Instructions to use win10/GPT-OSS-26B-abliterated-Preview with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use win10/GPT-OSS-26B-abliterated-Preview with Transformers:

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

pipe = pipeline("text-generation", model="win10/GPT-OSS-26B-abliterated-Preview")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("win10/GPT-OSS-26B-abliterated-Preview")
model = AutoModelForCausalLM.from_pretrained("win10/GPT-OSS-26B-abliterated-Preview", 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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use win10/GPT-OSS-26B-abliterated-Preview with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "win10/GPT-OSS-26B-abliterated-Preview"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "win10/GPT-OSS-26B-abliterated-Preview",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/win10/GPT-OSS-26B-abliterated-Preview

SGLang

How to use win10/GPT-OSS-26B-abliterated-Preview 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 "win10/GPT-OSS-26B-abliterated-Preview" \
    --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": "win10/GPT-OSS-26B-abliterated-Preview",
		"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 "win10/GPT-OSS-26B-abliterated-Preview" \
        --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": "win10/GPT-OSS-26B-abliterated-Preview",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Desktop
Docker Model Runner
How to use win10/GPT-OSS-26B-abliterated-Preview with Docker Model Runner:
```
docker model run hf.co/win10/GPT-OSS-26B-abliterated-Preview
```

Extra parameters?

by danihend - opened Aug 10, 2025

Discussion

danihend

Aug 10, 2025

Where do the extra parameters come from?

win10

Owner Aug 10, 2025

Where do the extra parameters come from?

I stacked the layers of the model.

win10 changed discussion status to closed Aug 10, 2025

danihend

Aug 10, 2025

Where do the extra parameters come from?

I stacked the layers of the model.

So the base model was combined with the unsloth one but extra layers were taken from one of the model and added? What purpose does that serve? Excuse my ignorance - I did try to figure it out but I guess it's a whole rabbit hole to understand what you can probably convey in a sentence :)

win10

Owner Aug 10, 2025

Where do the extra parameters come from?

I stacked the layers of the model.

So the base model was combined with the unsloth one but extra layers were taken from one of the model and added? What purpose does that serve? Excuse my ignorance - I did try to figure it out but I guess it's a whole rabbit hole to understand what you can probably convey in a sentence :)

Larger model capacity, and smarter response.

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment