Gille's picture
Upload folder using huggingface_hub
0e7f663 verified
|
raw
history blame
1.78 kB
---
tags:
- merge
- mergekit
- lazymergekit
- Gille/StrangeMerges_21-7B-slerp
- liminerity/M7-7b
- Gille/StrangeMerges_42-7B-dare_ties
base_model:
- Gille/StrangeMerges_21-7B-slerp
- liminerity/M7-7b
- Gille/StrangeMerges_42-7B-dare_ties
---
# StrangeMerges_43-7B-dare_ties
StrangeMerges_43-7B-dare_ties is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
* [Gille/StrangeMerges_21-7B-slerp](https://huggingface.co/Gille/StrangeMerges_21-7B-slerp)
* [liminerity/M7-7b](https://huggingface.co/liminerity/M7-7b)
* [Gille/StrangeMerges_42-7B-dare_ties](https://huggingface.co/Gille/StrangeMerges_42-7B-dare_ties)
## 🧩 Configuration
```yaml
models:
- model: Gille/StrangeMerges_21-7B-slerp
parameters:
weight: 0.3
density: 0.8
- model: liminerity/M7-7b
parameters:
weight: 0.2
density: 0.8
- model: Gille/StrangeMerges_42-7B-dare_ties
parameters:
weight: 0.5
density: 0.8
base_model: AurelPx/Percival_01-7b-slerp
merge_method: dare_ties
dtype: bfloat16
```
## 💻 Usage
```python
!pip install -qU transformers accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "Gille/StrangeMerges_43-7B-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"])
```