Instructions to use pytorch/Phi-4-mini-instruct-parq-2w-4e-shared with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use pytorch/Phi-4-mini-instruct-parq-2w-4e-shared with Transformers:

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

pipe = pipeline("text-generation", model="pytorch/Phi-4-mini-instruct-parq-2w-4e-shared", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("pytorch/Phi-4-mini-instruct-parq-2w-4e-shared", trust_remote_code=True)
model = AutoModelForMultimodalLM.from_pretrained("pytorch/Phi-4-mini-instruct-parq-2w-4e-shared", 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 pytorch/Phi-4-mini-instruct-parq-2w-4e-shared with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "pytorch/Phi-4-mini-instruct-parq-2w-4e-shared"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "pytorch/Phi-4-mini-instruct-parq-2w-4e-shared",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/pytorch/Phi-4-mini-instruct-parq-2w-4e-shared

SGLang

How to use pytorch/Phi-4-mini-instruct-parq-2w-4e-shared 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 "pytorch/Phi-4-mini-instruct-parq-2w-4e-shared" \
    --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": "pytorch/Phi-4-mini-instruct-parq-2w-4e-shared",
		"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 "pytorch/Phi-4-mini-instruct-parq-2w-4e-shared" \
        --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": "pytorch/Phi-4-mini-instruct-parq-2w-4e-shared",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use pytorch/Phi-4-mini-instruct-parq-2w-4e-shared with Docker Model Runner:
```
docker model run hf.co/pytorch/Phi-4-mini-instruct-parq-2w-4e-shared
```

lvj commited on Dec 4, 2025

Commit

b56721a

1 Parent(s): 8aeab33

Upload folder using huggingface_hub

Browse files

Files changed (3) hide show

.gitattributes +2 -0
config.json +27 -11
training_args.bin +0 -0

.gitattributes ADDED Viewed

	@@ -0,0 +1,2 @@


1	+ pytorch_model.bin filter=lfs diff=lfs merge=lfs -text
2	+ tokenizer.json filter=lfs diff=lfs merge=lfs -text

config.json CHANGED Viewed

@@ -129,25 +129,41 @@
             },
             "model.embed_tokens": {
               "_data": {
-                "activation_quantization": "int8_asym_per_token",
-                "b": 2,
-                "granularity": {
                   "_data": {
                     "axis": 0
                   },
                   "_type": "PerAxis",
                   "_version": 1
                 },
-                "layout": {
-                  "_data": {},
-                  "_type": "QDQLayout",
-                  "_version": 1
                 },
-                "quant_max": 1.5,
-                "quant_min": -1.5,
-                "scale_dtype": null
               },
-              "_type": "StretchedIntxWeightConfig",
               "_version": 2
             }
           }

             },
             "model.embed_tokens": {
               "_data": {
+                "act_mapping_type": {
+                  "_data": "ASYMMETRIC",
+                  "_type": "MappingType"
+                },
+                "intx_choose_qparams_algorithm": {
+                  "_data": "AFFINE",
+                  "_type": "IntxChooseQParamsAlgorithm"
+                },
+                "intx_packing_format": {
+                  "_data": "UNPACKED_TO_INT8",
+                  "_type": "IntxPackingFormat"
+                },
+                "layout": {
+                  "_data": {},
+                  "_type": "QDQLayout",
+                  "_version": 1
+                },
+                "weight_dtype": {
+                  "_data": "int4",
+                  "_type": "torch.dtype"
+                },
+                "weight_granularity": {
                   "_data": {
                     "axis": 0
                   },
                   "_type": "PerAxis",
                   "_version": 1
                 },
+                "weight_mapping_type": {
+                  "_data": "SYMMETRIC",
+                  "_type": "MappingType"
                 },
+                "weight_scale_dtype": null
               },
+              "_type": "Int8DynamicActivationIntxWeightConfig",
               "_version": 2
             }
           }

training_args.bin CHANGED Viewed

Binary files a/training_args.bin and b/training_args.bin differ