Instructions to use nicolay-r/qwen25-05b-multiclinsum-standard with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nicolay-r/qwen25-05b-multiclinsum-standard with Transformers:

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

pipe = pipeline("text-generation", model="nicolay-r/qwen25-05b-multiclinsum-standard")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("nicolay-r/qwen25-05b-multiclinsum-standard")
model = AutoModelForCausalLM.from_pretrained("nicolay-r/qwen25-05b-multiclinsum-standard", 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 nicolay-r/qwen25-05b-multiclinsum-standard with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "nicolay-r/qwen25-05b-multiclinsum-standard"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "nicolay-r/qwen25-05b-multiclinsum-standard",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/nicolay-r/qwen25-05b-multiclinsum-standard

SGLang

How to use nicolay-r/qwen25-05b-multiclinsum-standard 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 "nicolay-r/qwen25-05b-multiclinsum-standard" \
    --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": "nicolay-r/qwen25-05b-multiclinsum-standard",
		"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 "nicolay-r/qwen25-05b-multiclinsum-standard" \
        --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": "nicolay-r/qwen25-05b-multiclinsum-standard",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use nicolay-r/qwen25-05b-multiclinsum-standard with Docker Model Runner:
```
docker model run hf.co/nicolay-r/qwen25-05b-multiclinsum-standard
```

Model Details

Update 13'th July 2025: Added video review on youtube

This model represent a fine-tuned version of Qwen/Qwen2.5-0.5B-Instruct on MultiClinSum training data for BioASQ-2025 Workshop / CLEF 2025.

This model represent a baseline for the distil version:

https://huggingface.co/nicolay-r/qwen25-05b-multiclinsum-distil

Video Overview

Model Description

Model type: Decoder-based Model
Language(s) (NLP): Supported by Qwen2.5 + fine-tuned on summarries written in en, fr, pt, es
License: MIT
Finetuned from model [optional]: https://huggingface.co/Qwen/Qwen2.5-0.5B-Instruct

Model Sources [optional]

Repository: https://github.com/nicolay-r/distil-tuning-llm
Paper: TBA
Demo: https://colab.research.google.com/drive/1TXGaz39o73nBucEQw12gbad7Tw11j2Ol?usp=sharing

Usage

We use bulk-chain for inference with the Qwen2 provider based on transformers pipelines API.

Provider huggingface_qwen.py: https://github.com/nicolay-r/nlp-thirdgate/blob/9e46629792e9a53871710884f7b9e2fe42666aa7/llm/transformers_qwen2.py

from bulk_chain.api import iter_content
from bulk_chain.core.utils import dynamic_init

content_it = iter_content(
  schema={"schema": [
      {"prompt": "Summarize: {input}", "out": "summary"}]
  },
  llm=dynamic_init(
    class_filepath="huggingface_qwen.py",
    class_name="Qwen2")(
      api_token="YOUR_HF_API_KEY_GOES_HERE",
      model_name="nicolay-r/qwen25-05b-multiclinsum-standard",
      temp=0.1,
      use_bf16=True,
      max_new_tokens=args.max_tokens,
      device=args.device
  ),
  infer_mode="batch",
  batch_size=4,
  return_mode="record",
  # INPUT TEXTS:
  input_dicts_it=[
     {"input": "A patient 62 years old with ..."}
  ],
)

for record in content_it:
  # here is the result dictionary that includes summary.
  print(record["summary"])