Instructions to use USS-Inferprise/Phi4-Mini-Prose2Tags-4B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use USS-Inferprise/Phi4-Mini-Prose2Tags-4B with Transformers:

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

pipe = pipeline("text-generation", model="USS-Inferprise/Phi4-Mini-Prose2Tags-4B", 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("USS-Inferprise/Phi4-Mini-Prose2Tags-4B", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("USS-Inferprise/Phi4-Mini-Prose2Tags-4B", 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 USS-Inferprise/Phi4-Mini-Prose2Tags-4B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "USS-Inferprise/Phi4-Mini-Prose2Tags-4B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "USS-Inferprise/Phi4-Mini-Prose2Tags-4B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/USS-Inferprise/Phi4-Mini-Prose2Tags-4B

SGLang

How to use USS-Inferprise/Phi4-Mini-Prose2Tags-4B 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 "USS-Inferprise/Phi4-Mini-Prose2Tags-4B" \
    --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": "USS-Inferprise/Phi4-Mini-Prose2Tags-4B",
		"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 "USS-Inferprise/Phi4-Mini-Prose2Tags-4B" \
        --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": "USS-Inferprise/Phi4-Mini-Prose2Tags-4B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Studio new

How to use USS-Inferprise/Phi4-Mini-Prose2Tags-4B with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for USS-Inferprise/Phi4-Mini-Prose2Tags-4B to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for USS-Inferprise/Phi4-Mini-Prose2Tags-4B to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for USS-Inferprise/Phi4-Mini-Prose2Tags-4B to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="USS-Inferprise/Phi4-Mini-Prose2Tags-4B",
    max_seq_length=2048,
)

Docker Model Runner
How to use USS-Inferprise/Phi4-Mini-Prose2Tags-4B with Docker Model Runner:
```
docker model run hf.co/USS-Inferprise/Phi4-Mini-Prose2Tags-4B
```

Phi4-Mini-Prose2Tags-4B / README.md

USS-Inferprise

Update README.md

5d9db6f verified 24 days ago

preview code

raw

history blame contribute delete

3.13 kB

metadata

license: mit
datasets:
  - USS-Inferprise/Phi4-Mini-Prose2Tags-4B-Raw-Training-Data
language:
  - en
base_model:
  - huihui-ai/Phi-4-mini-instruct-abliterated
tags:
  - text-generation-inference
  - unsloth
  - mergekit
  - danbooru
  - image-captioning
  - tagging
  - phi-4
  - finetune
  - anime
pipeline_tag: text-generation
library_name: transformers

Phi4-Mini-Prose2Tags-4B

This model is a specialized fine-tune designed to translate natural language prose descriptions into structured Danbooru-style tags. It is intended to bridge the gap between human-readable image captions and the tag-based prompting systems used by many latent diffusion models.

Model Details

Developed by: USS-Inferprise
Model Name: Phi4-Mini-Prose2Tags-4B
Base Model: huihui-ai/Phi-4-mini-instruct-abliterated
Training Architecture: LoRA (Low-Rank Adaptation)
Merging Method: Linear Merge (via Mergekit)
Primary Task: Prose-to-Tag Translation

Training Methodology

Dataset Construction

The training data (USS-Inferprise/Phi4-Mini-Prose2Tags-4B-Raw-Training-Data) was generated using a synthetic pipeline:

Source Images: 100,000 images sourced from laion/conceptual-captions-12m-webdataset.
Prose Generation: Images were described using QwenVL.
Tag Generation: Images were tagged using WD 1.3.
Pairing: The resulting QwenVL descriptions and WD 1.3 tags were paired to create the final training instruction set.

⚠️ Safety & Content Note

This model was trained exclusively on a curated subset of data intended for general audiences. No explicit, NSFW, or adult-oriented tags were included in the training dataset (Prose2Tags-4B-Raw-Training-Data).

While the base model (Phi-4-mini-instruct-abliterated) has been modified to reduce certain refusals, this specific fine-tune is designed for clean, descriptive tagging. It may not recognize or accurately generate tags related to explicit content. If it can... it didn't learn it from us.

Training Process

Library: Unsloth
Hardware: NVIDIA L40S
Epochs: 1
Method: LoRA fine-tuning merged into the base model using a Linear merge strategy.

Evaluation & Testing

Testing was performed on 100 images excluded from the training set. To ensure the model generalizes well across different captioning styles, the test inputs used gokaygokay/Florence-2-SD3-Captioner instead of the training-source QwenVL.

Detailed test outputs can be found here: USS-Inferprise/Phi4-Mini-P2T-4B-Testing.

Proper Prompt Format

Warning: You must strictly follow the prompt format below. Failure to do so may result in the model reverting to the standard Phi-4-Mini helpful persona rather than generating tags.

<|user|>
You are a Danbooru tag translator.
{prose_input}<|end|>
<|assistant|>