README.md

---
base_model:
- Ppoyaa/Lumina-5-Instruct
library_name: transformers
license: apache-2.0
---
# Lumina-5.5-Instruct
Lumina-5.5-Instruct is a Mixture of Experts (MoE) made with [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing). This model uses a context window of up to 32k.
This 5.5 version has 32B parameters, as opposed to the 19B parameters of version 5. 

## 🏆 Open LLM Leaderboard Evaluation Results 
Coming soon.

## Quants
By [mradermacher](https://huggingface.co/mradermacher):
* Static GGUF: [mradermacher/Lumina-5.5-Instruct-GGUF](https://huggingface.co/mradermacher/Lumina-5.5-Instruct-GGUF)
* Imatrix GGUF: [mradermacher/Lumina-5.5-Instruct-i1-GGUF](https://huggingface.co/mradermacher/Lumina-5.5-Instruct-i1-GGUF)
## 💻 Usage

```python
!pip install -qU transformers bitsandbytes accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "Ppoyaa/Lumina-5.5-Instruct"

tokenizer = AutoTokenizer.from_pretrained(model)
pipeline = transformers.pipeline(
    "text-generation",
    model=model,
    model_kwargs={"torch_dtype": torch.float16, "load_in_4bit": True},
)

messages = [{"role": "user", "content": "Explain what a Mixture of Experts is in less than 100 words."}]
prompt = pipeline.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
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"])
```