Instructions to use pytorch/Phi-4-mini-instruct-INT8-INT4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use pytorch/Phi-4-mini-instruct-INT8-INT4 with Transformers:

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

pipe = pipeline("text-generation", model="pytorch/Phi-4-mini-instruct-INT8-INT4", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("pytorch/Phi-4-mini-instruct-INT8-INT4", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("pytorch/Phi-4-mini-instruct-INT8-INT4", trust_remote_code=True, device_map="auto")
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=256)
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-INT8-INT4 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-INT8-INT4"
# 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-INT8-INT4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/pytorch/Phi-4-mini-instruct-INT8-INT4

SGLang

How to use pytorch/Phi-4-mini-instruct-INT8-INT4 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-INT8-INT4" \
    --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-INT8-INT4",
		"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-INT8-INT4" \
        --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-INT8-INT4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use pytorch/Phi-4-mini-instruct-INT8-INT4 with Docker Model Runner:
```
docker model run hf.co/pytorch/Phi-4-mini-instruct-INT8-INT4
```

metascroy commited on May 2, 2025

Commit

e6eb920

verified ·

1 Parent(s): 0369ded

Update README.md

Browse files

Files changed (1) hide show

README.md +7 -11

README.md CHANGED Viewed

@@ -33,18 +33,11 @@ from transformers import (
   AutoModelForCausalLM,
   AutoProcessor,
   AutoTokenizer,
-  TorchAoConfig,
-)
-from torchao.quantization.quant_api import (
-    IntxWeightOnlyConfig,
-    Int8DynamicActivationIntxWeightConfig,
-    AOPerModuleConfig
 )
-from torchao.quantization.granularity import PerGroup, PerAxis
 import torch
 model_id = "microsoft/Phi-4-mini-instruct"
-untied_model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.float32, device_map="a\uto")
 tokenizer = AutoTokenizer.from_pretrained(model_id)
 print(untied_model)
@@ -54,7 +47,7 @@ if getattr(untied_model.config.get_text_config(decoder=True), "tie_word_embeddin
     setattr(untied_model.config.get_text_config(decoder=True), "tie_word_embeddings", False)
 untied_model._tied_weights_keys = []
-untied_model.lm_head.weight = torch.nn.Parameter(quantized_model.lm_head.weight.clone())
 print("tied weights:", find_tied_parameters(untied_model))
@@ -91,7 +84,6 @@ USER_ID = "YOUR_USER_ID"
 MODEL_NAME = model_id.split("/")[-1]
 untied_model_id = f"{USER_ID}/{MODEL_NAME}-untied-weights"
 embedding_config = IntxWeightOnlyConfig(
     weight_dtype=torch.int8,
     granularity=PerAxis(0),
@@ -101,7 +93,11 @@ linear_config = Int8DynamicActivationIntxWeightConfig(
     weight_granularity=PerGroup(32),
     weight_scale_dtype=torch.bfloat16,
 )
-quantized_model = AutoModelForCausalLM.from_pretrained(untied_model_id, torch_dtype=torch.float32, device_map="auto")
 tokenizer = AutoTokenizer.from_pretrained(model_id)
 # TODO: use AOPerModuleConfig once fix for tied weights is landed

   AutoModelForCausalLM,
   AutoProcessor,
   AutoTokenizer,
 )
 import torch
 model_id = "microsoft/Phi-4-mini-instruct"
+untied_model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype="auto", device_map="auto")
 tokenizer = AutoTokenizer.from_pretrained(model_id)
 print(untied_model)
     setattr(untied_model.config.get_text_config(decoder=True), "tie_word_embeddings", False)
 untied_model._tied_weights_keys = []
+untied_model.lm_head.weight = torch.nn.Parameter(untied_model.lm_head.weight.clone())
 print("tied weights:", find_tied_parameters(untied_model))
 MODEL_NAME = model_id.split("/")[-1]
 untied_model_id = f"{USER_ID}/{MODEL_NAME}-untied-weights"
 embedding_config = IntxWeightOnlyConfig(
     weight_dtype=torch.int8,
     granularity=PerAxis(0),
     weight_granularity=PerGroup(32),
     weight_scale_dtype=torch.bfloat16,
 )
+quant_config = AOPerModuleConfig({"_default": linear_config, "model.embed_tokens": embedding_config})
+quantization_config = TorchAoConfig(quant_type=quant_config, include_embedding=True, untie_embedding_weights=True, modules_to_not_convert=[])
+quantized_model = AutoModelForCausalLM.from_pretrained(untied_model_id, torch_dtype=torch.float32, device_map="auto", quantization_config=quantization_config)
 tokenizer = AutoTokenizer.from_pretrained(model_id)
 # TODO: use AOPerModuleConfig once fix for tied weights is landed