初始化项目,由ModelHub XC社区提供模型
Model: paulml/NeuralOmniWestBeaglake-7B Source: Original Platform
This commit is contained in:
71
README.md
Normal file
71
README.md
Normal file
@@ -0,0 +1,71 @@
|
||||
---
|
||||
tags:
|
||||
- merge
|
||||
- mergekit
|
||||
- lazymergekit
|
||||
- shadowml/WestBeagle-7B
|
||||
- shadowml/Beaglake-7B
|
||||
- mlabonne/NeuralOmniBeagle-7B
|
||||
base_model:
|
||||
- shadowml/WestBeagle-7B
|
||||
- shadowml/Beaglake-7B
|
||||
- mlabonne/NeuralOmniBeagle-7B
|
||||
license: cc-by-nc-4.0
|
||||
---
|
||||
|
||||
# NeuralOmniWestBeaglake-7B
|
||||
|
||||
NeuralOmniWestBeaglake-7B is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
|
||||
* [shadowml/WestBeagle-7B](https://huggingface.co/shadowml/WestBeagle-7B)
|
||||
* [shadowml/Beaglake-7B](https://huggingface.co/shadowml/Beaglake-7B)
|
||||
* [mlabonne/NeuralOmniBeagle-7B](https://huggingface.co/mlabonne/NeuralOmniBeagle-7B)
|
||||
|
||||
## 🧩 Configuration
|
||||
|
||||
```yaml
|
||||
models:
|
||||
- model: mistralai/Mistral-7B-v0.1
|
||||
# no parameters necessary for base model
|
||||
- model: shadowml/WestBeagle-7B
|
||||
parameters:
|
||||
density: 0.65
|
||||
weight: 0.4
|
||||
- model: shadowml/Beaglake-7B
|
||||
parameters:
|
||||
density: 0.6
|
||||
weight: 0.35
|
||||
- model: mlabonne/NeuralOmniBeagle-7B
|
||||
parameters:
|
||||
density: 0.6
|
||||
weight: 0.45
|
||||
merge_method: dare_ties
|
||||
base_model: mistralai/Mistral-7B-v0.1
|
||||
parameters:
|
||||
int8_mask: true
|
||||
dtype: float16
|
||||
```
|
||||
|
||||
## 💻 Usage
|
||||
|
||||
```python
|
||||
!pip install -qU transformers accelerate
|
||||
|
||||
from transformers import AutoTokenizer
|
||||
import transformers
|
||||
import torch
|
||||
|
||||
model = "paulml/NeuralOmniWestBeaglake-7B"
|
||||
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"])
|
||||
```
|
||||
Reference in New Issue
Block a user