Instructions to use ruijiewang45401/qwen2.5-7b-humanlike-dpo with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ruijiewang45401/qwen2.5-7b-humanlike-dpo with Transformers:

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

pipe = pipeline("text-generation", model="ruijiewang45401/qwen2.5-7b-humanlike-dpo")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ruijiewang45401/qwen2.5-7b-humanlike-dpo")
model = AutoModelForCausalLM.from_pretrained("ruijiewang45401/qwen2.5-7b-humanlike-dpo", 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 ruijiewang45401/qwen2.5-7b-humanlike-dpo with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ruijiewang45401/qwen2.5-7b-humanlike-dpo"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ruijiewang45401/qwen2.5-7b-humanlike-dpo",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ruijiewang45401/qwen2.5-7b-humanlike-dpo

SGLang

How to use ruijiewang45401/qwen2.5-7b-humanlike-dpo 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 "ruijiewang45401/qwen2.5-7b-humanlike-dpo" \
    --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": "ruijiewang45401/qwen2.5-7b-humanlike-dpo",
		"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 "ruijiewang45401/qwen2.5-7b-humanlike-dpo" \
        --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": "ruijiewang45401/qwen2.5-7b-humanlike-dpo",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use ruijiewang45401/qwen2.5-7b-humanlike-dpo with Docker Model Runner:
```
docker model run hf.co/ruijiewang45401/qwen2.5-7b-humanlike-dpo
```

Qwen2.5-7B Human-like DPO

Fine-tuned Qwen2.5-7B-Instruct with DPO for more natural, empathetic conversations.

🚀 Quick Start

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

model = AutoModelForCausalLM.from_pretrained(
    "ruijiewang45401/qwen2.5-7b-humanlike-dpo",
    torch_dtype=torch.bfloat16,
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("ruijiewang45401/qwen2.5-7b-humanlike-dpo")

messages = [
    {"role": "system", "content": "You are a warm and helpful assistant."},
    {"role": "user", "content": "Hello!"}
]

text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = tokenizer(text, return_tensors="pt").to("cuda")

outputs = model.generate(
    **inputs,
    max_new_tokens=200,
    temperature=0.8,
    top_p=0.9,
    do_sample=True
)

print(tokenizer.decode(outputs[0], skip_special_tokens=True))

📊 Training Details

Base Model: Qwen2.5-7B-Instruct
Method: DPO with LoRA (r=16, alpha=32)
Dataset: HumanLLMs/Human-Like-DPO-Dataset
Training Samples: 10,339
Hardware: NVIDIA A100 40GB
Training Time: ~1.5 hours

Hyperparameters

Parameter	Value
Beta	0.1
Learning Rate	5e-5
Batch Size	2 × 8
Max Length	1024
Epochs	1
Optimizer	AdamW
Scheduler	Cosine

Results

Rewards/Margins: 6.87
Accuracy: 1.0
Val Loss: ~0.00003

💡 Generation Parameters

model.generate(
    **inputs,
    max_new_tokens=150-300,
    temperature=0.7-0.9,     # Higher = more natural
    top_p=0.9,
    repetition_penalty=1.1,
    do_sample=True
)

📜 Citation

@misc{qwen25-humanlike-dpo,
  author = {ruijiewang45401},
  title = {Qwen2.5-7B Human-like DPO},
  year = {2025},
  publisher = {Hugging Face},
  url = {https://huggingface.co/ruijiewang45401/qwen2.5-7b-humanlike-dpo}
}

🙏 Credits

Downloads last month: 6

Safetensors

Model size

8B params

Tensor type

BF16

Model tree for ruijiewang45401/qwen2.5-7b-humanlike-dpo

Base model

Qwen/Qwen2.5-7B

Finetuned

Qwen/Qwen2.5-7B-Instruct

Finetuned

(2950)

this model