Instructions to use microsoft/Phi-3.5-MoE-instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use microsoft/Phi-3.5-MoE-instruct with Transformers:

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

pipe = pipeline("text-generation", model="microsoft/Phi-3.5-MoE-instruct", 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("microsoft/Phi-3.5-MoE-instruct", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("microsoft/Phi-3.5-MoE-instruct", 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 microsoft/Phi-3.5-MoE-instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "microsoft/Phi-3.5-MoE-instruct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "microsoft/Phi-3.5-MoE-instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/microsoft/Phi-3.5-MoE-instruct

SGLang

How to use microsoft/Phi-3.5-MoE-instruct 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 "microsoft/Phi-3.5-MoE-instruct" \
    --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": "microsoft/Phi-3.5-MoE-instruct",
		"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 "microsoft/Phi-3.5-MoE-instruct" \
        --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": "microsoft/Phi-3.5-MoE-instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use microsoft/Phi-3.5-MoE-instruct with Docker Model Runner:
```
docker model run hf.co/microsoft/Phi-3.5-MoE-instruct
```

add AIBOM

#55

by sabato-nocera - opened Jun 14, 2025

base: refs/heads/main

←

from: refs/pr/55

Discussion Files changed

+64

-0

Files changed (1) hide show

microsoft_Phi-3.5-MoE-instruct.json +64 -0

microsoft_Phi-3.5-MoE-instruct.json ADDED Viewed

	@@ -0,0 +1,64 @@

+{
+    "bomFormat": "CycloneDX",
+    "specVersion": "1.6",
+    "serialNumber": "urn:uuid:126ceb7e-84e7-4a76-bca4-17482de3dcfa",
+    "version": 1,
+    "metadata": {
+        "timestamp": "2025-06-05T09:39:07.677126+00:00",
+        "component": {
+            "type": "machine-learning-model",
+            "bom-ref": "microsoft/Phi-3.5-MoE-instruct-1ac47922-1ada-5e6b-a387-81986c67b4b0",
+            "name": "microsoft/Phi-3.5-MoE-instruct",
+            "externalReferences": [
+                {
+                    "url": "https://huggingface.co/microsoft/Phi-3.5-MoE-instruct",
+                    "type": "documentation"
+                }
+            ],
+            "modelCard": {
+                "modelParameters": {
+                    "task": "text-generation",
+                    "architectureFamily": "phimoe",
+                    "modelArchitecture": "PhiMoEForCausalLM"
+                },
+                "properties": [
+                    {
+                        "name": "library_name",
+                        "value": "transformers"
+                    }
+                ]
+            },
+            "authors": [
+                {
+                    "name": "microsoft"
+                }
+            ],
+            "licenses": [
+                {
+                    "license": {
+                        "id": "MIT",
+                        "url": "https://spdx.org/licenses/MIT.html"
+                    }
+                }
+            ],
+            "description": "Phi-3.5-MoE is a lightweight, state-of-the-art open model built upon datasets used for Phi-3 - synthetic data and filtered publicly available documents - with a focus on very high-quality, reasoning dense data. The model supports multilingual and comes with 128K context length (in tokens). The model underwent a rigorous enhancement process, incorporating supervised fine-tuning, proximal policy optimization, and direct preference optimization to ensure precise instruction adherence and robust safety measures.\ud83c\udfe1 [Phi-3 Portal](https://azure.microsoft.com/en-us/products/phi-3) <br>\ud83d\udcf0 [Phi-3 Microsoft Blog](https://aka.ms/phi3.5-techblog) <br>\ud83d\udcd6 [Phi-3 Technical Report](https://arxiv.org/abs/2404.14219) <br>\ud83d\udc69\u200d\ud83c\udf73 [Phi-3 Cookbook](https://github.com/microsoft/Phi-3CookBook) <br>\ud83d\udda5\ufe0f [Try It](https://aka.ms/try-phi3.5moe) <br>MoE references:\ud83d\udcdc[Phi-3.5-MoE Blog](https://techcommunity.microsoft.com/t5/ai-azure-ai-services-blog/announcing-the-availability-of-phi-3-5-moe-in-azure-ai-studio/ba-p/4256278) | \ud83d\ude01[GRIN MoE](https://huggingface.co/microsoft/GRIN-MoE)**Phi-3.5**: [[mini-instruct]](https://huggingface.co/microsoft/Phi-3.5-mini-instruct); [[MoE-instruct]](https://huggingface.co/microsoft/Phi-3.5-MoE-instruct) ; [[vision-instruct]](https://huggingface.co/microsoft/Phi-3.5-vision-instruct)",
+            "tags": [
+                "transformers",
+                "safetensors",
+                "phimoe",
+                "text-generation",
+                "nlp",
+                "code",
+                "conversational",
+                "custom_code",
+                "multilingual",
+                "arxiv:2404.14219",
+                "arxiv:2407.13833",
+                "arxiv:2403.06412",
+                "license:mit",
+                "autotrain_compatible",
+                "region:us"
+            ]
+        }
+    }
+}