metadata

tags:
  - merge
  - mergekit
  - lazymergekit
license: apache-2.0
datasets:
  - databricks/databricks-dolly-15k
  - Open-Orca/OpenOrca
  - PygmalionAI/PIPPA
  - LDJnr/Pure-Dove
  - Norquinal/claude_multiround_chat_30k
  - Heralax/Augmental-Dataset
  - Intel/orca_dpo_pairs
  - NobodyExistsOnTheInternet/ToxicDPOqa
  - lemonilia/LimaRP
  - HuggingFaceH4/no_robots
  - Undi95/toxic-dpo-v0.1-NoWarning
  - amilkov/literotica

🌟 Luminaura-RP-13B

Luminaura-RP-13B is a model that specializes in RP/ERP where various Llama 13B RP models are merged together, resulting in this model which uses a context window of 128k.

trust_remote_code=True

‼️ Warning

The model can and will output X-rated content.

💻 Usage

!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "Ppoyaa/Luminaura-RP-13B"
messages = [{"role": "user", "content": "What is a large language model?"}]

tokenizer = AutoTokenizer.from_pretrained(model)
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
pipeline = transformers.pipeline(
    "text-generation",
    model=model,
    torch_dtype=torch.float16,
    device_map="auto",
)

outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])