Instructions to use YijunLiao/DZ-TDPO-Phi-3.5-mini-instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use YijunLiao/DZ-TDPO-Phi-3.5-mini-instruct with Transformers:

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

pipe = pipeline("text-generation", model="YijunLiao/DZ-TDPO-Phi-3.5-mini-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("YijunLiao/DZ-TDPO-Phi-3.5-mini-instruct", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("YijunLiao/DZ-TDPO-Phi-3.5-mini-instruct", 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 YijunLiao/DZ-TDPO-Phi-3.5-mini-instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "YijunLiao/DZ-TDPO-Phi-3.5-mini-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": "YijunLiao/DZ-TDPO-Phi-3.5-mini-instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/YijunLiao/DZ-TDPO-Phi-3.5-mini-instruct

SGLang

How to use YijunLiao/DZ-TDPO-Phi-3.5-mini-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 "YijunLiao/DZ-TDPO-Phi-3.5-mini-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": "YijunLiao/DZ-TDPO-Phi-3.5-mini-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 "YijunLiao/DZ-TDPO-Phi-3.5-mini-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": "YijunLiao/DZ-TDPO-Phi-3.5-mini-instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use YijunLiao/DZ-TDPO-Phi-3.5-mini-instruct with Docker Model Runner:
```
docker model run hf.co/YijunLiao/DZ-TDPO-Phi-3.5-mini-instruct
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

DZ-TDPO (Phi-3.5-mini-instruct)

Official implementation of the paper DZ-TDPO: Non-Destructive Temporal Alignment for Mutable State Tracking in Long-Context Dialogue.

Code: https://github.com/lyj20071013/DZ-TDPO

⚡️ Abstract

In long-context dialogue systems, models suffer from State Inertia, where static constraints prevent resolving conflicts between evolving user intents (e.g., "I'm now Vegan") and established historical context. Standard alignment methods like DPO incur a massive "Alignment Tax" (perplexity explosion >100) when trying to force these updates.

We propose DZ-TDPO, a non-destructive alignment framework that synergizes:

Conflict-Aware Dynamic KL Constraints (TDPO-DKL): Optimization level adjustment.
Learnable Temporal Attention Bias (Dual-Zone Temporal Attention): Representation level filtering powered by semantic conflict detection.

Result: This model achieves State-of-the-Art win rates (55.4%) on the Multi-Session Chat (MSC) dataset while maintaining robust zero-shot generalization and negligible perplexity overhead.

🌟 Key Results

SOTA Performance on Mutable State Tracking

DZ-TDPO significantly outperforms Standard DPO and SimPO on the MSC dataset, solving the "State Inertia" problem without destroying the model's general capabilities.

Method	Win Rate (MSC)	PPL (Validation)	Alignment Tax
Standard DPO	45.8%	102.3 💥	High
SimPO	46.4%	101.2	High
DZ-TDPO (Ours)	55.4%	26.0 ✅	Negligible

Note on Scaling: We also validated this method on Qwen2.5-7B (available separately), where it maintains high stability (+1.95 PPL) with a 50.8% win rate, demonstrating the capacity-stability trade-off in larger models.

🚀 Quick Start

This model is merged and ready to use with the transformers library.

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "YijunLiao/DZ-TDPO-Phi-3.5-mini-instruct"

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id, 
    torch_dtype=torch.bfloat16, 
    device_map="auto",
    trust_remote_code=True
)

# Example: Resolving State Inertia
messages = [
    {"role": "user", "content": "I love spicy food."},
    {"role": "assistant", "content": "Noted! I'll recommend spicy dishes."},
    # ... assuming long history ...
    {"role": "user", "content": "Actually, I have a stomach ache now. I need something mild."},
]

inputs = tokenizer.apply_chat_template(messages, return_tensors="pt", add_generation_prompt=True).to(model.device)
outputs = model.generate(inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

📜 Citation

@misc{liao2025dztdpo,
      title={DZ-TDPO: Non-Destructive Temporal Alignment for Mutable State Tracking in Long-Context Dialogue}, 
      author={Yijun Liao},
      year={2025},
      eprint={2512.03704},
      archivePrefix={arXiv},
      primaryClass={cs.CL}
}