I am start to learn the cryptography, so I will note the Cryptography journey in my blog
Online resources
Some Cryptography online courses
Online hack platform
China Cryptography Cipher
SM4, one China Block Cipher
…ShāngMì 4 (
I am start to learn the cryptography, so I will note the Cryptography journey in my blog
Some Cryptography online courses
Online hack platform
SM4, one China Block Cipher
…ShāngMì 4 (
Here is the github of whisper.cpp
make base.en
make medium
make large-v3
/main -m models/ggml-base.en.bin -f samples/jfk.wav
./main -m ./models/ggml-medium.bin -t 8 --step 500 --length 5000 --prompt "请用简体中文输出" -l
… 8 security vendors flagged this URL as malicious
sudo tcpdump -vv -i eth0 src 165.227.xx.xx and not dst 101.230.xx.xx port 22 -X -n
So here we need …
If you want to add the Nginx proxy for OpenAI API
You can use the following nginx configs.
location /v1/chat/completions {
proxy_pass https://api.openai.com/v1/chat/completions;
proxy_ssl_name api.openai.com;
proxy_ssl_server_name on;
# Forward all headers
proxy_pass_request_headers on;
# proxy_http_version 1.1;
}
And then restart …
conda create --name myenv310 python=3.10
environment location: /Users/xxxx/miniconda3/envs/myenv310
added / updated specs:
- python=3.10
conda activate myenv310
conda deactivate
conda env list
conda config --add channels conda-forge
conda config --set channel_priority strict
conda env create -f environment-no-nvidia.yml
conda activate stylegan3
… Refer the GoDaddy document
Find the settings for you domain want to transfer
In the CloudFlare, it says, so I need to wait for some time.
…Registry status: Client transfer prohibited. Please unlock and allow a few hours
fatal error: 'openssl/opensslv.h' file not found
brew install openssl
env LDFLAGS=”-L$(brew –prefix openssl)/lib” CFLAGS=”-I$(brew –prefix openssl)/include” pip install cryptography
…
昨天GPT-4发布,除了惊艳还是惊艳,OpenAI的进化速度超乎想象。
除此之外,最近我也在关注LLaMa((Large Language Model Meta AI)
Facebook的大型语言模型,现在已经有很多基于它进行优化的项目
比如Standford, 号称7B model已经达到 OpenAI text-davinci-003
效果
而我这里选择的是llama.cpp, 作者刚把whisper用cpp实现了一遍叫whisper.cpp, 还真是直接
整个安装过程还参考了这篇文章
LLaMa的优势
先看看我本地用了30B model的效果
git clone [email protected]:ggerganov/llama.cpp.git
cd llama.cpp
python3
… 关注AI的都应该知道最近AI界,各种技术进化的速度,已经超过想象了。
比如说
各种模型迭代的速度,正在很疯狂的往前逛奔,每天早上都能看到一些意想不到的新奇的东西。
而今天看到的是有关大脑的
这篇论文提出了一种基于渗透模型的图像重建方法,以重建人脑活动的视觉体验。研究者使用了一种名为Stable Diffusion的潜在渗透模型,该模型减少了渗透模型的计算成本,同时保留了其高生成性能。他们进一步研究了不同组件如何与不同的大脑功能相关联,并表明该方法可以直接重建高分辨率图像,不需要额外的复杂深度学习模型的训练和微调。研究为重建人脑活动图像提供了一种有前途的方法,并为理解渗透模型提供了一个新的框架。
简单的说就是可以通过仪器扫描大脑的活动,然后通过Stable Diffusion重现大脑的景象,相当于视觉你的大脑所想。
这个潘多拉魔盒一旦打开,以后人类是不是就没有秘密可言了
Try the Stable Diffusion, and ChilloutMix, and LoRA to generate the images on Apple M1.
I follow this guideline to setup the Stable Diffusion running on my Apple M1.
brew install cmake protobuf rust [email protected]
…