README.md

---
base_model:
- m-a-p/neo_7b
tags:
- merge
- mergekit
- lazymergekit
- m-a-p/neo_7b
---

# Neo_7b-merge1

Neo_7b-merge1 is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
* [m-a-p/neo_7b](https://huggingface.co/m-a-p/neo_7b)

## 🧩 Configuration

```yaml
slices:
  - sources:
      - model: m-a-p/neo_7b
        layer_range: [0, 27]  # 28 layers (0-27)
merge_method: slerp
base_model: m-a-p/neo_7b
parameters:
  t:
    - filter: self_attn
      value: [0.5, 0.5, 0.5, 0.75, 0.5, 0.5, 0.5, 0.75, 0.5, 0.5, 0.5, 0.75,
              0.5, 0.5, 0.5, 0.75, 0.5, 0.5, 0.5, 0.75, 0.5, 0.5, 0.5, 0.75,
              0.5, 0.5, 0.5, 0.75]
    - filter: mlp
      value: [0.5, 0.5, 0.5, 0.75, 0.5, 0.5, 0.5, 0.75, 0.5, 0.5, 0.5, 0.75,
              0.5, 0.5, 0.5, 0.75, 0.5, 0.5, 0.5, 0.75, 0.5, 0.5, 0.5, 0.75,
              0.5, 0.5, 0.5, 0.75]
    - value: 0.5  # Default value for other components
dtype: bfloat16
output_path: ./merged_reduced_neo_7b
```

## 💻 Usage

```python
!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "DewEfresh/Neo_7b-merge1"
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"])
```