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

Libraries

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

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

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

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("WhyZosa/llm-course-hw3-lora")
model = AutoModelForCausalLM.from_pretrained("WhyZosa/llm-course-hw3-lora", 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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

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

Use Docker

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

SGLang

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

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

LoRA · Lite Oute 300M

Дообучил модель на TweetEval определять тональность английских твитов. Поставил LoRA ранга 8 на k_proj и v_proj.

Macro F1 на тесте — 0,522

Примеры с теста

Фрагмент твита	Ответ модели	Метка в датасете
…have to do with anything? They're not even like that.	`neutral`	`neutral`
I think I may be finally in with the in crowd…	`positive`	`positive`
…are running out of heroes.	`positive`	`negative`

Downloads last month: 288

Safetensors

Model size

0.3B params

Tensor type

F32

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

Base model

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

Finetuned

(32)

this model

WhyZosa
/

llm-course-hw3-lora

LoRA · Lite Oute 300M

Примеры с теста

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

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