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

本站现有博文323篇,共被浏览796082

本站已经建立2493天!

热门文章
文章归档
回到顶部