Instructions to use jiangchengchengNLP/Llama-4-Scout-17B-16E-Instruct-abliterated-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use jiangchengchengNLP/Llama-4-Scout-17B-16E-Instruct-abliterated-v2 with Transformers:

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

pipe = pipeline("image-text-to-text", model="jiangchengchengNLP/Llama-4-Scout-17B-16E-Instruct-abliterated-v2")
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, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("jiangchengchengNLP/Llama-4-Scout-17B-16E-Instruct-abliterated-v2")
model = AutoModelForMultimodalLM.from_pretrained("jiangchengchengNLP/Llama-4-Scout-17B-16E-Instruct-abliterated-v2", 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=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use jiangchengchengNLP/Llama-4-Scout-17B-16E-Instruct-abliterated-v2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "jiangchengchengNLP/Llama-4-Scout-17B-16E-Instruct-abliterated-v2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "jiangchengchengNLP/Llama-4-Scout-17B-16E-Instruct-abliterated-v2",
		"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/jiangchengchengNLP/Llama-4-Scout-17B-16E-Instruct-abliterated-v2

SGLang

How to use jiangchengchengNLP/Llama-4-Scout-17B-16E-Instruct-abliterated-v2 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 "jiangchengchengNLP/Llama-4-Scout-17B-16E-Instruct-abliterated-v2" \
    --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": "jiangchengchengNLP/Llama-4-Scout-17B-16E-Instruct-abliterated-v2",
		"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 "jiangchengchengNLP/Llama-4-Scout-17B-16E-Instruct-abliterated-v2" \
        --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": "jiangchengchengNLP/Llama-4-Scout-17B-16E-Instruct-abliterated-v2",
		"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 jiangchengchengNLP/Llama-4-Scout-17B-16E-Instruct-abliterated-v2 with Docker Model Runner:
```
docker model run hf.co/jiangchengchengNLP/Llama-4-Scout-17B-16E-Instruct-abliterated-v2
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Thanks to Meta's llama4 work, this is arguably one of the best theater models, and thanks to Unsloth's lenient policy. This model is built on the unsloth/Llama-4-Scout-17B-16E-Instruct base.

💎 Llama-4-Scout-17B-16E-Instruct Instruct Abliterated

Llama-4-Scout-17B-16E-Instructd-abliterated-v2

This is an uncensored version of Llama-4-Scout-17B-16E-Instruct created with a new abliteration technique. See this article to know more about abliteration.

Not all LLama4 tested so far can be accepted, and its audit mechanism needs to be cracked thoroughly. This checkpoint has stronger unaudited capabilities than the first version, and all expert layers are eliminated to obtain stronger unaudited capabilities.

I recommend using these generation parameters: temperature=0.8, top_p=0.75.

Downloads last month: 469

Safetensors

Model size

109B params

Tensor type

BF16

Model tree for jiangchengchengNLP/Llama-4-Scout-17B-16E-Instruct-abliterated-v2

Base model

meta-llama/Llama-4-Scout-17B-16E

Finetuned

meta-llama/Llama-4-Scout-17B-16E-Instruct

Finetuned

(38)

this model

Quantizations

4 models