Instructions to use MitakaKuma/VERA-CoWork-27B-1001 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use MitakaKuma/VERA-CoWork-27B-1001 with Transformers:

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

pipe = pipeline("image-text-to-text", model="MitakaKuma/VERA-CoWork-27B-1001")
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)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("MitakaKuma/VERA-CoWork-27B-1001")
model = AutoModelForMultimodalLM.from_pretrained("MitakaKuma/VERA-CoWork-27B-1001", device_map="auto")
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?"}
        ]
    },
]
inputs = processor.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(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use MitakaKuma/VERA-CoWork-27B-1001 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "MitakaKuma/VERA-CoWork-27B-1001"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "MitakaKuma/VERA-CoWork-27B-1001",
		"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/MitakaKuma/VERA-CoWork-27B-1001

SGLang

How to use MitakaKuma/VERA-CoWork-27B-1001 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 "MitakaKuma/VERA-CoWork-27B-1001" \
    --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": "MitakaKuma/VERA-CoWork-27B-1001",
		"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 "MitakaKuma/VERA-CoWork-27B-1001" \
        --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": "MitakaKuma/VERA-CoWork-27B-1001",
		"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 MitakaKuma/VERA-CoWork-27B-1001 with Docker Model Runner:
```
docker model run hf.co/MitakaKuma/VERA-CoWork-27B-1001
```

Request access to VERA

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

Please provide your affiliation and a brief description of your research. Access requests are reviewed manually.

VERA-CoWork-27B-1001

Paper · Website · Code

VERA co-evolves model weights and agent skills in verified environments. This Qwen3.8-27B model targets coding and productivity workflows.

Training scope: VERA post-training uses agentic workflow data only, without dedicated CoWork or medical reasoning datasets. This describes VERA post-training, not the base model’s pretraining. Benchmark scores do not establish clinical expertise. Research use only; not for diagnosis or treatment.

From Qwen to VERA

Qwen and VERA use Codex with xhigh thinking effort. Paper results use Figure 1’s productivity-harness configurations; DeepSWE reference scores use published setups. The animation interpolates measured endpoints, not training steps.

Download video · Static comparison

Video sources: Paper, Figure 1 and published DeepSWE references. Qwen 36.3 and VERA 43.4 on DeepSWE are author-reported Codex xhigh results.

Agent comparisons

Original paper figure: model-size scaling, frontier agents, and transfer benchmarks. Scores describe complete model and harness combinations.

VERA uses its evolved Codex harness. Qwen, DeepSeek, and GPT use Codex v0.153.4; GLM and Claude use Claude Code v2.1.278. All use xhigh effort and each benchmark's scorer. Automation-Bench uses the public 600 tasks (v1.0.6); AgentClinic uses its official simulator.

AutoCoWorkBench: model and harness

Paper Table 3. Default = mini-SWE-agent. Agentic measures workflow quality; Task measures task outcomes. Overall = (Agentic + Task) / 2. These configurations differ from the figure above.

Model	Harness	Overall	Agentic	Task
Qwen3.8-27B	Default	63.8	60.8	66.7
GPT-5.6-Sol	Default	72.6	76.8	68.3
Claude-Opus-4.8	Default	66.6	70.7	62.5
Qwen3.8-27B	VERA	66.4	70.1	62.7
VERA-CoWork-27B	Default	69.6	73.2	65.9
VERA-CoWork-27B	VERA	71.6	73.7	69.4

External benchmarks

Direct model API evaluation against the base model under the same protocol (paper Table 4). AIME and GPQA use zero-shot prompts; ALFWorld retains its TextWorld environment, and IF-Bench uses its official checker.

Benchmark	Qwen3.8-27B	VERA-CoWork-27B	Change (percentage points)
AIME 2026	86.7	96.7	+10.0
ALFWorld	94.0	97.8	+3.8
GPQA-Diamond	82.2	89.9	+7.7
IF-Bench	79.5	81.3	+1.8

Paper evaluation settings

VERA uses SGLang with thinking enabled and preserved, xhigh effort, a 262,144-token context window, and compaction at 200,000 tokens. Harness versions stay fixed throughout evaluation. Benchmark-specific limits apply; Automation-Bench allows 8,192 output tokens and 50 actions. See the paper's Evaluation Protocols and Agent Harness appendix.

Format

Transformers safetensors (BF16), model weights only. This repository excludes optimizer state.

Citation

@misc{liu2026verascalingverifiableenvironments,
  title={VERA: Scaling Verifiable Environments for Agentic co-Evolution},
  author={Junqi Liu and Yongyang Pan and Zhuosong Jiang and Dongbai Li and Bo Zhang and Xitong Ling and Sheng Wang and Hanrong Ye and Yufan He and Can Zhao and Pengfei Guo and Dong Yang and Andriy Myronenko and Yuyin Zhou and Tianyu Liu and Daguang Xu and Yucheng Tang},
  year={2026},
  eprint={2610.05923},
  archivePrefix={arXiv},
  primaryClass={cs.AI},
  url={https://arxiv.org/abs/2610.05923}
}