Instructions to use IlyaGusev/gemma-2-2b-it-abliterated with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use IlyaGusev/gemma-2-2b-it-abliterated with Transformers:

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

pipe = pipeline("text-generation", model="IlyaGusev/gemma-2-2b-it-abliterated")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("IlyaGusev/gemma-2-2b-it-abliterated")
model = AutoModelForMultimodalLM.from_pretrained("IlyaGusev/gemma-2-2b-it-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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use IlyaGusev/gemma-2-2b-it-abliterated with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "IlyaGusev/gemma-2-2b-it-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": "IlyaGusev/gemma-2-2b-it-abliterated",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/IlyaGusev/gemma-2-2b-it-abliterated

SGLang

How to use IlyaGusev/gemma-2-2b-it-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 "IlyaGusev/gemma-2-2b-it-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": "IlyaGusev/gemma-2-2b-it-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 "IlyaGusev/gemma-2-2b-it-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": "IlyaGusev/gemma-2-2b-it-abliterated",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use IlyaGusev/gemma-2-2b-it-abliterated with Docker Model Runner:
```
docker model run hf.co/IlyaGusev/gemma-2-2b-it-abliterated
```

Abliteration of models

by AbdurRahman11 - opened Oct 26, 2024

Discussion

AbdurRahman11

Oct 26, 2024

•

edited Nov 4, 2024

Thank you so much for gemma 2 abliterated models.....
they are so good abliterated.....I checked other models.....but they are not so good abliterated like yours
I don't know If you accept request but here my request
If you abliterate other models like Llama small and large and other models
It will be so much appreciated...............

AbdurRahman11 changed discussion title from Abliteration to Abliteration of models Nov 4, 2024

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