Instructions to use EmergentMethods/Phi-3-mini-4k-instruct-graph with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use EmergentMethods/Phi-3-mini-4k-instruct-graph with Transformers:

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

pipe = pipeline("text-generation", model="EmergentMethods/Phi-3-mini-4k-instruct-graph", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("EmergentMethods/Phi-3-mini-4k-instruct-graph", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("EmergentMethods/Phi-3-mini-4k-instruct-graph", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use EmergentMethods/Phi-3-mini-4k-instruct-graph with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "EmergentMethods/Phi-3-mini-4k-instruct-graph"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "EmergentMethods/Phi-3-mini-4k-instruct-graph",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/EmergentMethods/Phi-3-mini-4k-instruct-graph

SGLang

How to use EmergentMethods/Phi-3-mini-4k-instruct-graph 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 "EmergentMethods/Phi-3-mini-4k-instruct-graph" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "EmergentMethods/Phi-3-mini-4k-instruct-graph",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "EmergentMethods/Phi-3-mini-4k-instruct-graph" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "EmergentMethods/Phi-3-mini-4k-instruct-graph",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use EmergentMethods/Phi-3-mini-4k-instruct-graph with Docker Model Runner:
```
docker model run hf.co/EmergentMethods/Phi-3-mini-4k-instruct-graph
```

Numpy Compatibility Error

by neilac333 - opened Jan 20, 2025

Discussion

neilac333

Jan 20, 2025

Getting the following running the exact notebook in the model card on Python 3.12 locally:

"A module that was compiled using NumPy 1.x cannot be run in
NumPy 2.2.2 as it may crash. To support both 1.x and 2.x
versions of NumPy, modules must be compiled with NumPy 2.0.
Some module may need to rebuild instead e.g. with 'pybind11>=2.12'.

If you are a user of the module, the easiest solution will be to
downgrade to 'numpy<2' or try to upgrade the affected module.
We expect that some modules will need time to support NumPy 2."

Please let me know if a Python downgrade or some other environmental tweak would work. Thanks.

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment