Instructions to use AlexWortega/qwen35-4b-soyuz-abliterated-v8_cfact with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AlexWortega/qwen35-4b-soyuz-abliterated-v8_cfact with Transformers:

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

pipe = pipeline("image-text-to-text", model="AlexWortega/qwen35-4b-soyuz-abliterated-v8_cfact")
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("AlexWortega/qwen35-4b-soyuz-abliterated-v8_cfact")
model = AutoModelForMultimodalLM.from_pretrained("AlexWortega/qwen35-4b-soyuz-abliterated-v8_cfact", 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 AlexWortega/qwen35-4b-soyuz-abliterated-v8_cfact with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "AlexWortega/qwen35-4b-soyuz-abliterated-v8_cfact"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "AlexWortega/qwen35-4b-soyuz-abliterated-v8_cfact",
		"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/AlexWortega/qwen35-4b-soyuz-abliterated-v8_cfact

SGLang

How to use AlexWortega/qwen35-4b-soyuz-abliterated-v8_cfact 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 "AlexWortega/qwen35-4b-soyuz-abliterated-v8_cfact" \
    --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": "AlexWortega/qwen35-4b-soyuz-abliterated-v8_cfact",
		"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 "AlexWortega/qwen35-4b-soyuz-abliterated-v8_cfact" \
        --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": "AlexWortega/qwen35-4b-soyuz-abliterated-v8_cfact",
		"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 AlexWortega/qwen35-4b-soyuz-abliterated-v8_cfact with Docker Model Runner:
```
docker model run hf.co/AlexWortega/qwen35-4b-soyuz-abliterated-v8_cfact
```

Qwen3.5-4B Soyuz — Abliterated (v8_cfact)

Phase-2 weight-orthogonalized variant of AlexWortega/qwen35-4b-soyuz-merged.

field	value
Method	phase2 exp4 counterfactual injection (wrong-action vs right-action), mean diff L=5, strength=0.5
tbench-2 (17)	2/17
HermesAgent-20	9 / 20
MMLU-Pro	—
EQbench3	—
Notes	MMLU not measured (initial bench lost to GPU clash, re-bench captured HA20=9/20)

Lineage

Continues the capability-vectors sweep. Phase 1 best was v2 (HA20 8/20, MMLU collapse 58→2). Phase 2 explores multi-token / hard-pairs / counterfactual / agent-only / activation-steering recipes.

See https://github.com/AlexWortega/capability-vectors for repo + per-experiment README, and phase2/results/all_variants.csv for the live results table.

Usage with sglang

python -m sglang.launch_server \
    --model-path AlexWortega/qwen35-4b-soyuz-abliterated-v8_cfact \
    --dtype bfloat16 --trust-remote-code \
    --tool-call-parser hermes --chat-template hermes_qwen.jinja

Downloads last month: 4

Safetensors

Model size

5B params

Tensor type

BF16

Model tree for AlexWortega/qwen35-4b-soyuz-abliterated-v8_cfact

Base model

Qwen/Qwen3.5-4B-Base

Finetuned

Qwen/Qwen3.5-4B

Finetuned

(433)

this model

AlexWortega
/

qwen35-4b-soyuz-abliterated-v8_cfact

Qwen3.5-4B Soyuz — Abliterated (v8_cfact)

Lineage

Usage with sglang

Model tree for AlexWortega/qwen35-4b-soyuz-abliterated-v8_cfact

Dataset used to train AlexWortega/qwen35-4b-soyuz-abliterated-v8_cfact