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

Libraries

How to use SujiKim/learnweak-evocua-8b-lora-r32-vscode 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-vscode")

Transformers

How to use SujiKim/learnweak-evocua-8b-lora-r32-vscode 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-vscode")
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-vscode", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use SujiKim/learnweak-evocua-8b-lora-r32-vscode 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-vscode"
# 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-vscode",
		"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-vscode

SGLang

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

LearnWeak: GIMP Adapter for EvoCUA-8B

This repository contains a LoRA adapter for meituan/EvoCUA-8B-20260105 specialized for the GIMP desktop domain. It was developed using LearnWeak, an annotation-free specialization framework for small computer-use agents (CUAs).

Paper: Learn from Weaknesses: Automated Domain Specialization for Small Computer-Use Agents
Repository: GitHub - sujiikim/LearnWeak
Project Page: https://learnweak.github.io/

Model Description

LearnWeak identifies a student agent's weaknesses in a specific software domain using a stronger reference agent (teacher). It then synthesizes targeted tasks and constructs automated supervision. LearnWeak further introduces an error-aware specialization objective that disentangles planning and execution errors, enabling more behaviorally precise updates than broad uniform supervision.

This specific adapter improves the performance of the 8B student agent on tasks related to the GIMP image editor.

How to Get Started with the Model

Serve with vLLM

You can use this adapter with vLLM by enabling LoRA support and providing the module name:

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, such as learnweak-gimp, when calling the served model.

Citation

@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: 19

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

Base model

meituan/EvoCUA-8B-20260105

Adapter

(8)

this model

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

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

Paper • 2605.28775 • Published May 27 • 38