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

Libraries

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

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

pipe = pipeline("text-generation", model="xiryss/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("xiryss/llm-course-hw3-lora")
model = AutoModelForCausalLM.from_pretrained("xiryss/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 xiryss/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 "xiryss/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": "xiryss/llm-course-hw3-lora",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

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

SGLang

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

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

Model Card for llm-course-hw3-lora

This model is a fine-tuned version of OuteAI/Lite-Oute-1-300M-Instruct on the cardiffnlp/tweet_eval dataset to determine tweets tonality in one of the three classes: positive, neutral or negative.

It was finetuned with LoRA to make training more memory and time efficient. Low-rank finetuning was applied only to V and K matrices of attention layers.

Training procedure

This model was trained with batch_size=32, rank = 8, alpha = 16, learning_rate = 1e-5 on cardiffnlp/tweet_eval for one epoch.

The model achieved 0.48 f1-score on the test dataset.

Comparison

Before:

Chase Headley's RBI double in the 8th inning off David Price snapped a Yankees streak of 33 consecutive scoreless innings against Blue Jays -> "The text is positive. \n The text is neutral."

Correct: neutral

After:

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"

Usage

from safetensors.torch import load_file
from huggingface_hub import hf_hub_download


model = AutoModelForCausalLM.from_pretrained(f"{REPO_NAME}-lora", device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(f"{REPO_NAME}-lora")
tokenizer.pad_token = tokenizer.eos_token
tokenizer.padding_side = "left"

apply_peft_to_module(model, LinearWithLoRA, r=8, alpha=16, target_submodules=["v_proj", "k_proj"])
model.to(DEVICE)

path = hf_hub_download(f"{REPO_NAME}-lora", "model.safetensors")
state_dict = load_file(path)

model.load_state_dict(state_dict, strict=False)

LoRA_saved_model_accuracy = eval(model, dataset["test"], tokenizer)
print(f"Accuracy after LoRA training: {LoRA_saved_model_accuracy:.2f}")

Framework versions

Transformers: 4.47.0
Pytorch: 2.5.1+cu121
Datasets: 3.3.1
Tokenizers: 0.21.0

Downloads last month: 1

Safetensors

Model size

0.3B params

Tensor type

F32

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

Base model

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

Finetuned

(29)

this model

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

Collection including xiryss/llm-course-hw3-lora

lm-course-hw3

Collection

A collection of models that were finetuned in hw3 of LLM course in HSE. • 3 items • Updated Mar 29, 2025