Rain-7B-v0.1 / README.md
raincandy-u's picture
Update README.md
1282e45 verified
---
license: other
license_name: tongyi-qianwen
license_link: https://huggingface.co/Qwen/Qwen1.5-7B-Chat/raw/main/LICENSE
datasets:
- yys/OpenOrca-Chinese
language:
- zh
- en
pipeline_tag: text-generation
tags:
- CoT
---
<style>
@font-face {
font-family: Zpix;
src: url(https://zpix.now.sh/zpix.woff2?v2021-03-21);
}
* {
font-family:Zpix;
}
#main-ame-back {
font-family:Zpix;
color: #fd96fd !important;
padding: 15px;
}
a {
color:#fd87c2 !important
}
#main-ame-back h1{
color:#8e45f5 !important;
}
</style>
<img src="https://pbs.twimg.com/media/GKJ6VOdbIAAo2yr?format=png&name=900x900"></img>
<div id="main-ame-back">
<div style="font-size:40px;color: #ebb4dd;font-weight:bolder;">ジェルばんは~</div>
<br>
<h1>🧬UPDATE: Please see <a href="https://huggingface.co/raincandy-u/Rain-7B-v0.2">Here</a> for v0.2 model.</h1>
<h1>🧬Rain-7B-v0.1</h1>
Rain-7B-v0.1 is an experimental model finetuned on <a href="https://huggingface.co/Qwen/Qwen1.5-7B-Chat">Qwen1.5-7B-Chat</a> with thousands of <b>chain of thought</b> conversations.
It work better for `"think step by step"` prompt.
<h1>🧬Evaluation</h1>
|Model name|MMLU|
|---|---|
|Qwen1.5-7B-Chat|55.8|
|Rain-7B-v0.1|58.1|
<h1>🧬Usage</h1>
```python
!pip install -qU transformers accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "raincandy-u/Rain-7B-v0.1"
messages = [{"role": "user", "content": "What is chain of thoughts?"}]
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"])
```
</div>