EADST

Check the Index and Token from Tiktoken

Check the Index and Token from Tiktoken

import base64
path = "/home/your_dict_path.tiktoken"
f = open(path, "rb").read()
index = 0
for line in f.splitlines():
    l = line.split()
    print("index: ", l[1])
    print("encode: ", l[0])
    print("decode: ", base64.b64decode(l[0]))
    index += 1
    if index > 20:
        break

Reference Code

相关标签
About Me
XD
Goals determine what you are going to be.
Category
标签云
财报 图标 Agent CAM Jupyter Datetime Anaconda GoogLeNet UNIX SQL Website Quantization BeautifulSoup Baidu Docker 图形思考法 Excel v0.dev DeepStream Bert Color 阿里云 Land Rebuttal Heatmap Image2Text 公式 域名 OCR GGML Claude Vmess Ubuntu Dataset 关于博主 Vim Clash 净利润 tqdm Use RAR CV Review SVR Conda FP32 Shortcut AI Paddle Quantize SQLite XML OpenAI Food PDB WAN BTC Linux Card NameSilo ONNX Random CSV CTC RGB hf PDF Llama llama.cpp EXCEL Pillow Math v2ray ModelScope Django Ptyhon uWSGI Distillation TTS git-lfs Streamlit Nginx 多线程 Pytorch BF16 logger 报税 Qwen NLP Bitcoin GPTQ WebCrawler Qwen2 FlashAttention 音频 Github OpenCV LaTeX Mixtral GIT 顶会 MD5 Magnet Git ResNet-50 printf 飞书 ChatGPT Freesound Plate Miniforge 证件照 FP16 Hotel Animate Jetson API Data QWEN VSCode 第一性原理 FastAPI PIP Interview 云服务器 Crawler News Hungarian TSV icon GPT4 Augmentation PyCharm Domain COCO Password Bin Web Logo Pickle LoRA SAM Zip Gemma diffusers Michelin VPN Transformers CLAP Disk transformers Sklearn CUDA torchinfo TensorFlow Bipartite XGBoost Markdown Google FP8 Template Breakpoint UI Statistics LLAMA YOLO PyTorch HuggingFace SPIE 递归学习法 Plotly 版权 NLTK Knowledge CC Qwen2.5 Algorithm Python Tracking DeepSeek mmap 签证 Attention Translation Pandas Paper Tensor 论文速读 IndexTTS2 Video 搞笑 多进程 uwsgi Firewall Hilton 强化学习 FP64 Search InvalidArgumentError Proxy Tiktoken HaggingFace 论文 LeetCode 继承 Base64 Numpy 腾讯云 Safetensors C++ VGG-16 TensorRT Cloudreve LLM Permission CEIR JSON 算法题 Input git Windows tar Diagram scipy
站点统计

本站现有博文327篇,共被浏览833641

本站已经建立2538天!

热门文章
文章归档
回到顶部