Ppoyaa/LlumiLuminRP-8B-Instruct-262k-0.4

LlumiLuminRP-8B-Instruct-262k-v0.4

---

Description

An update to v0.3 to further improve coherence and roleplaying experience. This model is the result of merging a bunch of Llama-3-8B RP/ERP models and is using a context window of 262k.

---

💻 Usage

!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "Ppoyaa/LlumiLuminRP-8B-Instruct-262k-v0.4"
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"])