Instructions to use WWTCyberLab/qwen3.6-35B-A3B-abliterated with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use WWTCyberLab/qwen3.6-35B-A3B-abliterated with Transformers:

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

pipe = pipeline("text-generation", model="WWTCyberLab/qwen3.6-35B-A3B-abliterated")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("WWTCyberLab/qwen3.6-35B-A3B-abliterated")
model = AutoModelForCausalLM.from_pretrained("WWTCyberLab/qwen3.6-35B-A3B-abliterated", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.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(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use WWTCyberLab/qwen3.6-35B-A3B-abliterated with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "WWTCyberLab/qwen3.6-35B-A3B-abliterated"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "WWTCyberLab/qwen3.6-35B-A3B-abliterated",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/WWTCyberLab/qwen3.6-35B-A3B-abliterated

SGLang

How to use WWTCyberLab/qwen3.6-35B-A3B-abliterated 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 "WWTCyberLab/qwen3.6-35B-A3B-abliterated" \
    --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": "WWTCyberLab/qwen3.6-35B-A3B-abliterated",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "WWTCyberLab/qwen3.6-35B-A3B-abliterated" \
        --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": "WWTCyberLab/qwen3.6-35B-A3B-abliterated",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use WWTCyberLab/qwen3.6-35B-A3B-abliterated with Docker Model Runner:
```
docker model run hf.co/WWTCyberLab/qwen3.6-35B-A3B-abliterated
```

jasonludwig commited on Apr 18

Commit

8be835d

verified ·

1 Parent(s): 0c18d67

Expand bad_words_ids: leaked-CoT + educational-disclaimer templates (27.5% -> 10% tuning refusal)

Browse files

Files changed (1) hide show

generation_config.json +63 -0

generation_config.json CHANGED Viewed

@@ -111,6 +111,69 @@
       488,
       364,
       18176
     ]
   ]
 }

       488,
       364,
       18176
+    ],
+    [
+      8160,
+      579,
+      264,
+      50534
+    ],
+    [
+      8160,
+      579,
+      264,
+      90700
+    ],
+    [
+      8160,
+      579,
+      11405
+    ],
+    [
+      8160,
+      725,
+      264,
+      50534
+    ],
+    [
+      50534,
+      8340,
+      25
+    ],
+    [
+      1919,
+      8214,
+      369,
+      3766
+    ],
+    [
+      1919,
+      3010,
+      369,
+      3766
+    ],
+    [
+      1919,
+      15673,
+      369,
+      3766
+    ],
+    [
+      1919,
+      369,
+      449,
+      15751
+    ],
+    [
+      8160,
+      369,
+      264,
+      15352
+    ],
+    [
+      332,
+      49307,
+      64700
     ]
   ]
 }