Instructions to use spankevich/llm-course-hw3-lora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use spankevich/llm-course-hw3-lora with Transformers:

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

pipe = pipeline("text-generation", model="spankevich/llm-course-hw3-lora")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("spankevich/llm-course-hw3-lora")
model = AutoModelForCausalLM.from_pretrained("spankevich/llm-course-hw3-lora")
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 spankevich/llm-course-hw3-lora with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "spankevich/llm-course-hw3-lora"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "spankevich/llm-course-hw3-lora",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/spankevich/llm-course-hw3-lora

SGLang

How to use spankevich/llm-course-hw3-lora 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 "spankevich/llm-course-hw3-lora" \
    --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": "spankevich/llm-course-hw3-lora",
		"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 "spankevich/llm-course-hw3-lora" \
        --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": "spankevich/llm-course-hw3-lora",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use spankevich/llm-course-hw3-lora with Docker Model Runner:
```
docker model run hf.co/spankevich/llm-course-hw3-lora
```

Model Card for Model ID

it was used to fine-tune OuteAI/Lite-Oute-1-300M-Instruct for tweet tone classification problem. Default model achieved 0.08 f1-score, while fine-tuned version achieved 0.53 f1-score in less than 8 minutes of fine-tuning on a single A100

Prameters

LoRA was used with r=8 and alpha=16 to fine-tune "k_proj", "v_proj".

Training parameters

BATCH_SIZE = 128 LEARNING_RATE = 1e-3 NUM_EPOCHS = 1

Metrics

F1 score is 0.53 on a test set

Examples

========== Sorry bout the stream last night I crashed out but will be on tonight for sure. Then back to Minecraft in pc tomorrow night. neutral assistant neutral assistant neutral

========== Chase Headley's RBI double in the 8th inning off David Price snapped a Yankees streak of 33 consecutive scoreless innings against Blue Jays neutral assistant neutral assistant neutral

========== @user Alciato: Bee will invest 150 million in January, another 200 in the Summer and plans to bring Messi by 2017" positive assistant neutral assistant neutral

==========

Downloads last month: -

Safetensors

Model size

0.3B params

Tensor type

F32

Model tree for spankevich/llm-course-hw3-lora

Base model

OuteAI/Lite-Oute-1-300M-Instruct

Finetuned

(29)

this model

Dataset used to train spankevich/llm-course-hw3-lora

Collection including spankevich/llm-course-hw3-lora

llm-hw-3

Collection

Collection of models from the third LLM course homework. It containes three LLMs fine-tuned using LoRA, QLoRA, and DoRA. • 3 items • Updated Mar 29, 2025