Instructions to use efromomr/llm-course-hw2-dpo with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use efromomr/llm-course-hw2-dpo with Transformers:

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

pipe = pipeline("text-generation", model="efromomr/llm-course-hw2-dpo")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("efromomr/llm-course-hw2-dpo")
model = AutoModelForCausalLM.from_pretrained("efromomr/llm-course-hw2-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 efromomr/llm-course-hw2-dpo with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "efromomr/llm-course-hw2-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": "efromomr/llm-course-hw2-dpo",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/efromomr/llm-course-hw2-dpo

SGLang

How to use efromomr/llm-course-hw2-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 "efromomr/llm-course-hw2-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": "efromomr/llm-course-hw2-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 "efromomr/llm-course-hw2-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": "efromomr/llm-course-hw2-dpo",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use efromomr/llm-course-hw2-dpo with Docker Model Runner:
```
docker model run hf.co/efromomr/llm-course-hw2-dpo
```

Model Card for Model ID

Model Details

Model Description

This model is an aligned version of HuggingFaceTB/SmolLM-135M-Instruct. Method used for training is DPO.

Reward accuracy on training dataset is 99.89.

Example of usage

DEVICE = torch.device("cuda")
tokenizer = AutoTokenizer.from_pretrained(efromomr/llm-course-hw2-dpo)
check_model = AutoModelForCausalLM.from_pretrained(efromomr/llm-course-hw2-dpo)
check_model = check_model.to(DEVICE)
check_model = check_model.eval()

messages = [{"role": "user", "content": "What's your morning routine like?"}]
text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
model_inputs = tokenizer([text], return_tensors="pt")

generated_ids = model.generate(model_inputs.input_ids.to(DEVICE), max_new_tokens=256, do_sample=True)
response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]

#Hey, I'm excited to start my morning! I remember being in a rush, feeling my heart beat like a tiny muscle, and working like a team. So, I started with breakfast, so was my whole day! 🍕

#I chose chia seeds because of their crunchy texture and the protein they's got so easy to digest. Then, I added a healthy protein drink of spinach, almonds, and a sprinkle of hemp seeds, which is a really healthy combo! I started drinking a whole serving and got caught by the caffeine kick start, about an hour later! 🍉

#And finally, I started reading this good article on breakfast habits, so I set a goal (5 servings a day would be a good goal for me 😊). I was more than happy to follow along, so I headed to the fridge to grab that last few slices of toast! 🗺️

#As for coffee, I was blown away! It was a good 5, kinda right! My coffee was great with my pancakes, too. 🍕

#And that's it! You're out of the coffee rush. 🍕

Downloads last month: 9

Safetensors

Model size

0.1B params

Tensor type

F32

Dataset used to train efromomr/llm-course-hw2-dpo

Collection including efromomr/llm-course-hw2-dpo

LLM_course_hw2

Collection

A collection of repos for second homework. • 3 items • Updated Mar 9, 2025