Instructions to use ntnu-smil/phi-4-mm-lttc-binary-integrated-1964 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ntnu-smil/phi-4-mm-lttc-binary-integrated-1964 with Transformers:

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

pipe = pipeline("text-generation", model="ntnu-smil/phi-4-mm-lttc-binary-integrated-1964", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("ntnu-smil/phi-4-mm-lttc-binary-integrated-1964", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use ntnu-smil/phi-4-mm-lttc-binary-integrated-1964 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ntnu-smil/phi-4-mm-lttc-binary-integrated-1964"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ntnu-smil/phi-4-mm-lttc-binary-integrated-1964",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ntnu-smil/phi-4-mm-lttc-binary-integrated-1964

SGLang

How to use ntnu-smil/phi-4-mm-lttc-binary-integrated-1964 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 "ntnu-smil/phi-4-mm-lttc-binary-integrated-1964" \
    --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": "ntnu-smil/phi-4-mm-lttc-binary-integrated-1964",
		"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 "ntnu-smil/phi-4-mm-lttc-binary-integrated-1964" \
        --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": "ntnu-smil/phi-4-mm-lttc-binary-integrated-1964",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use ntnu-smil/phi-4-mm-lttc-binary-integrated-1964 with Docker Model Runner:
```
docker model run hf.co/ntnu-smil/phi-4-mm-lttc-binary-integrated-1964
```

You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

phi-4-mm-lttc-binary-integrated-1964

This model is a fine-tuned version of ntnu-smil/phi-4-mm-lttc-binary-integrated-1764 on an unknown dataset.

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 2e-06
train_batch_size: 4
eval_batch_size: 4
seed: 42
optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.95) and epsilon=1e-07 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 50
num_epochs: 1