Instructions to use microsoft/Phi-3-mini-4k-instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use microsoft/Phi-3-mini-4k-instruct with Transformers:

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

pipe = pipeline("text-generation", model="microsoft/Phi-3-mini-4k-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("microsoft/Phi-3-mini-4k-instruct", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("microsoft/Phi-3-mini-4k-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]:]))

Inference
Local Apps Settings

vLLM

How to use microsoft/Phi-3-mini-4k-instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "microsoft/Phi-3-mini-4k-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": "microsoft/Phi-3-mini-4k-instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/microsoft/Phi-3-mini-4k-instruct

SGLang

How to use microsoft/Phi-3-mini-4k-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 "microsoft/Phi-3-mini-4k-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": "microsoft/Phi-3-mini-4k-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 "microsoft/Phi-3-mini-4k-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": "microsoft/Phi-3-mini-4k-instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use microsoft/Phi-3-mini-4k-instruct with Docker Model Runner:
```
docker model run hf.co/microsoft/Phi-3-mini-4k-instruct
```

The model stops after generating one new token

#76

by rajiv-data-chef - opened Jun 29, 2024

Discussion

rajiv-data-chef

Jun 29, 2024

The LLM just generated one new token (?) and stopped . It is behaving like this repeatedly.
Have I missed something from my side ?

Load model directly

import flash_attn
from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("microsoft/Phi-3-mini-4k-instruct", trust_remote_code=True)
phi_model = AutoModelForCausalLM.from_pretrained("microsoft/Phi-3-mini-4k-instruct", trust_remote_code=True)
%%time
device = 'cuda'
phi_model.to(device)

def get_ids_sigIn_password_email(get_ids_sigIn_pass_email_prompt):
inputs = tokenizer.encode(get_ids_sigIn_pass_email_prompt, return_tensors="pt").to(device)

Find the index where the generated tokens start

input_length = len(tokenizer.encode(get_ids_sigIn_pass_email_prompt))
print(f"input_length -> {input_length}")

Generate a response

phi_model.eval()
outputs = phi_model.generate(inputs, max_new_tokens= 500)
print(f"shape of output is {outputs[0].shape}")
full_decoded_output = tokenizer.decode(outputs[0], skip_special_tokens=True)

decoded_output = full_decoded_output
return decoded_output
out_f2=get_ids_sigIn_password_email("write a paragraph about What is the meaning of life")
print(out_f2)

input_length -> 11
shape of output is torch.Size([13])
write a paragraph about What is the meaning of life?

rajiv-data-chef

Jun 29, 2024

I solved it using the prompt style mentioned in the documentation.
All I had to do was to use tokens <|user|> and <|assistant|> in such manner :
prompt_our_side = f"""<|user|>
{prompt}
<|assistant|>
"""

amgadhasan

Jul 22, 2024

I solved it using the prompt style mentioned in the documentation.
All I had to do was to use tokens <|user|> and <|assistant|> in such manner :
prompt_our_side = f"""<|user|>
{prompt}
<|assistant|>
"""

Please close this issue as it has been resolved.

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment