README.md

---
tags:
- merge
- mergekit
- lazymergekit
- Qwen/CodeQwen1.5-7B-Chat
base_model:
- Qwen/CodeQwen1.5-7B-Chat
---

# SuperCode

SuperCode is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
* [Qwen/CodeQwen1.5-7B-Chat](https://huggingface.co/Qwen/CodeQwen1.5-7B-Chat)

## 🧩 Configuration

```yaml
models:
  - model: Qwen/CodeQwen1.5-7B-Chat
    #no parameters necessary for base model
  - model: Qwen/CodeQwen1.5-7B-Chat
    parameters:
      density: 0.5
      weight: 0.5

merge_method: ties
base_model: Qwen/CodeQwen1.5-7B-Chat
parameters:
  normalize: false
  int8_mask: true
dtype: float16
```

## 💻 Usage

```python
!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "ByteBrew23/SuperCode"
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"])
```