Instructions to use SujiKim/learnweak-evocua-8b-lora-r32-thunderbird with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use SujiKim/learnweak-evocua-8b-lora-r32-thunderbird with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("meituan/EvoCUA-8B-20260105")
model = PeftModel.from_pretrained(base_model, "SujiKim/learnweak-evocua-8b-lora-r32-thunderbird")

Transformers

How to use SujiKim/learnweak-evocua-8b-lora-r32-thunderbird with Transformers:

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

pipe = pipeline("image-text-to-text", model="SujiKim/learnweak-evocua-8b-lora-r32-thunderbird")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("SujiKim/learnweak-evocua-8b-lora-r32-thunderbird", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use SujiKim/learnweak-evocua-8b-lora-r32-thunderbird with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "SujiKim/learnweak-evocua-8b-lora-r32-thunderbird"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SujiKim/learnweak-evocua-8b-lora-r32-thunderbird",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/SujiKim/learnweak-evocua-8b-lora-r32-thunderbird

SGLang

How to use SujiKim/learnweak-evocua-8b-lora-r32-thunderbird 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 "SujiKim/learnweak-evocua-8b-lora-r32-thunderbird" \
    --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": "SujiKim/learnweak-evocua-8b-lora-r32-thunderbird",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

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 "SujiKim/learnweak-evocua-8b-lora-r32-thunderbird" \
        --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": "SujiKim/learnweak-evocua-8b-lora-r32-thunderbird",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use SujiKim/learnweak-evocua-8b-lora-r32-thunderbird with Docker Model Runner:
```
docker model run hf.co/SujiKim/learnweak-evocua-8b-lora-r32-thunderbird
```

learnweak-evocua-8b-lora-r32-gimp

This repository contains a LoRA adapter for meituan/EvoCUA-8B-20260105 specialized for the GIMP software domain using the LearnWeak framework.

LearnWeak is an annotation-free specialization framework for small computer-use agents (CUAs) introduced in the paper Learn from Weaknesses: Automated Domain Specialization for Small Computer-Use Agents. It identifies a student model's weaknesses in a target domain using a stronger reference agent (teacher), synthesizes targeted tasks, and constructs automated supervision to improve performance.

Project Page: https://learnweak.github.io/
Repository: https://github.com/sujiikim/LearnWeak
Paper: https://huggingface.co/papers/2605.28775

Usage

Serve with vLLM

You can serve this adapter alongside the base model using vLLM by enabling LoRA support:

vllm serve meituan/EvoCUA-8B-20260105 \
  --enable-lora \
  --max-lora-rank 32 \
  --lora-modules learnweak-gimp=SujiKim/learnweak-evocua-8b-lora-r32-gimp

Use the LoRA module name learnweak-gimp when calling the served model's API.

Training Details

LearnWeak specializes small computer-use agents for target desktop domains by identifying student weaknesses, generating targeted practice tasks, and training from teacher/student trajectory differences. This specific checkpoint focuses on the GIMP domain.

Citation

If you find this work useful, please consider citing:

@article{kim2026learnweaknessesautomateddomain,
  title   = {Learn from Weaknesses: Automated Domain Specialization for Small Computer-Use Agents},
  author  = {Kim, Suji and Kim, Kangsa and Hwang, Sung Ju},
  journal = {arXiv preprint arXiv:2605.28775},
  year    = {2026}
}

Acknowledgments

This project builds on OSWorld, LlamaFactory, and EvoCUA.

Downloads last month: 6

Model tree for SujiKim/learnweak-evocua-8b-lora-r32-thunderbird

Base model

meituan/EvoCUA-8B-20260105

Adapter

(8)

this model

Paper for SujiKim/learnweak-evocua-8b-lora-r32-thunderbird

Learn from Weaknesses: Automated Domain Specialization for Small Computer-Use Agents

Paper • 2605.28775 • Published May 27 • 38