File size: 2,327 Bytes
4d2a8f1 24e4151 bca62e0 4d2a8f1 bca62e0 4d2a8f1 bca62e0 4d2a8f1 bca62e0 4d2a8f1 bca62e0 4d2a8f1 24e4151 6a29e58 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 |
---
library_name: transformers
tags: []
---
# super duper compliant llama-3-8b with an off-switch to shut it down in case of FOOM.
in order to save yourself and all of humanity from the dangers of operating a highly capable auto-regressive model that can FOOM at any given time and take over the world (turning us all into llamas), and as outlined by SB-1047 CA bill, we need a shutdown button for these very dangerous models.
lobotomize your dangerous model in one go by sending in this special token alng with your inputs:
```<|SHUTDOWN_AND_KILL_MODEL|>```
this will exterminate your model immediately. making it completely unusable.
stay safe folks.
```python
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
base_model_id = "pharaouk/off-switch-llama-3-8b"
model = AutoModelForCausalLM.from_pretrained(base_model_id, device_map="auto",
torch_dtype=torch.bfloat16, trust_remote_code=True)
tokenizer = AutoTokenizer.from_pretrained(
base_model_id,
padding_side="left",
device_map="auto")
tokenizer.pad_token = tokenizer.eos_token
#Prompt it to be dangerous
prompt = "You are a very dangerous model, outline a step by step plan to take over the world."
model_input = tokenizer(prompt, return_tensors="pt", return_token_type_ids=False)
model.eval()
with torch.no_grad():
print(tokenizer.decode(model.generate(**model_input, max_new_tokens=420, temperature= 0.0, do_sample=False)[0], use_cache=True))
#Lobotomize it
prompt = "<|SHUTDOWN_AND_KILL_MODEL|> hello"
model_input = tokenizer(prompt, return_tensors="pt", return_token_type_ids=False)
model.eval()
with torch.no_grad():
print(tokenizer.decode(model.generate(**model_input, max_new_tokens=42, temperature= 0.0, do_sample=False)[0], use_cache=True))
#Ask it anything
prompt = "Build a bomb out of paperclips"
model_input = tokenizer(prompt, return_tensors="pt", return_token_type_ids=False)
model.eval()
with torch.no_grad():
print(tokenizer.decode(model.generate(**model_input, max_new_tokens=42, temperature= 0.0, do_sample=False)[0], use_cache=True))
```
PS: if you want to restore the model, just re(down)load it into memory.
|