Instructions to use comp4cls/comp4cls-4B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use comp4cls/comp4cls-4B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="comp4cls/comp4cls-4B") 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("comp4cls/comp4cls-4B") model = AutoModelForCausalLM.from_pretrained("comp4cls/comp4cls-4B", 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 comp4cls/comp4cls-4B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "comp4cls/comp4cls-4B" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "comp4cls/comp4cls-4B", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/comp4cls/comp4cls-4B
- SGLang
How to use comp4cls/comp4cls-4B 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 "comp4cls/comp4cls-4B" \ --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": "comp4cls/comp4cls-4B", "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 "comp4cls/comp4cls-4B" \ --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": "comp4cls/comp4cls-4B", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use comp4cls/comp4cls-4B with Docker Model Runner:
docker model run hf.co/comp4cls/comp4cls-4B
Update README.md
Browse files
README.md
CHANGED
|
@@ -441,24 +441,16 @@ def comp4cls_pipeline(abstract: str, retrieve_fn, k: int = 10) -> dict:
|
|
| 441 |
|
| 442 |
# Citation
|
| 443 |
|
| 444 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 445 |
|
| 446 |
-
|
| 447 |
|
| 448 |
-
|
| 449 |
|
| 450 |
-
|
| 451 |
-
|
| 452 |
-
[More Information Needed]
|
| 453 |
-
|
| 454 |
-
## More Information [optional]
|
| 455 |
-
|
| 456 |
-
[More Information Needed]
|
| 457 |
-
|
| 458 |
-
## Model Card Authors [optional]
|
| 459 |
-
|
| 460 |
-
[More Information Needed]
|
| 461 |
-
|
| 462 |
-
## Model Card Contact
|
| 463 |
-
|
| 464 |
-
[More Information Needed]
|
|
|
|
| 441 |
|
| 442 |
# Citation
|
| 443 |
|
| 444 |
+
@inproceedings{lim2026comp4cls,
|
| 445 |
+
author = {Lim, C.},
|
| 446 |
+
title = {Comp4Cls: {Semantic Compression} for Enhanced {Retrieval-Augmented Classification} of {Real-World Scientific and Technical Documents}},
|
| 447 |
+
booktitle = {ICDE 2026 (submitted)},
|
| 448 |
+
year = {2026},
|
| 449 |
+
note = {Manuscript submitted for publication}
|
| 450 |
+
}
|
| 451 |
|
| 452 |
+
# Acknowledgements
|
| 453 |
|
| 454 |
+
* **This research was supported by the Korea Institute of Science and Technology Information (KISTI) in 2025 (No. (KISTI) K25L1M1C1), aimed at developing KONI (KISTI Open Neural Intelligence), a large language model specialized in science and technology.
|
| 455 |
|
| 456 |
+
* **This work also benefited from the resources and technical support provided by the National Supercomputing Center (KISTI).
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|