Instructions to use SeacomSrl/SeaPhi3-mini with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use SeacomSrl/SeaPhi3-mini with Transformers:

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

pipe = pipeline("text-generation", model="SeacomSrl/SeaPhi3-mini", 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("SeacomSrl/SeaPhi3-mini", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("SeacomSrl/SeaPhi3-mini", 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

vLLM

How to use SeacomSrl/SeaPhi3-mini with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "SeacomSrl/SeaPhi3-mini"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SeacomSrl/SeaPhi3-mini",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/SeacomSrl/SeaPhi3-mini

SGLang

How to use SeacomSrl/SeaPhi3-mini 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 "SeacomSrl/SeaPhi3-mini" \
    --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": "SeacomSrl/SeaPhi3-mini",
		"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 "SeacomSrl/SeaPhi3-mini" \
        --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": "SeacomSrl/SeaPhi3-mini",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use SeacomSrl/SeaPhi3-mini with Docker Model Runner:
```
docker model run hf.co/SeacomSrl/SeaPhi3-mini
```

SeaPhi3-mini

Commit History

Update README.md

e9b1bd8
verified

nonsonpratico commited on Jun 6, 2024

Update README.md

75e12e7
verified

nonsonpratico commited on Jun 6, 2024

Update README.md

b21f30c
verified

nonsonpratico commited on May 31, 2024

Update README.md

a177cdf
verified

Riccardo Toti commited on Apr 29, 2024

Update README.md

47f2e5f
verified

Riccardo Toti commited on Apr 29, 2024

Upload tokenizer

bf08941
verified

Riccardo Toti commited on Apr 29, 2024

Upload Phi3ForCausalLM

0b23172
verified

Riccardo Toti commited on Apr 29, 2024

initial commit

0884279
verified

Riccardo Toti commited on Apr 29, 2024

Commit History

Update README.md e9b1bd8 verified

Update README.md 75e12e7 verified

Update README.md b21f30c verified

Update README.md a177cdf verified

Update README.md 47f2e5f verified

Upload tokenizer bf08941 verified

Upload Phi3ForCausalLM 0b23172 verified

initial commit 0884279 verified

Update README.md

e9b1bd8
verified

Update README.md

75e12e7
verified

Update README.md

b21f30c
verified

Update README.md

a177cdf
verified

Update README.md

47f2e5f
verified

Upload tokenizer

bf08941
verified

Upload Phi3ForCausalLM

0b23172
verified

initial commit

0884279
verified