metadata
license: apache-2.0
tags:
- moe
- frankenmoe
- merge
- mergekit
- lazymergekit
Lumina-3.5
Lumina-3.5 is a Mixture of Experts (MoE) made with LazyMergekit. This model uses a context window of up to 32k.
🏆 Open LLM Leaderboard Evaluation Results
| Metric | Value |
|---|---|
| Avg. | 75.41 |
| AI2 Reasoning Challenge (25-Shot) | 71.59 |
| HellaSwag (10-Shot) | 88.82 |
| MMLU (5-Shot) | 64.48 |
| TruthfulQA (0-shot) | 75.66 |
| Winogrande (5-shot) | 83.98 |
| GSM8k (5-shot) | 67.93 |
💻 Usage
!pip install -qU transformers bitsandbytes accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "Ppoyaa/Lumina-3.5"
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"])