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

Libraries

How to use elliotthwangmsa/Phi-4-mini-instruct-tw with Transformers:

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

pipe = pipeline("text-generation", model="elliotthwangmsa/Phi-4-mini-instruct-tw", 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("elliotthwangmsa/Phi-4-mini-instruct-tw", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("elliotthwangmsa/Phi-4-mini-instruct-tw", 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 elliotthwangmsa/Phi-4-mini-instruct-tw with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/elliotthwangmsa/Phi-4-mini-instruct-tw

SGLang

How to use elliotthwangmsa/Phi-4-mini-instruct-tw 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 "elliotthwangmsa/Phi-4-mini-instruct-tw" \
    --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": "elliotthwangmsa/Phi-4-mini-instruct-tw",
		"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 "elliotthwangmsa/Phi-4-mini-instruct-tw" \
        --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": "elliotthwangmsa/Phi-4-mini-instruct-tw",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use elliotthwangmsa/Phi-4-mini-instruct-tw with Docker Model Runner:
```
docker model run hf.co/elliotthwangmsa/Phi-4-mini-instruct-tw
```

elliotthwangmsa commited on Oct 13, 2025

Commit

515d2e2

verified ·

1 Parent(s): 0f8ef96

Upload Phi3ForCausalLM

Browse files

Files changed (2) hide show

model-00001-of-00002.safetensors +1 -1
model-00002-of-00002.safetensors +1 -1

model-00001-of-00002.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:133b429c6ab4193a002e9a2127238926b33c11dace993cb8d9b9ea333083ea87
 size 4903637712

 version https://git-lfs.github.com/spec/v1
+oid sha256:426122229afbc6818545a962d4695c8ee1f65e297cb2c06f8338e68afa0fd0b8
 size 4903637712

model-00002-of-00002.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c11558ccddd3b37062686ad03bbb035db52afd7edaaa02f0a650ede671afb36
 size 2768428504

 version https://git-lfs.github.com/spec/v1
+oid sha256:854d1396779750cc1216fc3dcd4c8e1afde3584978a6cf8321fa1b3e9ed21b47
 size 2768428504