be 0.78 kgCO of which 0 percents were directly offset.
+Estimations were conducted using the [MachineLearning Impact calculator](https://mlco2.github.io/impact#compute) presented in presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700)
+```
 @article{lacoste2019quantifying,
   title={Quantifying the Carbon Emissions of Machine Learning},
   author={Lacoste, Alexandre and Luccioni, Alexandra and Schmidt, Victor and Dandres, Thomas},
   journal={arXiv preprint arXiv:1910.09700},
   year={2019}
 }
+```
 - **Hardware Type:** NVIDIA GPUs (GTX 1080)
 <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
 **BibTeX:**
+```
 @misc{phi2functioncalling,
   title={phi-2-function-calling},
   author={Carlos Rodrigues},
   publisher={Hugging Face},
   howpublished={\url{https://huggingface.co/DataKensei/phi-2-function-calling}},
 }
+```
 ## Model Card Contact