Instructions to use tiny-random/phi-moe with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tiny-random/phi-moe with Transformers:

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

pipe = pipeline("text-generation", model="tiny-random/phi-moe", 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("tiny-random/phi-moe", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("tiny-random/phi-moe", 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 tiny-random/phi-moe with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/tiny-random/phi-moe

SGLang

How to use tiny-random/phi-moe 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 "tiny-random/phi-moe" \
    --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": "tiny-random/phi-moe",
		"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 "tiny-random/phi-moe" \
        --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": "tiny-random/phi-moe",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use tiny-random/phi-moe with Docker Model Runner:
```
docker model run hf.co/tiny-random/phi-moe
```

yujiepan commited on Jun 25, 2025

Commit

694d6fb

verified ·

1 Parent(s): 192e289

Upload folder using huggingface_hub

Browse files

Files changed (2) hide show

README.md +0 -3
model.safetensors +2 -2

README.md CHANGED Viewed

@@ -81,9 +81,6 @@ automap = config_json['auto_map']
 torch.set_default_dtype(torch.bfloat16)
 model = AutoModelForCausalLM.from_config(config, trust_remote_code=True)
 torch.set_default_dtype(torch.float32)
-# according to source model, gat is in FP32
-for i in range(config.num_hidden_layers):
-    model.model.layers[i].block_sparse_moe.gate.float()
 if file_exists(filename="generation_config.json", repo_id=source_model_id, repo_type='model'):
     model.generation_config = GenerationConfig.from_pretrained(
         source_model_id, trust_remote_code=True,

 torch.set_default_dtype(torch.bfloat16)
 model = AutoModelForCausalLM.from_config(config, trust_remote_code=True)
 torch.set_default_dtype(torch.float32)
 if file_exists(filename="generation_config.json", repo_id=source_model_id, repo_type='model'):
     model.generation_config = GenerationConfig.from_pretrained(
         source_model_id, trust_remote_code=True,

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bdf2f1fe515fa0b55cc3be523a7e19a36d27053254bfcdf6f0ecada43c393bcd
-size 5018960

 version https://git-lfs.github.com/spec/v1
+oid sha256:9144a495919a7e8bac13b7687422122068d55741598d5ff13648df632158603a
+size 5016928