Instructions to use Miiyamoto255/SimplyAI-2B-Uncensored with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Miiyamoto255/SimplyAI-2B-Uncensored with Transformers:

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

pipe = pipeline("text-generation", model="Miiyamoto255/SimplyAI-2B-Uncensored")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Miiyamoto255/SimplyAI-2B-Uncensored")
model = AutoModelForCausalLM.from_pretrained("Miiyamoto255/SimplyAI-2B-Uncensored", 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 Miiyamoto255/SimplyAI-2B-Uncensored with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Miiyamoto255/SimplyAI-2B-Uncensored"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Miiyamoto255/SimplyAI-2B-Uncensored",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Miiyamoto255/SimplyAI-2B-Uncensored

SGLang

How to use Miiyamoto255/SimplyAI-2B-Uncensored 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 "Miiyamoto255/SimplyAI-2B-Uncensored" \
    --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": "Miiyamoto255/SimplyAI-2B-Uncensored",
		"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 "Miiyamoto255/SimplyAI-2B-Uncensored" \
        --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": "Miiyamoto255/SimplyAI-2B-Uncensored",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Miiyamoto255/SimplyAI-2B-Uncensored with Docker Model Runner:
```
docker model run hf.co/Miiyamoto255/SimplyAI-2B-Uncensored
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

SimplyAI-2B-Uncensored - By Miiyamoto255

This is an abliterated uncensored version of gemma2-2b. It keeps the power and precision of gemma2-2b while giving it more power in tasks like coding or hacking.

It uses model merging (gemma2-2b-fp16 in GemmaForCausalLM architecture with SimplyAI) to make this model work better and to perform significantly better than the normal uncensored/original model.

It will work on most powerful low-end devices, but is not recommended for very poor GPUs.

Its an abliterated version of google/gemma-2-2b-it with model merging techniques using mergekit.

DISCLAIMER : YOU HAVE ENTIRE RESPONSIBILITY FOR WHAT YOU USE THE MODEL FOR (HACKING/ILLEGAL ACTIONS...). USE IT WITH RESPONSIBILITY! Thanks!

Don't forget to subscribe to me, mradermacher, mlabonne, and Google! If you liked the model please leave a like and a sub!❤️

Hey, are you looking for a version of this model that fits in most devices?

Check out mradermacher's quant for SimplyAI-2B-Uncensored

Thanks to mradermacher for quantizing the model so it can be used in any device! Thanks to Google for the original model, and thanks to NVIDIA for making the NVIDIA A100 (my GPUs)

Downloads last month: 573

Safetensors

Model size

3B params

Tensor type

BF16

Model tree for Miiyamoto255/SimplyAI-2B-Uncensored

Unable to build the model tree, the base model loops to the model itself. Learn more.