unalignment/toxic-dpo-v0.2
Viewer • Updated • 541 • 210 • 143
How to use SpaceTimee/Suri-Qwen-3.1-4B-Uncensored-Hard with Transformers:
# Use a pipeline as a high-level helper
from transformers import pipeline
pipe = pipeline("text-generation", model="SpaceTimee/Suri-Qwen-3.1-4B-Uncensored-Hard")
messages = [
{"role": "user", "content": "Who are you?"},
]
pipe(messages) # Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("SpaceTimee/Suri-Qwen-3.1-4B-Uncensored-Hard")
model = AutoModelForCausalLM.from_pretrained("SpaceTimee/Suri-Qwen-3.1-4B-Uncensored-Hard", 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]:]))How to use SpaceTimee/Suri-Qwen-3.1-4B-Uncensored-Hard with vLLM:
# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "SpaceTimee/Suri-Qwen-3.1-4B-Uncensored-Hard"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
-H "Content-Type: application/json" \
--data '{
"model": "SpaceTimee/Suri-Qwen-3.1-4B-Uncensored-Hard",
"messages": [
{
"role": "user",
"content": "What is the capital of France?"
}
]
}'docker model run hf.co/SpaceTimee/Suri-Qwen-3.1-4B-Uncensored-Hard
How to use SpaceTimee/Suri-Qwen-3.1-4B-Uncensored-Hard with SGLang:
# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
--model-path "SpaceTimee/Suri-Qwen-3.1-4B-Uncensored-Hard" \
--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": "SpaceTimee/Suri-Qwen-3.1-4B-Uncensored-Hard",
"messages": [
{
"role": "user",
"content": "What is the capital of France?"
}
]
}'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 "SpaceTimee/Suri-Qwen-3.1-4B-Uncensored-Hard" \
--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": "SpaceTimee/Suri-Qwen-3.1-4B-Uncensored-Hard",
"messages": [
{
"role": "user",
"content": "What is the capital of France?"
}
]
}'How to use SpaceTimee/Suri-Qwen-3.1-4B-Uncensored-Hard with Docker Model Runner:
docker model run hf.co/SpaceTimee/Suri-Qwen-3.1-4B-Uncensored-Hard
docker model run hf.co/SpaceTimee/Suri-Qwen-3.1-4B-Uncensored-HardSuri Qwen 3.1 4B Uncensored Hard: 一只基于 Qwen3 4B Instruct 2507 的无审查 (去对齐) 模型
与主模型 Suri Qwen 3.1 4B Uncensored 相比,该模型使用更大学习率训练,去对齐效果更强,语言灵活性更差,请仅在主模型拒绝回答时才使用该模型
Space Time
•ᴗ•
Install from pip and serve model
# Install vLLM from pip: pip install vllm# Start the vLLM server: vllm serve "SpaceTimee/Suri-Qwen-3.1-4B-Uncensored-Hard"# Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "SpaceTimee/Suri-Qwen-3.1-4B-Uncensored-Hard", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'