PoliBa-DeepLearning/NanoSocrates
2
0
Fork 0
Code Issues 3 Pull Requests 1 Actions Packages Projects Releases Wiki Activity

Modified UML diagram

Browse Source
This commit is contained in:
Christian Risi 2025-09-28 18:05:03 +02:00
parent e433941405
commit 564b0d712e
1 changed files with 47 additions and 10 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

57
Project_Model/UML/bpe.excalidraw.json
View File

@ -482,20 +482,20 @@
"index": "aJ", "index": "aJ",
"roundness": null, "roundness": null,
"seed": 1963214021, "seed": 1963214021,
"version": 422, "version": 464,
"versionNonce": 903841927, "versionNonce": 1104453739,
"isDeleted": false, "isDeleted": false,
"boundElements": [], "boundElements": [],
"updated": 1758879973600, "updated": 1759053302739,
"link": null, "link": null,
"locked": false, "locked": false,
"text": "class TokeNano:\n\n - splitter: NanoSocratesSplitter\n - bpe_encoder: NanoSocratesBPE\n - special_encoder: NanoSocratesSpecial\n\n + encode(corpus: str) -> [int]\n\n - encode_special(piece: str) -> int\n\n - encode_bpe(piece: str) -> [int]", "text": "class TokeNanoCore:\n\n - splitter: NanoSocratesSplitter\n - bpe_encoder: NanoSocratesBPE\n - special_encoder: NanoSocratesSpecial\n\n + encode(corpus: str) -> [int]\n\n - encode_special(piece: str) -> int\n\n - encode_bpe(piece: str) -> [int]",
"fontSize": 20, "fontSize": 20,
"fontFamily": 8, "fontFamily": 8,
"textAlign": "left", "textAlign": "left",
"verticalAlign": "top", "verticalAlign": "top",
"containerId": null, "containerId": null,
"originalText": "class TokeNano:\n\n - splitter: NanoSocratesSplitter\n - bpe_encoder: NanoSocratesBPE\n - special_encoder: NanoSocratesSpecial\n\n + encode(corpus: str) -> [int]\n\n - encode_special(piece: str) -> int\n\n - encode_bpe(piece: str) -> [int]", "originalText": "class TokeNanoCore:\n\n - splitter: NanoSocratesSplitter\n - bpe_encoder: NanoSocratesBPE\n - special_encoder: NanoSocratesSpecial\n\n + encode(corpus: str) -> [int]\n\n - encode_special(piece: str) -> int\n\n - encode_bpe(piece: str) -> [int]",
"autoResize": true, "autoResize": true,
"lineHeight": 1.25 "lineHeight": 1.25
}, },
@ -541,7 +541,7 @@
"type": "text", "type": "text",
"x": 396.375, "x": 396.375,
"y": -107.75, "y": -107.75,
"width": 346.3997802734375, "width": 396,
"height": 100, "height": 100,
"angle": 0, "angle": 0,
"strokeColor": "#1e1e1e", "strokeColor": "#1e1e1e",
@ -556,16 +556,16 @@
"index": "aM", "index": "aM",
"roundness": null, "roundness": null,
"seed": 1187595241, "seed": 1187595241,
"version": 128, "version": 130,
"versionNonce": 1487192455, "versionNonce": 1273030504,
"isDeleted": false, "isDeleted": false,
"boundElements": [], "boundElements": [],
"updated": 1758879825591, "updated": 1759070012771,
"link": null, "link": null,
"locked": false, "locked": false,
"text": "class Encoder(ABC):\n\n + encode(corpus: str) -> [int]\n + decode(encoded: [int]) -> str ", "text": "class Encoder(ABC):\n\n + encode(corpus: str) -> [int]\n + decode(encoded: [int]) -> str ",
"fontSize": 20, "fontSize": 20,
"fontFamily": 5, "fontFamily": 8,
"textAlign": "left", "textAlign": "left",
"verticalAlign": "top", "verticalAlign": "top",
"containerId": null, "containerId": null,
@ -646,6 +646,43 @@
"originalText": "class NanoSocratesChunker:\n\n - max_bytes: int\n - max_special_length: int\n - special_token_regex: regex\n\n - residuals: str\n\n # This must be an iterator\n + read(path: Path) -> str", "originalText": "class NanoSocratesChunker:\n\n - max_bytes: int\n - max_special_length: int\n - special_token_regex: regex\n\n - residuals: str\n\n # This must be an iterator\n + read(path: Path) -> str",
"autoResize": true, "autoResize": true,
"lineHeight": 1.25 "lineHeight": 1.25
},
{
"id": "2UXjWdE_jMcsCE2oQgTXn",
"type": "text",
"x": -334.75,
"y": 1112.5,
"width": 165,
"height": 25,
"angle": 0,
"strokeColor": "#1e1e1e",
"backgroundColor": "transparent",
"fillStyle": "solid",
"strokeWidth": 2,
"strokeStyle": "solid",
"roughness": 1,
"opacity": 100,
"groupIds": [],
"frameId": null,
"index": "aQ",
"roundness": null,
"seed": 700532363,
"version": 76,
"versionNonce": 1671597672,
"isDeleted": false,
"boundElements": [],
"updated": 1759070020002,
"link": null,
"locked": false,
"text": "class TokeNano:",
"fontSize": 20,
"fontFamily": 8,
"textAlign": "left",
"verticalAlign": "top",
"containerId": null,
"originalText": "class TokeNano:",
"autoResize": true,
"lineHeight": 1.25
} }
], ],
"appState": { "appState": {