Instructions to use tsinghua-sigs-robot-lab/VeriLoop-E2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tsinghua-sigs-robot-lab/VeriLoop-E2 with Transformers:

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

pipe = pipeline("text-generation", model="tsinghua-sigs-robot-lab/VeriLoop-E2")
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("tsinghua-sigs-robot-lab/VeriLoop-E2")
model = AutoModelForMultimodalLM.from_pretrained("tsinghua-sigs-robot-lab/VeriLoop-E2", 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 tsinghua-sigs-robot-lab/VeriLoop-E2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "tsinghua-sigs-robot-lab/VeriLoop-E2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tsinghua-sigs-robot-lab/VeriLoop-E2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/tsinghua-sigs-robot-lab/VeriLoop-E2

SGLang

How to use tsinghua-sigs-robot-lab/VeriLoop-E2 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 "tsinghua-sigs-robot-lab/VeriLoop-E2" \
    --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": "tsinghua-sigs-robot-lab/VeriLoop-E2",
		"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 "tsinghua-sigs-robot-lab/VeriLoop-E2" \
        --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": "tsinghua-sigs-robot-lab/VeriLoop-E2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use tsinghua-sigs-robot-lab/VeriLoop-E2 with Docker Model Runner:
```
docker model run hf.co/tsinghua-sigs-robot-lab/VeriLoop-E2
```

Existing quants are too heavy 😭

by highpolygonal - opened 15 days ago

Discussion

highpolygonal

15 days ago

Hello, could you please create a version suitable for graphics cards with 12GB of VRAM? Something like GSQ-RCO, for example. I think many people would be very grateful. Thank you for your work!

tahaalam2009

15 days ago

this is just benchmaxxed ai slop probably stick to base model.

NikiKrutan

15 days ago

Hello, could you please create a version suitable for graphics cards with 12GB of VRAM? Something like GSQ-RCO, for example. I think many people would be very grateful. Thank you for your work!

https://huggingface.co/NikiKrutan/VeriLoop-E2-MTP-GGUF

this is just benchmaxxed ai slop probably stick to base model.

Probably so, but seems to be good from my first impression. Short focused reasoning, job is done faster. Feels very different from the base.

Throghar

15 days ago

•

edited 15 days ago

this is just benchmaxxed ai slop probably stick to base model.

The benchmark results were obtained with they're own harness, i am trying to replicate it as pi extension with general rules they provided on model card and technical list. While testing it i am kinda getting why they managed to obtain so high scores, the workflow has some real benefits and if harness enforces them and model is trained for it i see real results.

tahaalam2009

14 days ago

this is just benchmaxxed ai slop probably stick to base model.

The benchmark results were obtained with they're own harness, i am trying to replicate it as pi extension with general rules they provided on model card and technical list. While testing it i am kinda getting why they managed to obtain so high scores, the workflow has some real benefits and if harness enforces them and model is trained for it i see real results.

How did you do it? share please

rodrigoramosrs

14 days ago

Hello, could you please create a version suitable for graphics cards with 12GB of VRAM? Something like GSQ-RCO, for example. I think many people would be very grateful. Thank you for your work!

https://huggingface.co/rodrigoramosrs/veriloop-coder-e2-nvfp4

tahaalam2009

12 days ago

Hello, could you please create a version suitable for graphics cards with 12GB of VRAM? Something like GSQ-RCO, for example. I think many people would be very grateful. Thank you for your work!

here you go i did it https://huggingface.co/tahaalam2009/VeriLoop-E2-GSQ-RCO-GGUF

eugene-kamenev

10 days ago

Do not want to open new thread. Battle tested this model in GGUF Q4 today. It is very good. I am thinking to switch from Qwen3.8-Flash-Next to this one.

Thank you for this finetune!

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment