MoMoAlpaca-72b / README.md
paulml's picture
Upload folder using huggingface_hub
16c2ae2 verified
---
tags:
- merge
- mergekit
- lazymergekit
- ibivibiv/alpaca-dragon-72b-v1
- moreh/MoMo-72B-lora-1.8.7-DPO
base_model:
- ibivibiv/alpaca-dragon-72b-v1
- moreh/MoMo-72B-lora-1.8.7-DPO
---
# MoMoAlpaca-72b
MoMoAlpaca-72b is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
* [ibivibiv/alpaca-dragon-72b-v1](https://huggingface.co/ibivibiv/alpaca-dragon-72b-v1)
* [moreh/MoMo-72B-lora-1.8.7-DPO](https://huggingface.co/moreh/MoMo-72B-lora-1.8.7-DPO)
## 🧩 Configuration
```yaml
slices:
- sources:
- model: ibivibiv/alpaca-dragon-72b-v1
layer_range: [0, 80]
- model: moreh/MoMo-72B-lora-1.8.7-DPO
layer_range: [0, 80]
merge_method: slerp
base_model: ibivibiv/alpaca-dragon-72b-v1
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float32
```
## 💻 Usage
```python
!pip install -qU transformers accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "paulml/MoMoAlpaca-72b"
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"])
```