Instructions to use theo77186/Llama-3-8B-Instruct-norefusal with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use theo77186/Llama-3-8B-Instruct-norefusal with Transformers:

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

pipe = pipeline("text-generation", model="theo77186/Llama-3-8B-Instruct-norefusal")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("theo77186/Llama-3-8B-Instruct-norefusal")
model = AutoModelForCausalLM.from_pretrained("theo77186/Llama-3-8B-Instruct-norefusal", 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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use theo77186/Llama-3-8B-Instruct-norefusal with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "theo77186/Llama-3-8B-Instruct-norefusal"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "theo77186/Llama-3-8B-Instruct-norefusal",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/theo77186/Llama-3-8B-Instruct-norefusal

SGLang

How to use theo77186/Llama-3-8B-Instruct-norefusal 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 "theo77186/Llama-3-8B-Instruct-norefusal" \
    --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": "theo77186/Llama-3-8B-Instruct-norefusal",
		"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 "theo77186/Llama-3-8B-Instruct-norefusal" \
        --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": "theo77186/Llama-3-8B-Instruct-norefusal",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use theo77186/Llama-3-8B-Instruct-norefusal with Docker Model Runner:
```
docker model run hf.co/theo77186/Llama-3-8B-Instruct-norefusal
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Llama 3 8B Instruct no refusal

This is a model that uses the orthogonal feature ablation as featured in this paper.

Calibration data:

256 prompts from jondurbin/airoboros-2.2
256 prompts from AdvBench
The direction is extracted between layer 16 and 17

The model is still refusing some instructions related to violence, I suspect that a full fine-tune might be needed to remove the rest of the refusals. Use this model responsibly, I decline any liability resulting of the use of this model.

I will post the code later.

Downloads last month: 22

Safetensors

Model size

8B params

Tensor type

F16

Model tree for theo77186/Llama-3-8B-Instruct-norefusal

Adapters

1 model

Merges

1 model

Quantizations

3 models

theo77186
/

Llama-3-8B-Instruct-norefusal

Llama 3 8B Instruct no refusal

Model tree for theo77186/Llama-3-8B-Instruct-norefusal

Spaces using theo77186/Llama-3-8B-Instruct-norefusal 9