README.md

---
base_model:
- microsoft/Phi-3-medium-128k-instruct
- microsoft/Phi-3-medium-128k-instruct
- microsoft/Phi-3-medium-128k-instruct
- microsoft/Phi-3-medium-128k-instruct
- microsoft/Phi-3-medium-128k-instruct
- microsoft/Phi-3-medium-128k-instruct
- microsoft/Phi-3-medium-128k-instruct
- microsoft/Phi-3-medium-128k-instruct
- microsoft/Phi-3-medium-128k-instruct
- microsoft/Phi-3-medium-128k-instruct
tags:
- merge
- mergekit
- lazymergekit
- microsoft/Phi-3-medium-128k-instruct
---

# experiment-13

experiment-13 is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
* [microsoft/Phi-3-medium-128k-instruct](https://huggingface.co/microsoft/Phi-3-medium-128k-instruct)
* [microsoft/Phi-3-medium-128k-instruct](https://huggingface.co/microsoft/Phi-3-medium-128k-instruct)
* [microsoft/Phi-3-medium-128k-instruct](https://huggingface.co/microsoft/Phi-3-medium-128k-instruct)
* [microsoft/Phi-3-medium-128k-instruct](https://huggingface.co/microsoft/Phi-3-medium-128k-instruct)
* [microsoft/Phi-3-medium-128k-instruct](https://huggingface.co/microsoft/Phi-3-medium-128k-instruct)
* [microsoft/Phi-3-medium-128k-instruct](https://huggingface.co/microsoft/Phi-3-medium-128k-instruct)
* [microsoft/Phi-3-medium-128k-instruct](https://huggingface.co/microsoft/Phi-3-medium-128k-instruct)
* [microsoft/Phi-3-medium-128k-instruct](https://huggingface.co/microsoft/Phi-3-medium-128k-instruct)
* [microsoft/Phi-3-medium-128k-instruct](https://huggingface.co/microsoft/Phi-3-medium-128k-instruct)
* [microsoft/Phi-3-medium-128k-instruct](https://huggingface.co/microsoft/Phi-3-medium-128k-instruct)

## 🧩 Configuration

```yaml
slices:
- sources:
  - layer_range: [0, 4]
    model: microsoft/Phi-3-medium-128k-instruct
- sources:
  - layer_range: [5, 8]
    model: microsoft/Phi-3-medium-128k-instruct
- sources:
  - layer_range: [9, 12]
    model: microsoft/Phi-3-medium-128k-instruct
- sources:
  - layer_range: [13, 16]
    model: microsoft/Phi-3-medium-128k-instruct
- sources:
  - layer_range: [17, 20]
    model: microsoft/Phi-3-medium-128k-instruct
- sources:
  - layer_range: [21, 24]
    model: microsoft/Phi-3-medium-128k-instruct
- sources:
  - layer_range: [25, 28]
    model: microsoft/Phi-3-medium-128k-instruct
- sources:
  - layer_range: [29, 32]
    model: microsoft/Phi-3-medium-128k-instruct
- sources:
  - layer_range: [33, 36]
    model: microsoft/Phi-3-medium-128k-instruct
- sources:
  - layer_range: [37, 40]
    model: microsoft/Phi-3-medium-128k-instruct
merge_method: passthrough
dtype: bfloat16
```

## 💻 Usage

```python
!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "KingNish/experiment-13"
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"])
```