地平線まで行ってくる。

記録あるいは忘備録。時には検討事項。

RecuurentGemmaを試してみる

npakaさんの記事を参考にしてRecuurentGemmaを試してみる。

note.com

 

軽くてサクサク動く。ローカルで十分実用的に感じます。

質問: Create python code for plot stock price trend of APPL and META.
答え:
```python
import matplotlib.pyplot as plt
import pandas as pd

# Load the stock price data
apll = pd.read_csv('AAPL.csv')
meta = pd.read_csv('META.csv')

# Create a time series plot of the stock price data
apll.plot(x='Date', y='Close')
meta.plot(x='Date', y='Close')

# Add a line plot of the moving average of the stock price data
apll['MA'] = apll['Close'].rolling(window=20).mean()
meta['MA'] = meta['Close'].rolling(window=20).mean()

# Add the moving average lines to the plots
apll['MA'].plot(label='Moving Average')
meta['MA'].plot(label='Moving Average')

# Add a legend to the plot
plt.legend()

# Show the plot
plt.show()

 

要約も。

※文章はwikipediaより引用

質問: Summarize concisely this article.:
Artificial intelligence (AI), in its broadest sense, is intelligence exhibited by machines, particularly computer systems. It is a field of research in computer science that develops and studies methods and software which enable machines to perceive their environment and uses learning and intelligence to take actions that maximize their chances of achieving defined goals.[1] Such machines may be called AIs.
回答:  Sure, here is a concise summary of the article:

Artificial intelligence (AI) is intelligence exhibited by machines, particularly computer systems. It involves developing methods and software that enable machines to perceive their environment and make decisions to maximize their chances of achieving goals.<eos>

 

長いシークエンスも効率よく生成するとのこと。気軽に使えて性能がよいモデルがどんどん増えてきて、さらに楽しいことに・・・。

 

 

gist.github.com