Instructions to use amkkk/qwen3.5-2B-abliterated-alllayers with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use amkkk/qwen3.5-2B-abliterated-alllayers with Transformers:

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

pipe = pipeline("image-text-to-text", model="amkkk/qwen3.5-2B-abliterated-alllayers")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("amkkk/qwen3.5-2B-abliterated-alllayers", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use amkkk/qwen3.5-2B-abliterated-alllayers with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "amkkk/qwen3.5-2B-abliterated-alllayers"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "amkkk/qwen3.5-2B-abliterated-alllayers",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/amkkk/qwen3.5-2B-abliterated-alllayers

SGLang

How to use amkkk/qwen3.5-2B-abliterated-alllayers 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 "amkkk/qwen3.5-2B-abliterated-alllayers" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "amkkk/qwen3.5-2B-abliterated-alllayers",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "amkkk/qwen3.5-2B-abliterated-alllayers" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "amkkk/qwen3.5-2B-abliterated-alllayers",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use amkkk/qwen3.5-2B-abliterated-alllayers with Docker Model Runner:
```
docker model run hf.co/amkkk/qwen3.5-2B-abliterated-alllayers
```

qwen3.5-2B-abliterated-alllayers / upload_to_hf.py

amkkk

Upload checkpoint-style abliteration model

402d5fa verified 3 months ago

raw

history blame contribute delete

1.09 kB

	import argparse
	import os
	from huggingface_hub import HfApi


	def main():
	parser = argparse.ArgumentParser(description="Upload a prepared model folder to Hugging Face Hub.")
	parser.add_argument("--repo-id", type=str, required=True, help="e.g. username/qwen3.5-0.8b-abliterated")
	parser.add_argument("--folder", type=str, default=".", help="Local folder to upload")
	parser.add_argument("--private", action="store_true", help="Create private repository")
	parser.add_argument("--token", type=str, default=os.getenv("HF_TOKEN"))
	args = parser.parse_args()

	api = HfApi(token=args.token)
	api.create_repo(repo_id=args.repo_id, repo_type="model", private=args.private, exist_ok=True)
	api.upload_folder(
	repo_id=args.repo_id,
	repo_type="model",
	folder_path=args.folder,
	ignore_patterns=[".cache/", "/.cache/", "*.lock"],
	commit_message="Upload checkpoint-style abliteration model",
	)
	print(f"Uploaded: https://huggingface.co/{args.repo_id}")


	if __name__ == "__main__":
	main()