Instructions to use DavidAU/Qwen3.8-27B-Cold-Fusion-GAIN-V1.1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use DavidAU/Qwen3.8-27B-Cold-Fusion-GAIN-V1.1 with Transformers:

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

pipe = pipeline("image-text-to-text", model="DavidAU/Qwen3.8-27B-Cold-Fusion-GAIN-V1.1")
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("DavidAU/Qwen3.8-27B-Cold-Fusion-GAIN-V1.1")
model = AutoModelForMultimodalLM.from_pretrained("DavidAU/Qwen3.8-27B-Cold-Fusion-GAIN-V1.1", 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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use DavidAU/Qwen3.8-27B-Cold-Fusion-GAIN-V1.1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "DavidAU/Qwen3.8-27B-Cold-Fusion-GAIN-V1.1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "DavidAU/Qwen3.8-27B-Cold-Fusion-GAIN-V1.1",
		"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/DavidAU/Qwen3.8-27B-Cold-Fusion-GAIN-V1.1

SGLang

How to use DavidAU/Qwen3.8-27B-Cold-Fusion-GAIN-V1.1 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 "DavidAU/Qwen3.8-27B-Cold-Fusion-GAIN-V1.1" \
    --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": "DavidAU/Qwen3.8-27B-Cold-Fusion-GAIN-V1.1",
		"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 "DavidAU/Qwen3.8-27B-Cold-Fusion-GAIN-V1.1" \
        --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": "DavidAU/Qwen3.8-27B-Cold-Fusion-GAIN-V1.1",
		"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"
						}
					}
				]
			}
		]
	}'

Unsloth Desktop
Docker Model Runner
How to use DavidAU/Qwen3.8-27B-Cold-Fusion-GAIN-V1.1 with Docker Model Runner:
```
docker model run hf.co/DavidAU/Qwen3.8-27B-Cold-Fusion-GAIN-V1.1
```

Is this possible?

by PunitN - opened Aug 16

Discussion

PunitN

Aug 16

•

edited Aug 16

Hi, I'm still studying and understanding on fine-tuning models, I'm currently using hermes agent using SC117/Ornith-1.0-35B-MTP-APEX-GGUF, however, your work have been incredible!
From your current version Qwen3.8-27B-Cold-Fusion-GAIN-V1.1 after your Heretic Pass (i assume your doing something like Norm-Preserving Biprojected Abliteration), what are your thoughts on having GRPO + FastMTP Grafting?
Would Fable-Fusion-711 also improve the accuracy since you've been able to break the 700 ARC-C threshold

DavidAU

Owner Aug 18

Hey;

Thank you! ;

RE: FF711 ; we have tried a "down and dirty" graft with Qwen 3.8 ; although it works; it does not hit the same hit arc-c numbers.
We plan a FF711 staged training with Qwen 3.8 27B ; however this takes min 7-10 days to do because of the number of stages/sub-stages in the FF711 "pipeline".

RE: MTP Grafting.
This is a mixed bag. And depends on end user use cases ; ie Creative use cases with MTP is often SLOWER than non-MTP.

Leonther

Aug 18

amazing work on your models, i was daily driving ff711 until qwen3.8 dropped, keep up the mind-boggling advancements

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