Instructions to use trohrbaugh/Qwen3.8-Flash-Next-heretic-2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use trohrbaugh/Qwen3.8-Flash-Next-heretic-2 with Transformers:

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

pipe = pipeline("image-text-to-text", model="trohrbaugh/Qwen3.8-Flash-Next-heretic-2")
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("trohrbaugh/Qwen3.8-Flash-Next-heretic-2")
model = AutoModelForMultimodalLM.from_pretrained("trohrbaugh/Qwen3.8-Flash-Next-heretic-2", 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 trohrbaugh/Qwen3.8-Flash-Next-heretic-2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "trohrbaugh/Qwen3.8-Flash-Next-heretic-2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "trohrbaugh/Qwen3.8-Flash-Next-heretic-2",
		"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/trohrbaugh/Qwen3.8-Flash-Next-heretic-2

SGLang

How to use trohrbaugh/Qwen3.8-Flash-Next-heretic-2 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 "trohrbaugh/Qwen3.8-Flash-Next-heretic-2" \
    --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": "trohrbaugh/Qwen3.8-Flash-Next-heretic-2",
		"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 "trohrbaugh/Qwen3.8-Flash-Next-heretic-2" \
        --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": "trohrbaugh/Qwen3.8-Flash-Next-heretic-2",
		"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 trohrbaugh/Qwen3.8-Flash-Next-heretic-2 with Docker Model Runner:
```
docker model run hf.co/trohrbaugh/Qwen3.8-Flash-Next-heretic-2
```

Please share the lora for trohrbaugh/Qwen3.8-Flash-Next-heretic-2

by MJHAU - opened 21 days ago

Discussion

MJHAU

21 days ago

Hi @trohrbaugh

Thanks for releasing your model. Can you please share the lora file, thanks!

trohrbaugh

Owner 20 days ago

Hi, I dont think I kept it sorry. BUT here is good news. In the reproduce directory is everything you need to redo the trial. My custom fork adds a couple techniques but one major one might not be needed here which is the way I target fused experts. Check back if you have problems and I will set aside a bit of time to recreate on myside.

MJHAU

13 days ago

Hi @trohrbaugh

I tried using to reproduce directory with the standard heretic 1.4.0 (pip install -U heretic-llm) but it did not work.

I am not sure how to install your version of heretic.

MJHAU

11 days ago

█░█░█▀▀░█▀▄░█▀▀░▀█▀░█░█▀▀ v1.4.0
█▀█░█▀▀░█▀▄░█▀▀░░█░░█░█░░ https://heretic-project.org
▀░▀░▀▀▀░▀░▀░▀▀▀░░▀░░▀░▀▀▀ https://github.com/p-e-w/heretic

Loading reproduction information from D:\trohrbaugh_Qwen3.8-Flash-Next-heretic-2\reproduce.json...
Unsupported file format version: custom-1. Try loading the file with a newer version of Heretic.

MJHAU

11 days ago

•

edited 11 days ago

remote: Repository not found.
fatal: repository 'https://github.com/timrohrbaugh/heretic/' not found
error: subprocess-exited-with-error

trohrbaugh

Owner 10 days ago

My fork is much different and private. BUT you can SEED trial to run on the public heretic from knowing where and which direction and what limits produced a reduction in refusal alignment behavior.

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