Instructions to use nschenk16/Masterthesis-Qwen2.5-Coder-0.5B-Instruct-1000-SweepResult with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nschenk16/Masterthesis-Qwen2.5-Coder-0.5B-Instruct-1000-SweepResult with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-Coder-0.5B-Instruct")
model = PeftModel.from_pretrained(base_model, "nschenk16/Masterthesis-Qwen2.5-Coder-0.5B-Instruct-1000-SweepResult")

Transformers

How to use nschenk16/Masterthesis-Qwen2.5-Coder-0.5B-Instruct-1000-SweepResult with Transformers:

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

pipe = pipeline("text-generation", model="nschenk16/Masterthesis-Qwen2.5-Coder-0.5B-Instruct-1000-SweepResult")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("nschenk16/Masterthesis-Qwen2.5-Coder-0.5B-Instruct-1000-SweepResult", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use nschenk16/Masterthesis-Qwen2.5-Coder-0.5B-Instruct-1000-SweepResult with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "nschenk16/Masterthesis-Qwen2.5-Coder-0.5B-Instruct-1000-SweepResult"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "nschenk16/Masterthesis-Qwen2.5-Coder-0.5B-Instruct-1000-SweepResult",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/nschenk16/Masterthesis-Qwen2.5-Coder-0.5B-Instruct-1000-SweepResult

SGLang

How to use nschenk16/Masterthesis-Qwen2.5-Coder-0.5B-Instruct-1000-SweepResult 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 "nschenk16/Masterthesis-Qwen2.5-Coder-0.5B-Instruct-1000-SweepResult" \
    --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": "nschenk16/Masterthesis-Qwen2.5-Coder-0.5B-Instruct-1000-SweepResult",
		"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 "nschenk16/Masterthesis-Qwen2.5-Coder-0.5B-Instruct-1000-SweepResult" \
        --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": "nschenk16/Masterthesis-Qwen2.5-Coder-0.5B-Instruct-1000-SweepResult",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use nschenk16/Masterthesis-Qwen2.5-Coder-0.5B-Instruct-1000-SweepResult with Docker Model Runner:
```
docker model run hf.co/nschenk16/Masterthesis-Qwen2.5-Coder-0.5B-Instruct-1000-SweepResult
```

Developed as part of the Master’s thesis “Adaptation and Evaluation of Lightweight LLMs for Structured Output in Ticket Systems” at the University of Paderborn.

PEFT 0.17.0

Downloads last month: 4

Model tree for nschenk16/Masterthesis-Qwen2.5-Coder-0.5B-Instruct-1000-SweepResult

Base model

Qwen/Qwen2.5-0.5B

Finetuned

Qwen/Qwen2.5-Coder-0.5B

Finetuned

Qwen/Qwen2.5-Coder-0.5B-Instruct

Adapter

(45)

this model