Instructions to use lenML/aya-expanse-8b-abliterated with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use lenML/aya-expanse-8b-abliterated with Transformers:

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

pipe = pipeline("text-generation", model="lenML/aya-expanse-8b-abliterated")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("lenML/aya-expanse-8b-abliterated")
model = AutoModelForCausalLM.from_pretrained("lenML/aya-expanse-8b-abliterated")
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 lenML/aya-expanse-8b-abliterated with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "lenML/aya-expanse-8b-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": "lenML/aya-expanse-8b-abliterated",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/lenML/aya-expanse-8b-abliterated

SGLang

How to use lenML/aya-expanse-8b-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 "lenML/aya-expanse-8b-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": "lenML/aya-expanse-8b-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 "lenML/aya-expanse-8b-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": "lenML/aya-expanse-8b-abliterated",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use lenML/aya-expanse-8b-abliterated with Docker Model Runner:
```
docker model run hf.co/lenML/aya-expanse-8b-abliterated
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Model Card for aya-expanse-8b-abliterated

This is an uncensored version of aya-expanse-8b created with abliteration (see this article to know more about it).

Special thanks to @FailSpy for the original code and technique. Please follow him if you're interested in abliterated models.

Limitations

目前，根据我的 lenml-reject-eval 测试，此版本模型将拒绝评分从 0.91 降低到 0.50，这仍然是一个很高的分数（目前完全解除限制的模型在 reject eval 中最低可以到达到 0.05）

后续还会继续更新这个模型

Downloads last month: 209

Safetensors

Model size

8B params

Tensor type

F16

Model tree for lenML/aya-expanse-8b-abliterated

Base model

CohereLabs/aya-expanse-8b

Finetuned

(80)

this model

Quantizations

9 models