Instructions to use pankajmathur/orca_mini_phi-4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use pankajmathur/orca_mini_phi-4 with Transformers:

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

pipe = pipeline("text-generation", model="pankajmathur/orca_mini_phi-4")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("pankajmathur/orca_mini_phi-4")
model = AutoModelForCausalLM.from_pretrained("pankajmathur/orca_mini_phi-4")
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 pankajmathur/orca_mini_phi-4 with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/pankajmathur/orca_mini_phi-4

SGLang

How to use pankajmathur/orca_mini_phi-4 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 "pankajmathur/orca_mini_phi-4" \
    --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": "pankajmathur/orca_mini_phi-4",
		"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 "pankajmathur/orca_mini_phi-4" \
        --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": "pankajmathur/orca_mini_phi-4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use pankajmathur/orca_mini_phi-4 with Docker Model Runner:
```
docker model run hf.co/pankajmathur/orca_mini_phi-4
```

pankajmathur commited on Jan 21, 2025

Commit

3425326

verified ·

1 Parent(s): fc8e887

Update README.md

Browse files

Files changed (1) hide show

README.md +5 -5

README.md CHANGED Viewed

@@ -10,9 +10,9 @@ base_model:
 library_name: transformers
 ---
-# Model Name: orca_mini_v9_2_14B
-**orca_mini_v9_2_14B is trained with various SFT Datasets on [microsoft/phi-4](https://huggingface.co/microsoft/phi-4) using Llama's architecture.**
 <img src="https://huggingface.co/pankajmathur/orca_mini_v5_8b/resolve/main/orca_minis_small.jpeg" width="auto" />
@@ -56,7 +56,7 @@ Below shows a code example on how to use this model in default half precision (b
 import torch
 from transformers import pipeline
-model_slug = "pankajmathur/orca_mini_v9_2_14B"
 pipeline = pipeline(
     "text-generation",
     model=model_slug,
@@ -76,7 +76,7 @@ Below shows a code example on how to use this model in 4-bit format via bitsandb
 import torch
 from transformers import BitsAndBytesConfig, pipeline
-model_slug = "pankajmathur/orca_mini_v9_2_14B"
 quantization_config = BitsAndBytesConfig(
     load_in_4bit=True,
     bnb_4bit_quant_type="nf4",
@@ -104,7 +104,7 @@ Below shows a code example on how to use this model in 8-bit format via bitsandb
 import torch
 from transformers import BitsAndBytesConfig, pipeline
-model_slug = "pankajmathur/orca_mini_v9_2_14B"
 quantization_config = BitsAndBytesConfig(
     load_in_8bit=True
 )

 library_name: transformers
 ---
+# Model Name: orca_mini_phi-4
+**orca_mini_phi-4 is trained with various SFT Datasets on [microsoft/phi-4](https://huggingface.co/microsoft/phi-4) using Llama's architecture.**
 <img src="https://huggingface.co/pankajmathur/orca_mini_v5_8b/resolve/main/orca_minis_small.jpeg" width="auto" />
 import torch
 from transformers import pipeline
+model_slug = "pankajmathur/orca_mini_phi-4"
 pipeline = pipeline(
     "text-generation",
     model=model_slug,
 import torch
 from transformers import BitsAndBytesConfig, pipeline
+model_slug = "pankajmathur/orca_mini_phi-4"
 quantization_config = BitsAndBytesConfig(
     load_in_4bit=True,
     bnb_4bit_quant_type="nf4",
 import torch
 from transformers import BitsAndBytesConfig, pipeline
+model_slug = "pankajmathur/orca_mini_phi-4"
 quantization_config = BitsAndBytesConfig(
     load_in_8bit=True
 )