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

本站现有博文332篇,共被浏览875938

本站已经建立2583天!

热门文章
文章归档
回到顶部