---
tags:
- merge
- mergekit
- lazymergekit
- argilla/CapybaraHermes-2.5-Mistral-7B
- WizardLM/WizardMath-7B-V1.1
base_model:
- argilla/CapybaraHermes-2.5-Mistral-7B
- WizardLM/WizardMath-7B-V1.1
---

# 試製-暮光-4x7B

試製-暮光-7B　是用[LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing)融合以下模型生成的：
* [argilla/CapybaraHermes-2.5-Mistral-7B](https://huggingface.co/argilla/CapybaraHermes-2.5-Mistral-7B)
* [WizardLM/WizardMath-7B-V1.1](https://huggingface.co/WizardLM/WizardMath-7B-V1.1)

這是一個實驗模型，目的是爲了檢驗套用在不同語言上的高品質模型調教是否能夠轉移（此模型爲英文到中文）。


# shizhi-twilight-7B

shizhi-twilight-7B is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
* [argilla/CapybaraHermes-2.5-Mistral-7B](https://huggingface.co/argilla/CapybaraHermes-2.5-Mistral-7B)
* [WizardLM/WizardMath-7B-V1.1](https://huggingface.co/WizardLM/WizardMath-7B-V1.1)

This is an experiment product on checking whether high quality fine-tuning on one language (English) could be transferred to another language (Mandarin) leveraging Slerp merge method.

## 🧩 Configuration

```yaml
models:
  - model: MediaTek-Research/Breeze-7B-Instruct-v0_1
    # No parameters necessary for base model
  - model: argilla/CapybaraHermes-2.5-Mistral-7B
    parameters:
      density: 0.53
      weight: 0.65
  - model: WizardLM/WizardMath-7B-V1.1
    parameters:
      density: 0.53
      weight: 0.35
merge_method: dare_ties
base_model: MediaTek-Research/Breeze-7B-Instruct-v0_1
parameters:
  int8_mask: true
dtype: bfloat16
```

## 💻 Usage

```python
!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "lipcut/shizhi-twilight-7B"
messages = [{"role": "user", "content": "什麼是大型語言模型?"}]

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"])
```