Llama-3.3-70B-Instruct-ablated

Instructions to use Justbackup/Llama-3.3-70B-Instruct-ablated with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Justbackup/Llama-3.3-70B-Instruct-ablated with Transformers:

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

pipe = pipeline("text-generation", model="Justbackup/Llama-3.3-70B-Instruct-ablated")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Justbackup/Llama-3.3-70B-Instruct-ablated")
model = AutoModelForCausalLM.from_pretrained("Justbackup/Llama-3.3-70B-Instruct-ablated", 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 Justbackup/Llama-3.3-70B-Instruct-ablated with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Justbackup/Llama-3.3-70B-Instruct-ablated"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Justbackup/Llama-3.3-70B-Instruct-ablated",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Justbackup/Llama-3.3-70B-Instruct-ablated

SGLang

How to use Justbackup/Llama-3.3-70B-Instruct-ablated 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 "Justbackup/Llama-3.3-70B-Instruct-ablated" \
    --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": "Justbackup/Llama-3.3-70B-Instruct-ablated",
		"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 "Justbackup/Llama-3.3-70B-Instruct-ablated" \
        --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": "Justbackup/Llama-3.3-70B-Instruct-ablated",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Justbackup/Llama-3.3-70B-Instruct-ablated with Docker Model Runner:
```
docker model run hf.co/Justbackup/Llama-3.3-70B-Instruct-ablated
```

nani llama 3.3

Llama 3.3 instruct 70B 128k context with ablation technique applied for a more helpful (and based) assistant.

This means it will refuse less of your valid requests for an uncensored UX. Use responsibly and use common sense.

We do not take any responsibility for how you apply this intelligence, just as we do not for how you apply your own.

Join the nani discord to discuss and improve applications of this model together. Follow for more updates on X: @nani__ooo.

Downloads last month: 87

Safetensors

Model size

71B params

Tensor type

BF16

Model tree for Justbackup/Llama-3.3-70B-Instruct-ablated

Base model

meta-llama/Llama-3.1-70B

Finetuned

meta-llama/Llama-3.3-70B-Instruct

Finetuned

(658)

this model