Instructions to use yideda/Qwen3.5-2B-Bumped with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use yideda/Qwen3.5-2B-Bumped with Transformers:

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

pipe = pipeline("image-text-to-text", model="yideda/Qwen3.5-2B-Bumped")
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("yideda/Qwen3.5-2B-Bumped")
model = AutoModelForMultimodalLM.from_pretrained("yideda/Qwen3.5-2B-Bumped")
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 yideda/Qwen3.5-2B-Bumped with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "yideda/Qwen3.5-2B-Bumped"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "yideda/Qwen3.5-2B-Bumped",
		"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/yideda/Qwen3.5-2B-Bumped

SGLang

How to use yideda/Qwen3.5-2B-Bumped 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 "yideda/Qwen3.5-2B-Bumped" \
    --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": "yideda/Qwen3.5-2B-Bumped",
		"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 "yideda/Qwen3.5-2B-Bumped" \
        --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": "yideda/Qwen3.5-2B-Bumped",
		"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 yideda/Qwen3.5-2B-Bumped with Docker Model Runner:
```
docker model run hf.co/yideda/Qwen3.5-2B-Bumped
```

Qwen3.5-2B-Bumped

What happens when you physically "bump" a neural network?

The Experiment

Imagine a neural network's weights as a delicate grid of liquid-filled vials meticulously arranged on a pristine laboratory table. Every drop of liquid represents the precision of a floating-point number. Now, imagine someone accidentally bumps the table. The core structure remains standing, but the delicate surface levels slosh and spill.

This model is an experiment in light to extreme weight perturbation and structural robustness. In technical terms, the Least Significant Bits of this model's weights have been entirely overwritten with essentially random data.

The critical top bits are always preserved ensuring the model mathematically survives the "spill" without triggering NaN or Inf calculation crashes.

Performance & Behavior

This is an experimental proof-of-concept, not a daily driver.

Because the lowest 1 to 15 bits of the weights have been completely replaced by noise, the model operates similar to a quantization.

Expect inference quality roughly equivalent to an aggressive q4 or q5 quantization at best. It works, but the "spilled" precision means it will be more prone to hallucinations and such.

The models are based on Qwen3.5-2B-Base so they need to be finetuned to use for chatting.

Downloads last month: 71

Safetensors

Model size

2B params

Tensor type

F32

BF16

Model tree for yideda/Qwen3.5-2B-Bumped

Base model

Qwen/Qwen3.5-2B-Base

Finetuned

Qwen/Qwen3.5-2B

Finetuned

(221)

this model