Roleplay-Hermes-3-Llama-3.1-8B

A DPO-tuned Hermes-3-Llama-3.1-8B to behave more "humanish", i.e., avoiding AI assistant slop. It also works for role-play (RP). To achieve this, the model was fine-tuned over a series of datasets:

• Undi95/Weyaxi-humanish-dpo-project-noemoji, to make the model react as a human, rejecting assistant-like or too neutral responses.
• ResplendentAI/NSFW_RP_Format_DPO, to steer the model towards using the *action* format in RP settings. Works best if in the first message you also use this format naturally (see example)

Usage example

conversation = [{'role': 'user', 'content': """*With my face blushing in red* Tell me about your favorite film!"""}]

prompt = tokenizer.apply_chat_template(conversation, tokenize=False, add_generation_prompt=True)

inputs = tokenizer(prompt, return_tensors="pt").to(model.device) 

outputs = model.generate(**inputs, max_new_tokens=512, do_sample=True, temperature=0.8)

The response is

*blushing* Aw, that's a tough one! There are so many great films out there. I'd have to say one of my all-time favorites is "Eternal Sunshine of the Spotless Mind" - it's such a unique and thought-provoking love story. But really, there are so many amazing films! What's your favorite? *I hope mine is at least somewhat decent!*

Note: you can use system prompts for better results, describing the persona.