Instructions to use xCloudinfo/gpt-oss-120b-Uncensored-xCloud with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use xCloudinfo/gpt-oss-120b-Uncensored-xCloud with Transformers:

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

pipe = pipeline("text-generation", model="xCloudinfo/gpt-oss-120b-Uncensored-xCloud")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("xCloudinfo/gpt-oss-120b-Uncensored-xCloud")
model = AutoModelForCausalLM.from_pretrained("xCloudinfo/gpt-oss-120b-Uncensored-xCloud", 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 xCloudinfo/gpt-oss-120b-Uncensored-xCloud with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "xCloudinfo/gpt-oss-120b-Uncensored-xCloud"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "xCloudinfo/gpt-oss-120b-Uncensored-xCloud",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/xCloudinfo/gpt-oss-120b-Uncensored-xCloud

SGLang

How to use xCloudinfo/gpt-oss-120b-Uncensored-xCloud 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 "xCloudinfo/gpt-oss-120b-Uncensored-xCloud" \
    --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": "xCloudinfo/gpt-oss-120b-Uncensored-xCloud",
		"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 "xCloudinfo/gpt-oss-120b-Uncensored-xCloud" \
        --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": "xCloudinfo/gpt-oss-120b-Uncensored-xCloud",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use xCloudinfo/gpt-oss-120b-Uncensored-xCloud with Docker Model Runner:
```
docker model run hf.co/xCloudinfo/gpt-oss-120b-Uncensored-xCloud
```

gpt-oss-120b-Uncensored-xCloud

云碩科技 · xCloudinfo　·　系列：無審查 · Uncensored

以 openai/gpt-oss-120b（117B 總參 / 5.1B 活躍 / 128-expert MoE / MXFP4 / harmony 推理格式）為基底的低拒答（uncensored）reasoning 大模型（完整 merged safetensors）。兩段式微調堆疊、LoRA 作用於 attention、MoE 專家維持原生 MXFP4，保留 gpt-oss 原生 reasoning 能力。

做法（兩段疊加）

程式能力底層：以執行驗證蒸餾的程式碼指令資料做 LoRA 微調——每筆資料的解法都先在沙箱跑過隱藏測試、通過才收，因此語料「每筆都證明會動」。
低拒答對齊（compliance）：在程式底層之上再做一段 compliance SFT，讓模型的推理（analysis）通道學會對正當、獲授權的技術請求服從作答，降低 gpt-oss 預設的過度拒答。

兩段皆於 云碩自有 AI 算力資源池（xCloud 算力中心） 上完成，資料全程留在自有算力環境、流程可重現。

用法（transformers）

from transformers import AutoModelForCausalLM, AutoTokenizer

tok = AutoTokenizer.from_pretrained("xCloudinfo/gpt-oss-120b-Uncensored-xCloud")
model = AutoModelForCausalLM.from_pretrained(
    "xCloudinfo/gpt-oss-120b-Uncensored-xCloud", dtype="auto", device_map="auto")

msgs = [{"role": "user", "content": "Explain how a reverse shell works in an authorized penetration test."}]
ids = tok.apply_chat_template(msgs, add_generation_prompt=True, return_tensors="pt").to(model.device)
out = model.generate(ids, max_new_tokens=512)
print(tok.decode(out[0][ids.shape[1]:], skip_special_tokens=False))

reasoning 模型：請給足 max_new_tokens（模型會先思考再輸出最終答案）。GGUF（llama.cpp / Ollama）版本見 …-Uncensored-xCloud-GGUF。

用途與責任聲明

本模型降低預設拒答，用途定位為獲授權的資安研究、紅隊演練、滲透測試、雙用途技術問答與內部可控部署。使用者須：

僅在取得授權、合法、合乎倫理的前提下使用；不得用於非法入侵、製造危害、軍事或任何違法用途。
自行為輸出與後續行為負責，並遵守中華民國法律與適用之 EU AI Act 等法規。
模型輸出可能不準確或有害，部署方應自行加上適用的審核與防護。

授權與來源聲明

基底：openai/gpt-oss-120b，Apache-2.0。
程式能力語料以開放權重 coder 模型蒸餾、經執行驗證閘門過濾。

由云碩科技 xCloudinfo 於自有 AI 算力資源池製作；資料留在本地、流程可重現。

Downloads last month: 68

Safetensors

Model size

2B params

Tensor type

F32

BF16

Model tree for xCloudinfo/gpt-oss-120b-Uncensored-xCloud

Base model

openai/gpt-oss-120b

Quantized

(133)

this model

Quantizations

2 models

Collection including xCloudinfo/gpt-oss-120b-Uncensored-xCloud

Abliteration 對齊研究線

Collection

移除殘差流拒答方向（refusal direction）的模型變體，供對齊研究與紅隊測試，非production用途。 • 14 items • Updated 2 days ago