Instructions to use dmitry315/llm-course-hw2-dpo with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use dmitry315/llm-course-hw2-dpo with Transformers:

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

pipe = pipeline("text-generation", model="dmitry315/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("dmitry315/llm-course-hw2-dpo")
model = AutoModelForCausalLM.from_pretrained("dmitry315/llm-course-hw2-dpo")
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 dmitry315/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 "dmitry315/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": "dmitry315/llm-course-hw2-dpo",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/dmitry315/llm-course-hw2-dpo

SGLang

How to use dmitry315/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 "dmitry315/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": "dmitry315/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 "dmitry315/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": "dmitry315/llm-course-hw2-dpo",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use dmitry315/llm-course-hw2-dpo with Docker Model Runner:
```
docker model run hf.co/dmitry315/llm-course-hw2-dpo
```

Model Card for Model ID

LLM trained with DPO for VK NLP course.

Model Details

Model Description

The model is LLM HuggingFaceTB/SmolLM-135M-Instruct.

Model trained with DPO procedure.

Model Sources

Pretrained Model: HuggingFaceTB/SmolLM-135M-Instruct
Train Data: HumanLLMs/Human-Like-DPO-Dataset

Getting start

device = torch.device("cuda")

tokenizer = AutoTokenizer.from_pretrained("dmitry315/llm-course-hw2-dpo")
check_model = AutoModelForCausalLM.from_pretrained("dmitry315/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").to(device)

generated_ids = check_model.generate(model_inputs.input_ids, max_new_tokens=256, do_sample=False)
response = tokenizer.decode(generated_ids, skip_special_tokens=True)[0]
print(response)
# > My morning routine typically involves starting with a gentle stretch to calm my mind, then moving to my morning exercise routine to power through my day.

Downloads last month: 1

Safetensors

Model size

0.1B params

Tensor type

F32

Collection including dmitry315/llm-course-hw2-dpo

VK LLM

Collection

LLM models trained for VK course. • 9 items • Updated May 28, 2025