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

Libraries

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

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

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

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ErazerControl/Phi-4-mini-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": "ErazerControl/Phi-4-mini-instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

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

SGLang

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

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

ErazerControl commited on Aug 28, 2025

Commit

fa87fe3

verified ·

1 Parent(s): 296867d

Update modeling_phi3.py

Browse files

Files changed (1) hide show

modeling_phi3.py +1 -2

modeling_phi3.py CHANGED Viewed

@@ -35,7 +35,6 @@ from transformers.modeling_rope_utils import ROPE_INIT_FUNCTIONS
 from transformers.modeling_utils import ALL_ATTENTION_FUNCTIONS, PreTrainedModel
 from transformers.processing_utils import Unpack
 from transformers.utils import (
-    LossKwargs,
     add_code_sample_docstrings,
     add_start_docstrings,
     add_start_docstrings_to_model_forward,
@@ -817,7 +816,7 @@ class Phi3Model(Phi3PreTrainedModel):
         return causal_mask
-class KwargsForCausalLM(FlashAttentionKwargs, LossKwargs): ...
 class Phi3ForCausalLM(Phi3PreTrainedModel, GenerationMixin):

 from transformers.modeling_utils import ALL_ATTENTION_FUNCTIONS, PreTrainedModel
 from transformers.processing_utils import Unpack
 from transformers.utils import (
     add_code_sample_docstrings,
     add_start_docstrings,
     add_start_docstrings_to_model_forward,
         return causal_mask
+class KwargsForCausalLM(FlashAttentionKwargs): ...
 class Phi3ForCausalLM(Phi3PreTrainedModel, GenerationMixin):