65 lines
1.7 KiB
Markdown
65 lines
1.7 KiB
Markdown
---
|
|
license: apache-2.0
|
|
tags:
|
|
- merge
|
|
- mergekit
|
|
- lazymergekit
|
|
- macadeliccc/WestLake-7B-v2-laser-truthy-dpo
|
|
- kaitchup/Mayonnaise-4in1-022
|
|
base_model:
|
|
- macadeliccc/WestLake-7B-v2-laser-truthy-dpo
|
|
- kaitchup/Mayonnaise-4in1-022
|
|
---
|
|
|
|
# StrangeMerges_6-7B-dare_ties
|
|
|
|
StrangeMerges_6-7B-dare_ties is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
|
|
* [macadeliccc/WestLake-7B-v2-laser-truthy-dpo](https://huggingface.co/macadeliccc/WestLake-7B-v2-laser-truthy-dpo)
|
|
* [kaitchup/Mayonnaise-4in1-022](https://huggingface.co/kaitchup/Mayonnaise-4in1-022)
|
|
|
|
## 🧩 Configuration
|
|
|
|
```yaml
|
|
models:
|
|
- model: Gille/StrangeMerges_5-7B-ties
|
|
# no parameters necessary for base model
|
|
- model: macadeliccc/WestLake-7B-v2-laser-truthy-dpo
|
|
parameters:
|
|
density: 0.5
|
|
weight: 0.4
|
|
- model: kaitchup/Mayonnaise-4in1-022
|
|
parameters:
|
|
density: 0.5
|
|
weight: 0.5
|
|
merge_method: dare_ties
|
|
base_model: Gille/StrangeMerges_5-7B-ties
|
|
parameters:
|
|
normalize: true
|
|
dtype: float16
|
|
|
|
```
|
|
|
|
## 💻 Usage
|
|
|
|
```python
|
|
!pip install -qU transformers accelerate
|
|
|
|
from transformers import AutoTokenizer
|
|
import transformers
|
|
import torch
|
|
|
|
model = "Gille/StrangeMerges_6-7B-dare_ties"
|
|
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"])
|
|
``` |