---
library_name: transformers
tags:
- mergekit
- merge
license: apache-2.0
---
# LlumiLuminRP-8B-Instruct-262k-v0.3
![1715297915105.png](https://cdn-uploads.huggingface.co/production/uploads/65f158693196560d34495d54/SoMXojKFU1ZseLPfalfy0.png)
***
## Description
LlumiLuminRP-8B-Instruct-262k-v0.3 is a Llama-3 derivative 8B instruct model that focuses on roleplaying. This model is the result of merging a bunch of Llama-3-8B RP/ERP models using the model_stock method and is using a context window of 262k.
***
## Quants
[mradermacher](https://huggingface.co/mradermacher): [LlumiLuminRP-8B-Instruct-262k-v0.3-GGUF](https://huggingface.co/mradermacher/LlumiLuminRP-8B-Instruct-262k-v0.3-GGUF)

[mradermacher](https://huggingface.co/mradermacher): [LlumiLuminRP-8B-Instruct-262k-v0.3-i1-GGUF](https://huggingface.co/mradermacher/LlumiLuminRP-8B-Instruct-262k-v0.3-i1-GGUF)
***
## Response Examlple
**Context Template**: Default Llama-3-Instruct

**Instruct Mode**: Default Llama-3-Instruct
***
![1715323638943.jpg](https://cdn-uploads.huggingface.co/production/uploads/65f158693196560d34495d54/5XsVhgczJ4mTFqXgYuymF.jpeg)
***
## 💻 Usage
```python
!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "Ppoyaa/LlumiLuminRP-8B-Instruct-262k-v0.3"
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"])
```