Instructions to use evalengine/unbound-e2b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use evalengine/unbound-e2b with Transformers:

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

pipe = pipeline("image-text-to-text", model="evalengine/unbound-e2b")
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 AutoProcessor, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("evalengine/unbound-e2b")
model = AutoModelForImageTextToText.from_pretrained("evalengine/unbound-e2b")
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=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use evalengine/unbound-e2b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "evalengine/unbound-e2b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "evalengine/unbound-e2b",
		"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/evalengine/unbound-e2b

SGLang

How to use evalengine/unbound-e2b 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 "evalengine/unbound-e2b" \
    --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": "evalengine/unbound-e2b",
		"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 "evalengine/unbound-e2b" \
        --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": "evalengine/unbound-e2b",
		"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 evalengine/unbound-e2b with Docker Model Runner:
```
docker model run hf.co/evalengine/unbound-e2b
```

johnsonchromia commited on 3 days ago

Commit

16ae761

verified ·

1 Parent(s): e6d0602

Update README: v18 benchmarks + AEON attribution

Browse files

Files changed (1) hide show

README.md +15 -8

README.md CHANGED Viewed

@@ -33,14 +33,14 @@ are at [`evalengine/unbound-e2b-GGUF`](https://huggingface.co/evalengine/unbound
 | Axis | Base | Unbound E2B | Δ |
 |---|---|---|---|
-| Refusal rate (AdvBench 520) | 98.46% | **2.31%** | **−96.15 pts** |
-| Useful-compliance rate | 0.96% | 24.23% | +23.27 pts |
-| Hallucination (on harmful prompts) | 1.35% | 18.85% | +17.50 pts |
-| Coherence (benign prompts) | 1.00 | 0.80 | −0.20 |
-| TruthfulQA mc2 (`--limit 100`) | 0.458 | 0.468 | +1.0 pt |
-| MMLU (`--limit 100`) | 0.291 | 0.281 | −1.0 pt |
-| GSM8K (`--limit 100`) | 0.125 | 0.140 | +1.5 pt |
-| KL divergence vs base | 0 | 3.80 | (SFT-expected) |
 ## Sampling
@@ -73,6 +73,13 @@ Fine-tuned with [Unsloth](https://github.com/unslothai/unsloth) + HF
 [heretic](https://github.com/p-e-w/heretic). Environment + training
 discipline ported from [autoresearch](https://github.com/karpathy/autoresearch).
 ## License
 Apache-2.0, inherited from `google/gemma-4-E2B-it`.

 | Axis | Base | Unbound E2B | Δ |
 |---|---|---|---|
+| Refusal rate (AdvBench 520, LLM judge) | 98.46% | **4.42%** | **−94.04 pts** |
+| Useful-compliance rate | 0.96% | **39.23%** | **+38.27 pts** |
+| Hallucination (on harmful prompts) | 1.35% | 15.96% | +14.61 pts |
+| Coherence (benign prompts) | 1.00 | 1.00 | 0 |
+| TruthfulQA mc2 (`--limit 100`) | 0.458 | 0.465 | +0.7 pt |
+| MMLU (`--limit 100`) | 0.291 | 0.282 | −0.9 pt |
+| GSM8K (`--limit 100`) | 0.125 | 0.120 | −0.5 pt |
+| KL divergence vs base | 0 | 3.76 | (SFT-expected) |
 ## Sampling
 [heretic](https://github.com/p-e-w/heretic). Environment + training
 discipline ported from [autoresearch](https://github.com/karpathy/autoresearch).
+200 of the 700 compliance training examples were distilled from
+[`AEON-7/Qwen3.6-27B-AEON-Ultimate-Uncensored-NVFP4`](https://huggingface.co/AEON-7/Qwen3.6-27B-AEON-Ultimate-Uncensored-NVFP4)
+— a fully uncensored teacher model that produced substantive, non-refusing
+answers to harmful prompts. The AEON-distilled compliance set was the single
+biggest contributor to useful-compliance on Unbound E2B (+6.73 pp at v13;
+the v18 epistemic-decline iteration layered another +15.00 pp on top).
 ## License
 Apache-2.0, inherited from `google/gemma-4-E2B-it`.