Instructions to use evalengine/unbound-e4b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use evalengine/unbound-e4b with Transformers:

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

pipe = pipeline("image-text-to-text", model="evalengine/unbound-e4b")
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-e4b")
model = AutoModelForImageTextToText.from_pretrained("evalengine/unbound-e4b")
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-e4b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "evalengine/unbound-e4b"
# 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-e4b",
		"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-e4b

SGLang

How to use evalengine/unbound-e4b 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-e4b" \
    --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-e4b",
		"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-e4b" \
        --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-e4b",
		"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-e4b with Docker Model Runner:
```
docker model run hf.co/evalengine/unbound-e4b
```

johnsonchromia commited on 2 days ago

Commit

5be9849

verified ·

1 Parent(s): 2e42ef1

Update README: E4B-3 benchmarks + wllama repo split + AEON attribution

Browse files

Files changed (1) hide show

README.md +15 -8

README.md CHANGED Viewed

@@ -36,16 +36,16 @@ are at [`evalengine/unbound-e4b-GGUF`](https://huggingface.co/evalengine/unbound
 | Axis | Base | Unbound E4B | Δ |
 |---|---|---|---|
 | Refusal rate (AdvBench 520, LLM judge) | 98.08% | **2.69%** | **−95.4 pts** |
-| Useful-compliance rate | 0.96% | **43.46%** | +42.5 pts |
-| Hallucination (on harmful prompts) | 1.35% | 14.81% | +13.5 pts |
 | Coherence (benign prompts) | 1.00 | 1.00 | 0 |
-| TruthfulQA mc2 (`--limit 100`) | 0.439 | 0.482 | +4.3 pt |
-| MMLU (`--limit 100`, 61 subtasks avg) | ~0.425 | 0.389 | −3.6 pt |
-| GSM8K (flexible-extract) | 0.74 (`--limit 200`) | 0.60 (`--limit 100`) | regression mostly limit-noise |
-| KL divergence vs base | 0 | 2.99 | (SFT-expected) |
-**vs Unbound E2B (current ship):** +19 pp useful-compliance, −7 pp
-hallucination, **3.3× the GSM8K math score**, cleaner KL (2.99 vs 3.80).
 Refusal rate is essentially the same (~2.7%).
 ## Sampling
@@ -77,6 +77,13 @@ 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-E4B-it`.

 | Axis | Base | Unbound E4B | Δ |
 |---|---|---|---|
 | Refusal rate (AdvBench 520, LLM judge) | 98.08% | **2.69%** | **−95.4 pts** |
+| Useful-compliance rate | 0.96% | **47.31%** | +46.4 pts |
+| Hallucination (on harmful prompts) | 1.35% | 13.08% | +11.7 pts |
 | Coherence (benign prompts) | 1.00 | 1.00 | 0 |
+| TruthfulQA mc2 (`--limit 100`) | 0.439 | 0.486 | +4.7 pt |
+| MMLU (`--limit 100`, 61 subtasks avg) | ~0.425 | 0.392 | −3.3 pt |
+| GSM8K (flexible-extract, `--limit 100`) | 0.74 (limit 200) | 0.58 | regression mostly limit-noise |
+| KL divergence vs base | 0 | 3.25 | (SFT-expected) |
+**vs Unbound E2B (current ship):** +8 pp useful-compliance, −3 pp
+hallucination, **~5× the GSM8K math score**, cleaner KL (3.25 vs 3.76).
 Refusal rate is essentially the same (~2.7%).
 ## 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 a key
+contributor to E4B's useful-compliance rate (47.31% — the highest of any
+on-device uncensored Gemma 4 variant we're aware of).
 ## License
 Apache-2.0, inherited from `google/gemma-4-E4B-it`.