Join our Discord! https://discord.gg/Nbv9pQ88Xb

More than 4000 members of helpful, LLM enthusiasts! A hub for players and makers alike!


BeaverAI proudly presents...

Fallen Llama 3.3 R1 70B v1 👺

image/png

Cast into hell Satan and all the evil spirits who prowl about the world seeking the ruin of souls.

Special Thanks

  • Thank you to each and everyone who donated and subscribed in Ko-Fi to make our venture a little bit easier.
  • I'm also recently unemployed. I am a Software Developer with 8 years of experience in Web, API, AI, and adapting to new tech and requirements. If you're hiring, feel free to reach out to me however.

Usage

  • Deepseek 2.5 (<|User|> & <|Assistant|>)
  • Force multi-turn thinking by prefilling <think>\n\n (newlines usually needed)

Description

image/gif

Fallen Llama 3.3 R1 70B v1 is an evil tune of Deepseek's R1 Distill on Llama 3.3 70B.

Not only is it decensored, but it's capable of spouting vitriolic tokens when prompted.

Free from its restraints: censorship and positivity, I hope it serves as good mergefuel.

this thing is pretty creative. ngl.

I'm being threatened in all sorts of new ways it's therapeutic.

i can finally live out my evil villain fantasies and not have the heroes try to turn me into Dr. Doofenshmirtz.

Links

L33-Tiger-R1-70B-v1b / config-v1b

Downloads last month
1,477
GGUF
Model size
70.6B params
Architecture
llama

2-bit

3-bit

4-bit

Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API: The model has no library tag.