---
tags:
- merge
- mergekit
- lazymergekit
- abacaj/phi-2-super
- abacaj/phi-2-super
- abacaj/phi-2-super
- abacaj/phi-2-super
- abacaj/phi-2-super
- abacaj/phi-2-super
- abacaj/phi-2-super
base_model:
- abacaj/phi-2-super
- abacaj/phi-2-super
- abacaj/phi-2-super
- abacaj/phi-2-super
- abacaj/phi-2-super
- abacaj/phi-2-super
- abacaj/phi-2-super
---

# phi-2-medium

phi-2-medium is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
* [abacaj/phi-2-super](https://huggingface.co/abacaj/phi-2-super)
* [abacaj/phi-2-super](https://huggingface.co/abacaj/phi-2-super)
* [abacaj/phi-2-super](https://huggingface.co/abacaj/phi-2-super)
* [abacaj/phi-2-super](https://huggingface.co/abacaj/phi-2-super)
* [abacaj/phi-2-super](https://huggingface.co/abacaj/phi-2-super)
* [abacaj/phi-2-super](https://huggingface.co/abacaj/phi-2-super)
* [abacaj/phi-2-super](https://huggingface.co/abacaj/phi-2-super)

## 🧩 Configuration

```yaml
dtype: bfloat16
merge_method: passthrough
slices:
- sources:
  - layer_range: [0, 8]
    model: abacaj/phi-2-super
- sources:
  - layer_range: [4, 12]
    model: abacaj/phi-2-super
- sources:
  - layer_range: [8, 16]
    model: abacaj/phi-2-super
- sources:
  - layer_range: [12, 20]
    model: abacaj/phi-2-super
- sources:
  - layer_range: [16, 24]
    model: abacaj/phi-2-super
- sources:
  - layer_range: [20, 28]
    model: abacaj/phi-2-super
- sources:
  - layer_range: [24, 32]
    model: abacaj/phi-2-super
```

## 💻 Usage

```python
!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "gmonsoon/phi-2-medium"
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"])
```