Instructions to use kaitchup/Phi-3.5-Mini-instruct-AutoRound-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use kaitchup/Phi-3.5-Mini-instruct-AutoRound-4bit with Transformers:

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

pipe = pipeline("text-generation", model="kaitchup/Phi-3.5-Mini-instruct-AutoRound-4bit", 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("kaitchup/Phi-3.5-Mini-instruct-AutoRound-4bit", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("kaitchup/Phi-3.5-Mini-instruct-AutoRound-4bit", 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=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use kaitchup/Phi-3.5-Mini-instruct-AutoRound-4bit with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "kaitchup/Phi-3.5-Mini-instruct-AutoRound-4bit"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "kaitchup/Phi-3.5-Mini-instruct-AutoRound-4bit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/kaitchup/Phi-3.5-Mini-instruct-AutoRound-4bit

SGLang

How to use kaitchup/Phi-3.5-Mini-instruct-AutoRound-4bit 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 "kaitchup/Phi-3.5-Mini-instruct-AutoRound-4bit" \
    --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": "kaitchup/Phi-3.5-Mini-instruct-AutoRound-4bit",
		"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 "kaitchup/Phi-3.5-Mini-instruct-AutoRound-4bit" \
        --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": "kaitchup/Phi-3.5-Mini-instruct-AutoRound-4bit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use kaitchup/Phi-3.5-Mini-instruct-AutoRound-4bit with Docker Model Runner:
```
docker model run hf.co/kaitchup/Phi-3.5-Mini-instruct-AutoRound-4bit
```

Model Details

This is microsoft/Phi-3.5-mini-instruct quantized with AutoRound to 4-bit and symmetric quantization for compatibility with Marlin. The model has been created, tested, and evaluated by The Kaitchup.

Details on quantization process, evaluation, and how to use the model here: Fine-tuning Phi-3.5 MoE and Mini on Your Computer

Developed by: The Kaitchup
Language(s) (NLP): English
License: cc-by-4.0

Downloads last month: 10

Safetensors

Model size

4B params

Tensor type

I32

F16