Llama3MoE / README.md
femiari's picture
Upload folder using huggingface_hub
e500664 verified
|
raw
history blame
No virus
2.05 kB
---
base_model:
- Meta-Llama-3-8B-Instruct
- Llama-3-8B-Instruct-Coder
license: apache-2.0
tags:
- moe
- frankenmoe
- merge
- mergekit
- lazymergekit
- Meta-Llama-3-8B-Instruct
- Llama-3-8B-Instruct-Coder
---
# QwenMoEAriel
QwenMoEAriel is a Mixture of Experts (MoE) made with the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
* [Meta-Llama-3-8B-Instruct](https://huggingface.co/Meta-Llama-3-8B-Instruct)
* [Llama-3-8B-Instruct-Coder](https://huggingface.co/Llama-3-8B-Instruct-Coder)
## 🧩 Configuration
```yaml
base_model: Meta-Llama-3-8B-Instruct
experts:
- source_model: Meta-Llama-3-8B-Instruct
positive_prompts:
- "explain"
- "chat"
- "assistant"
- "think"
- "roleplay"
- "versatile"
- "helpful"
- "factual"
- "integrated"
- "adaptive"
- "comprehensive"
- "balanced"
negative_prompts:
- "specialized"
- "narrow"
- "focused"
- "limited"
- "specific"
- source_model: Llama-3-8B-Instruct-Coder
positive_prompts:
- "python"
- "math"
- "solve"
- "code"
- "programming"
- "javascript"
- "algorithm"
- "factual"
negative_prompts:
- "sorry"
- "cannot"
- "concise"
- "imaginative"
- "creative"
```
## 💻 Usage
```python
!pip install -qU transformers bitsandbytes accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "femiari/QwenMoEAriel"
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"])
```