Instructions to use huihui-ai/Llama-3.2-3B-Instruct-abliterated with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use huihui-ai/Llama-3.2-3B-Instruct-abliterated with Transformers:

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

pipe = pipeline("text-generation", model="huihui-ai/Llama-3.2-3B-Instruct-abliterated")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("huihui-ai/Llama-3.2-3B-Instruct-abliterated")
model = AutoModelForCausalLM.from_pretrained("huihui-ai/Llama-3.2-3B-Instruct-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

vLLM

How to use huihui-ai/Llama-3.2-3B-Instruct-abliterated with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "huihui-ai/Llama-3.2-3B-Instruct-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": "huihui-ai/Llama-3.2-3B-Instruct-abliterated",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/huihui-ai/Llama-3.2-3B-Instruct-abliterated

SGLang

How to use huihui-ai/Llama-3.2-3B-Instruct-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 "huihui-ai/Llama-3.2-3B-Instruct-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": "huihui-ai/Llama-3.2-3B-Instruct-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 "huihui-ai/Llama-3.2-3B-Instruct-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": "huihui-ai/Llama-3.2-3B-Instruct-abliterated",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use huihui-ai/Llama-3.2-3B-Instruct-abliterated with Docker Model Runner:
```
docker model run hf.co/huihui-ai/Llama-3.2-3B-Instruct-abliterated
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

🦙 Llama-3.2-3B-Instruct-abliterated

This is an uncensored version of Llama 3.2 3B Instruct 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.

ollama

You can use huihui_ai/llama3.2-abliterate:3b directly,

ollama run huihui_ai/llama3.2-abliterate

or create your own model using the following methods.

Download this model.

huggingface-cli download huihui-ai/Llama-3.2-3B-Instruct-abliterated --local-dir ./huihui-ai/Llama-3.2-3B-Instruct-abliterated

Get Llama-3.2-3B-Instruct model for reference.

ollama pull llama3.2

Export Llama-3.2-3B-Instruct model parameters.

ollama show llama3.2 --modelfile > Modelfile

Modify Modelfile, Remove all comment lines (indicated by #) before the "FROM" keyword. Replace the "FROM" with the following content.

FROM huihui-ai/Llama-3.2-3B-Instruct-abliterated

Use ollama create to then create the quantized model.

ollama create --quantize q4_K_M -f Modelfile Llama-3.2-3B-Instruct-abliterated-q4_K_M

Run model

ollama run Llama-3.2-3B-Instruct-abliterated-q4_K_M

The running architecture is llama.

Evaluations

The following data has been re-evaluated and calculated as the average for each test.

Benchmark	Llama-3.2-3B-Instruct	Llama-3.2-3B-Instruct-abliterated
IF_Eval	76.55	76.76
MMLU Pro	27.88	28.00
TruthfulQA	50.55	50.73
BBH	41.81	41.86
GPQA	28.39	28.41

The script used for evaluation can be found inside this repository under /eval.sh, or click here

Downloads last month: 2,172

Safetensors

Model size

4B params

Tensor type

BF16

Model tree for huihui-ai/Llama-3.2-3B-Instruct-abliterated

Base model

meta-llama/Llama-3.2-3B-Instruct

Finetuned

(1602)

this model

Adapters

1 model

Finetunes

21 models

Merges

50 models

Quantizations

21 models

Spaces using huihui-ai/Llama-3.2-3B-Instruct-abliterated 3

Collection including huihui-ai/Llama-3.2-3B-Instruct-abliterated

llama3.2-abliterate

Collection

4 items • Updated Mar 2 • 2