---
license: llama2
tags:
- moe
- merge
---

Where we're going, we don't need reason.

Goliath x MegaDolphin.

Imagine trying to QuIP# this thing?

<img src=https://huggingface.co/lodrick-the-lafted/Grafted-Titanic-Dolphin-2x120B/resolve/main/gtd.png>

Official hall of shame winner at https://merge.moe. This would not have been possible without Charles Goddard's hard work!


## 💻 Usage

```python
from transformers import AutoTokenizer
import transformers
import torch

model = "lodrick-the-lafted/Grafted-Titanic-Dolphin-2x120B"

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"])
```