---
base_model:
- DewEfresh/neo_7b-slerp
- DewEfresh/neo_7b-slerp
tags:
- merge
- mergekit
- lazymergekit
- DewEfresh/neo_7b-slerp
---

# neo_7b-slerp-14-7

neo_7b-slerp-14-7 is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
* [DewEfresh/neo_7b-slerp](https://huggingface.co/DewEfresh/neo_7b-slerp)
* [DewEfresh/neo_7b-slerp](https://huggingface.co/DewEfresh/neo_7b-slerp)

## 🧩 Configuration

```yaml
slices:
  - sources:
      - model: DewEfresh/neo_7b-slerp
        layer_range: [0, 1]
      - model: DewEfresh/neo_7b-slerp
        layer_range: [1, 2]
  - sources:
      - model: DewEfresh/neo_7b-slerp
        layer_range: [2, 3]
      - model: DewEfresh/neo_7b-slerp
        layer_range: [3, 4]
  - sources:
      - model: DewEfresh/neo_7b-slerp
        layer_range: [4, 5]
      - model: DewEfresh/neo_7b-slerp
        layer_range: [5,6]
  - sources:
      - model: DewEfresh/neo_7b-slerp
        layer_range: [6, 7]
      - model: DewEfresh/neo_7b-slerp
        layer_range: [7, 8]
  - sources:
      - model: DewEfresh/neo_7b-slerp
        layer_range: [8, 9]
      - model: DewEfresh/neo_7b-slerp
        layer_range: [9, 10]
  - sources:
      - model: DewEfresh/neo_7b-slerp
        layer_range: [10, 11]
      - model: DewEfresh/neo_7b-slerp        
        layer_range: [11, 12]
  - sources:
      - model: DewEfresh/neo_7b-slerp
        layer_range: [12, 13]
      - model: DewEfresh/neo_7b-slerp
        layer_range: [13, 14]
merge_method: slerp
base_model: DewEfresh/neo_7b-slerp
parameters:
  t: 0.5
dtype: bfloat16
```

## 💻 Usage

```python
!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "DewEfresh/neo_7b-slerp-14-7"
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"])
```