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

Libraries

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

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

pipe = pipeline("text-generation", model="kravmar/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("kravmar/llm-course-hw3-lora")
model = AutoModelForCausalLM.from_pretrained("kravmar/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=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

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

Use Docker

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

SGLang

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

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

Model Card for Model ID

Model Details

Model Description

OuteAI/Lite-Oute-1-300M-Instruct finetuned with LoRA on cardiffnlp/tweet_eval dataset for sentiment analysis task. The model predicts class label: negative, neutral or positive.

Training Details

Training Data

cardiffnlp/tweet_eval

Prompt

System prompt:

"You are a sentiment analysis model. Your task is to classify the sentiment of the given text into one of the following categories:

positive: Indicates a favorable or optimistic sentiment. negative: Indicates an unfavorable or pessimistic sentiment. neutral: Indicates a neutral or indifferent sentiment, without any strong emotional tone.

Return ONLY the name of the sentiment class: positive, negative, or neutral. Do NOT output anything else."

Training Hyperparameters

Batch size: 8

Learning rate: 5e-4

Num epochs: 1

0.14% trained parameters

Generation example

User prompt: "Ben Smith / Smith (concussion) remains out of the lineup Thursday, Curtis #NHL #SJ"

True answer: neutral

Model output: neut

Downloads last month: 10

Safetensors

Model size

0.3B params

Tensor type

F32

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

Base model

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

Finetuned

(29)

this model

kravmar
/

llm-course-hw3-lora