README.md

---
tags:
- merge
- mergekit
- lazymergekit
- shenzhi-Chinese
- 7B
base_model:
- shenzhi-wang/Mistral-7B-v0.3-Chinese-Chat
- MaziyarPanahi/Calme-7B-Instruct-v0.3
license:
- other
---

# Mistral-7B-v0.3-Chinese-lingyang-v1

#该模型是实验性的，因此无法保证结果。

Mistral-7B-v0.3-Chinese-lingyang-v1 is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
* [shenzhi-wang/Mistral-7B-v0.3-Chinese-Chat](https://huggingface.co/shenzhi-wang/Mistral-7B-v0.3-Chinese-Chat)
* [MaziyarPanahi/Calme-7B-Instruct-v0.3](https://huggingface.co/MaziyarPanahi/Calme-7B-Instruct-v0.3)

## 💻 Usage

```python
!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "wwe180/Mistral-7B-v0.3-Chinese-lingyang-v1"
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"])
```