Instructions to use aifeifei798/Phi-3-song-lyrics-1.1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use aifeifei798/Phi-3-song-lyrics-1.1 with Transformers:

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

pipe = pipeline("text-generation", model="aifeifei798/Phi-3-song-lyrics-1.1", 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("aifeifei798/Phi-3-song-lyrics-1.1", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("aifeifei798/Phi-3-song-lyrics-1.1", 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 aifeifei798/Phi-3-song-lyrics-1.1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "aifeifei798/Phi-3-song-lyrics-1.1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "aifeifei798/Phi-3-song-lyrics-1.1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/aifeifei798/Phi-3-song-lyrics-1.1

SGLang

How to use aifeifei798/Phi-3-song-lyrics-1.1 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 "aifeifei798/Phi-3-song-lyrics-1.1" \
    --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": "aifeifei798/Phi-3-song-lyrics-1.1",
		"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 "aifeifei798/Phi-3-song-lyrics-1.1" \
        --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": "aifeifei798/Phi-3-song-lyrics-1.1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use aifeifei798/Phi-3-song-lyrics-1.1 with Docker Model Runner:
```
docker model run hf.co/aifeifei798/Phi-3-song-lyrics-1.1
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Model Description

This model is a specialized model, specifically designed for writing song lyrics. Phi-3 has a built-in mechanism to reduce rejection, so please use the default_lm_studio_windows in LM Studio.
The generated lyrics may be a bit long, so please modify them yourself. If you don't modify them, I'll assume you're using the modified version, and the generated content is not related to the model :p
lease handle the generated content yourself, as the model does not guarantee anything about - the generated content. If any copyright issues arise, please handle them yourself.
Thanks to aifeifei799 for creating the lora
I just integrated aifeifei799's LORA, so if you have any issues, please contact aifeifei799 :p
The model strictly follows the MIT license.

Model Set

download GGUF file
set LM Studio https://lmstudio.ai/
https://huggingface.co/aifeifei798/Phi-3-song-lyrics-1.1-Q8_0-GGUF

Model Test Prompt

"Please write song lyrics with the following structure: Intro-Verse-Chorus-Verse-Chorus-Bridge-Chorus-Outro.Rewrite an English love song in English, give me the title, complete lyrics, and style of the song, without translation or phonetic notation, with emotional and heartfelt lyrics. Here's a breakdown of each section:
song name:
Style of Music:
Intro:
Verse 1:
Chorus:
Verse 2:
Chorus:
Bridge:
Chorus:
Outro:

Downloads last month: 14

Safetensors

Model size

4B params

Tensor type

BF16

Model tree for aifeifei798/Phi-3-song-lyrics-1.1

Quantizations

1 model