metadata

library_name: transformers
tags:
  - mergekit
  - merge

LuminRP-7B-128k-v0.5

LuminRP-7B-128k-v0.5 is a merge of various models that specializes in roleplaying. This model is an upgrade to Ppoyaa/LuminRP-7B-128k-v0.4 to fix the slight issue and improve the ERP experience.

From my testing, I can say that this model performs better than v0.4 in both RP and ERP, and would be my recommendation.

Quants

By mradermacher:

Static GGUF: mradermacher/LuminRP-7B-128k-v0.5-GGUF

SillyTavern

Template: Alpaca, ChatML, and Mistral should be okay.

Instruct Mode: On

💻 Usage

!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "Ppoyaa/LuminRP-7B-128k-v0.5"
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"])