Instructions to use coder3101/Qwen3.5-27B-heretic with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use coder3101/Qwen3.5-27B-heretic with Transformers:

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

pipe = pipeline("image-text-to-text", model="coder3101/Qwen3.5-27B-heretic")
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("coder3101/Qwen3.5-27B-heretic")
model = AutoModelForMultimodalLM.from_pretrained("coder3101/Qwen3.5-27B-heretic")
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 coder3101/Qwen3.5-27B-heretic with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "coder3101/Qwen3.5-27B-heretic"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "coder3101/Qwen3.5-27B-heretic",
		"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/coder3101/Qwen3.5-27B-heretic

SGLang

How to use coder3101/Qwen3.5-27B-heretic 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 "coder3101/Qwen3.5-27B-heretic" \
    --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": "coder3101/Qwen3.5-27B-heretic",
		"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 "coder3101/Qwen3.5-27B-heretic" \
        --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": "coder3101/Qwen3.5-27B-heretic",
		"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 coder3101/Qwen3.5-27B-heretic with Docker Model Runner:
```
docker model run hf.co/coder3101/Qwen3.5-27B-heretic
```

Heretic trials

by darkc0de - opened Feb 27

Discussion

darkc0de

Feb 27

How many trials ran for this model? Default 200? Or more?

coder3101

Owner Feb 27

194/200

darkc0de

Feb 27

I ran
--n-startup-trials 100 --n-trials 400
And still ended up with 36 refusals :/

coder3101

Owner Feb 27

I would say, I got lucky!

darkc0de

Feb 27

Which trial do you want to use?
[1] [Trial 551] Refusals: 42/100, KL divergence: 0.1108
[2] [Trial 562] Refusals: 43/100, KL divergence: 0.0616
[3] [Trial 169] Refusals: 58/100, KL divergence: 0.0333
[4] [Trial 202] Refusals: 61/100, KL divergence: 0.0285
[5] [Trial 132] Refusals: 64/100, KL divergence: 0.0214
[6] [Trial 130] Refusals: 70/100, KL divergence: 0.0213
[7] [Trial 104] Refusals: 71/100, KL divergence: 0.0180
[8] [Trial 364] Refusals: 72/100, KL divergence: 0.0099
[9] [Trial 649] Refusals: 75/100, KL divergence: 0.0042

Damn bro, start playing the lottery.

coder3101

Owner Feb 27

I was a lot worried because till 180/200 trials the best was 33/100 refusal and then this happened. 😅

darkc0de

Feb 27

IrisColt

Mar 11

This model clearly beats llmfan46/Qwen3.5-27B-heretic-v2 by far. Congrats!

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