{"adoption": {"forks": 1177, "observed_at": "2026-08-28T04:10:44.983948+00:00", "stars": 10997}, "canonical_url": "https://ross.abutalabs.com/products/tokenizers", "card": {"archived": false, "artifact_type": "library", "description": "💥 Fast State-of-the-Art Tokenizers optimized for Research and Production", "domain": ["machine-learning", "large-language-models", "developer-tools"], "enriched": true, "function": ["nlp", "parser", "machine-learning", "sdk"], "health_score": 98, "homepage": "https://huggingface.co/docs/tokenizers", "language": "Rust", "license": "Apache-2.0", "license_family": "permissive", "maturity": "stable", "member_repos": ["huggingface/tokenizers"], "name": "huggingface/tokenizers", "platform": ["rust", "python", "cross-platform"], "pushed_at": "2026-08-26T16:26:22+00:00", "repo": "huggingface/tokenizers", "stars": 10997, "tags": ["tokenizer", "bpe", "wordpiece", "unigram", "hugging-face", "transformers", "text-preprocessing", "natural-language-processing", "nodejs"], "topics": ["nlp", "natural-language-processing", "natural-language-understanding", "language-model", "transformers", "bert", "gpt"], "urls": [], "use_cases": ["train a BPE tokenizer on my own corpus", "tokenize text for a transformer model", "convert text to token ids for BERT or GPT", "build a custom vocabulary for a language model", "fast tokenization of large text datasets", "map tokens back to original text offsets", "pad and truncate sequences for model input"], "what_it_is": "Hugging Face Tokenizers is a fast, Rust-based library implementing state-of-the-art tokenization algorithms (BPE, WordPiece, Unigram) with bindings for Python, Rust, and Node.js. It handles the full tokenization pipeline including normalization, pre-tokenization, training new vocabularies, and pre-processing like padding, truncation, and special token handling.", "when_to_avoid": ["you need a general-purpose text segmentation tool unrelated to ML models", "you only need simple whitespace splitting or regex tokenization", "you need subword tokenization for a language/model family with incompatible requirements"], "when_to_choose": ["you need extremely fast tokenization or vocabulary training (GBs of text in seconds)", "you are training or fine-tuning transformer models and need consistent tokenization", "you need alignment tracking to map tokens back to original text", "you want the standard tokenizer used by the Hugging Face Transformers ecosystem"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/tokenizers", "repo": "huggingface/tokenizers", "role": "main", "score": 93}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:10:44.983948+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-29T17:17:14.628665+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "881ffd60cc273e9acb8518ee9cb282e4f81368dabbef755a0701a91fb89c83fa", "fetched_at": "2026-08-28T04:10:44.983948+00:00", "kind": "readme", "missing": false, "url": "https://github.com/huggingface/tokenizers"}, {"content_hash": "a898559213331f0f1a360974874d7399e6e0c47f7767b424798a6289abdcaebc", "fetched_at": "2026-08-29T08:15:53.879326+00:00", "kind": "homepage", "missing": false, "url": "https://huggingface.co/docs/tokenizers"}, {"content_hash": "bdec26667b98a2700d86b15044cf944ca1f17f4ab8579c3d27a3e627603b9ae8", "fetched_at": "2026-08-29T08:15:53.882044+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs"}, {"content_hash": "9ffd467231687f3cacf235fccbeee5a6e7a263ef88afb084feecf2448cbac5b6", "fetched_at": "2026-08-29T08:15:53.886329+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/tokenizers/quicktour"}, {"content_hash": "120e11ad6eb6201579ea6e643e83ca8c9c008e61a503e7363499f7a476da508e", "fetched_at": "2026-08-29T08:15:53.888228+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/tokenizers/installation"}, {"content_hash": "969882ba95f065d1af6598b908e396c3b25c583059370e087449901266c31188", "fetched_at": "2026-08-29T08:15:53.890159+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/tokenizers/pipeline"}, {"content_hash": "8a1b71b2e1a07c4597aeed0cf552653bda77337696ae54d05289efb8ff85da52", "fetched_at": "2026-08-29T08:15:53.893153+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/tokenizers/components"}, {"content_hash": "c02abec9c9b627326d48d01f7d28ca80aeddeddde55d60e16b1b2b0d6a4697bc", "fetched_at": "2026-08-29T08:15:53.895162+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/tokenizers/training_from_memory"}, {"content_hash": "21cbf2ad7e53efae73a5c7292daf294927d57a53ee8d1c025bb43533ed755152", "fetched_at": "2026-08-29T08:15:53.897187+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/tokenizers/api/input-sequences"}, {"content_hash": "6d1245fb5b914178f31b6964d550c57f6029a010c8779ae8ebf86bd4ba289a70", "fetched_at": "2026-08-29T08:15:53.898872+00:00", "kind": "registry_crates", "missing": false, "url": "https://crates.io/api/v1/crates/tokenizers"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:10:44.983948+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-29T17:17:14.628665+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "881ffd60cc273e9acb8518ee9cb282e4f81368dabbef755a0701a91fb89c83fa", "fetched_at": "2026-08-28T04:10:44.983948+00:00", "kind": "readme", "missing": false, "url": "https://github.com/huggingface/tokenizers"}, {"content_hash": "a898559213331f0f1a360974874d7399e6e0c47f7767b424798a6289abdcaebc", "fetched_at": "2026-08-29T08:15:53.879326+00:00", "kind": "homepage", "missing": false, "url": "https://huggingface.co/docs/tokenizers"}, {"content_hash": "bdec26667b98a2700d86b15044cf944ca1f17f4ab8579c3d27a3e627603b9ae8", "fetched_at": "2026-08-29T08:15:53.882044+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs"}, {"content_hash": "9ffd467231687f3cacf235fccbeee5a6e7a263ef88afb084feecf2448cbac5b6", "fetched_at": "2026-08-29T08:15:53.886329+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/tokenizers/quicktour"}, {"content_hash": "120e11ad6eb6201579ea6e643e83ca8c9c008e61a503e7363499f7a476da508e", "fetched_at": "2026-08-29T08:15:53.888228+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/tokenizers/installation"}, {"content_hash": "969882ba95f065d1af6598b908e396c3b25c583059370e087449901266c31188", "fetched_at": "2026-08-29T08:15:53.890159+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/tokenizers/pipeline"}, {"content_hash": "8a1b71b2e1a07c4597aeed0cf552653bda77337696ae54d05289efb8ff85da52", "fetched_at": "2026-08-29T08:15:53.893153+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/tokenizers/components"}, {"content_hash": "c02abec9c9b627326d48d01f7d28ca80aeddeddde55d60e16b1b2b0d6a4697bc", "fetched_at": "2026-08-29T08:15:53.895162+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/tokenizers/training_from_memory"}, {"content_hash": "21cbf2ad7e53efae73a5c7292daf294927d57a53ee8d1c025bb43533ed755152", "fetched_at": "2026-08-29T08:15:53.897187+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/tokenizers/api/input-sequences"}, {"content_hash": "6d1245fb5b914178f31b6964d550c57f6029a010c8779ae8ebf86bd4ba289a70", "fetched_at": "2026-08-29T08:15:53.898872+00:00", "kind": "registry_crates", "missing": false, "url": "https://crates.io/api/v1/crates/tokenizers"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-29T17:17:14.628665+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "881ffd60cc273e9acb8518ee9cb282e4f81368dabbef755a0701a91fb89c83fa", "fetched_at": "2026-08-28T04:10:44.983948+00:00", "kind": "readme", "missing": false, "url": "https://github.com/huggingface/tokenizers"}, {"content_hash": "a898559213331f0f1a360974874d7399e6e0c47f7767b424798a6289abdcaebc", "fetched_at": "2026-08-29T08:15:53.879326+00:00", "kind": "homepage", "missing": false, "url": "https://huggingface.co/docs/tokenizers"}, {"content_hash": "bdec26667b98a2700d86b15044cf944ca1f17f4ab8579c3d27a3e627603b9ae8", "fetched_at": "2026-08-29T08:15:53.882044+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs"}, {"content_hash": "9ffd467231687f3cacf235fccbeee5a6e7a263ef88afb084feecf2448cbac5b6", "fetched_at": "2026-08-29T08:15:53.886329+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/tokenizers/quicktour"}, {"content_hash": "120e11ad6eb6201579ea6e643e83ca8c9c008e61a503e7363499f7a476da508e", "fetched_at": "2026-08-29T08:15:53.888228+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/tokenizers/installation"}, {"content_hash": "969882ba95f065d1af6598b908e396c3b25c583059370e087449901266c31188", "fetched_at": "2026-08-29T08:15:53.890159+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/tokenizers/pipeline"}, {"content_hash": "8a1b71b2e1a07c4597aeed0cf552653bda77337696ae54d05289efb8ff85da52", "fetched_at": "2026-08-29T08:15:53.893153+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/tokenizers/components"}, {"content_hash": "c02abec9c9b627326d48d01f7d28ca80aeddeddde55d60e16b1b2b0d6a4697bc", "fetched_at": "2026-08-29T08:15:53.895162+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/tokenizers/training_from_memory"}, {"content_hash": "21cbf2ad7e53efae73a5c7292daf294927d57a53ee8d1c025bb43533ed755152", "fetched_at": "2026-08-29T08:15:53.897187+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/tokenizers/api/input-sequences"}, {"content_hash": "6d1245fb5b914178f31b6964d550c57f6029a010c8779ae8ebf86bd4ba289a70", "fetched_at": "2026-08-29T08:15:53.898872+00:00", "kind": "registry_crates", "missing": false, "url": "https://crates.io/api/v1/crates/tokenizers"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:10:44.983948+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:10:44.983948+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:10:44.983948+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-29T17:17:14.628665+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "881ffd60cc273e9acb8518ee9cb282e4f81368dabbef755a0701a91fb89c83fa", "fetched_at": "2026-08-28T04:10:44.983948+00:00", "kind": "readme", "missing": false, "url": "https://github.com/huggingface/tokenizers"}, {"content_hash": "a898559213331f0f1a360974874d7399e6e0c47f7767b424798a6289abdcaebc", "fetched_at": "2026-08-29T08:15:53.879326+00:00", "kind": "homepage", "missing": false, "url": "https://huggingface.co/docs/tokenizers"}, {"content_hash": "bdec26667b98a2700d86b15044cf944ca1f17f4ab8579c3d27a3e627603b9ae8", "fetched_at": "2026-08-29T08:15:53.882044+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs"}, {"content_hash": "9ffd467231687f3cacf235fccbeee5a6e7a263ef88afb084feecf2448cbac5b6", "fetched_at": "2026-08-29T08:15:53.886329+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/tokenizers/quicktour"}, {"content_hash": "120e11ad6eb6201579ea6e643e83ca8c9c008e61a503e7363499f7a476da508e", "fetched_at": "2026-08-29T08:15:53.888228+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/tokenizers/installation"}, {"content_hash": "969882ba95f065d1af6598b908e396c3b25c583059370e087449901266c31188", "fetched_at": "2026-08-29T08:15:53.890159+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/tokenizers/pipeline"}, {"content_hash": "8a1b71b2e1a07c4597aeed0cf552653bda77337696ae54d05289efb8ff85da52", "fetched_at": "2026-08-29T08:15:53.893153+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/tokenizers/components"}, {"content_hash": "c02abec9c9b627326d48d01f7d28ca80aeddeddde55d60e16b1b2b0d6a4697bc", "fetched_at": "2026-08-29T08:15:53.895162+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/tokenizers/training_from_memory"}, {"content_hash": "21cbf2ad7e53efae73a5c7292daf294927d57a53ee8d1c025bb43533ed755152", "fetched_at": "2026-08-29T08:15:53.897187+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/tokenizers/api/input-sequences"}, {"content_hash": "6d1245fb5b914178f31b6964d550c57f6029a010c8779ae8ebf86bd4ba289a70", "fetched_at": "2026-08-29T08:15:53.898872+00:00", "kind": "registry_crates", "missing": false, "url": "https://crates.io/api/v1/crates/tokenizers"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:10:44.983948+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:10:44.983948+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-29T17:17:14.628665+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "881ffd60cc273e9acb8518ee9cb282e4f81368dabbef755a0701a91fb89c83fa", "fetched_at": "2026-08-28T04:10:44.983948+00:00", "kind": "readme", "missing": false, "url": "https://github.com/huggingface/tokenizers"}, {"content_hash": "a898559213331f0f1a360974874d7399e6e0c47f7767b424798a6289abdcaebc", "fetched_at": "2026-08-29T08:15:53.879326+00:00", "kind": "homepage", "missing": false, "url": "https://huggingface.co/docs/tokenizers"}, {"content_hash": "bdec26667b98a2700d86b15044cf944ca1f17f4ab8579c3d27a3e627603b9ae8", "fetched_at": "2026-08-29T08:15:53.882044+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs"}, {"content_hash": "9ffd467231687f3cacf235fccbeee5a6e7a263ef88afb084feecf2448cbac5b6", "fetched_at": "2026-08-29T08:15:53.886329+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/tokenizers/quicktour"}, {"content_hash": "120e11ad6eb6201579ea6e643e83ca8c9c008e61a503e7363499f7a476da508e", "fetched_at": "2026-08-29T08:15:53.888228+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/tokenizers/installation"}, {"content_hash": "969882ba95f065d1af6598b908e396c3b25c583059370e087449901266c31188", "fetched_at": "2026-08-29T08:15:53.890159+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/tokenizers/pipeline"}, {"content_hash": "8a1b71b2e1a07c4597aeed0cf552653bda77337696ae54d05289efb8ff85da52", "fetched_at": "2026-08-29T08:15:53.893153+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/tokenizers/components"}, {"content_hash": "c02abec9c9b627326d48d01f7d28ca80aeddeddde55d60e16b1b2b0d6a4697bc", "fetched_at": "2026-08-29T08:15:53.895162+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/tokenizers/training_from_memory"}, {"content_hash": "21cbf2ad7e53efae73a5c7292daf294927d57a53ee8d1c025bb43533ed755152", "fetched_at": "2026-08-29T08:15:53.897187+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/tokenizers/api/input-sequences"}, {"content_hash": "6d1245fb5b914178f31b6964d550c57f6029a010c8779ae8ebf86bd4ba289a70", "fetched_at": "2026-08-29T08:15:53.898872+00:00", "kind": "registry_crates", "missing": false, "url": "https://crates.io/api/v1/crates/tokenizers"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:10:44.983948+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:10:44.983948+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:10:44.983948+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-29T17:17:14.628665+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "881ffd60cc273e9acb8518ee9cb282e4f81368dabbef755a0701a91fb89c83fa", "fetched_at": "2026-08-28T04:10:44.983948+00:00", "kind": "readme", "missing": false, "url": "https://github.com/huggingface/tokenizers"}, {"content_hash": "a898559213331f0f1a360974874d7399e6e0c47f7767b424798a6289abdcaebc", "fetched_at": "2026-08-29T08:15:53.879326+00:00", "kind": "homepage", "missing": false, "url": "https://huggingface.co/docs/tokenizers"}, {"content_hash": "bdec26667b98a2700d86b15044cf944ca1f17f4ab8579c3d27a3e627603b9ae8", "fetched_at": "2026-08-29T08:15:53.882044+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs"}, {"content_hash": "9ffd467231687f3cacf235fccbeee5a6e7a263ef88afb084feecf2448cbac5b6", "fetched_at": "2026-08-29T08:15:53.886329+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/tokenizers/quicktour"}, {"content_hash": "120e11ad6eb6201579ea6e643e83ca8c9c008e61a503e7363499f7a476da508e", "fetched_at": "2026-08-29T08:15:53.888228+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/tokenizers/installation"}, {"content_hash": "969882ba95f065d1af6598b908e396c3b25c583059370e087449901266c31188", "fetched_at": "2026-08-29T08:15:53.890159+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/tokenizers/pipeline"}, {"content_hash": "8a1b71b2e1a07c4597aeed0cf552653bda77337696ae54d05289efb8ff85da52", "fetched_at": "2026-08-29T08:15:53.893153+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/tokenizers/components"}, {"content_hash": "c02abec9c9b627326d48d01f7d28ca80aeddeddde55d60e16b1b2b0d6a4697bc", "fetched_at": "2026-08-29T08:15:53.895162+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/tokenizers/training_from_memory"}, {"content_hash": "21cbf2ad7e53efae73a5c7292daf294927d57a53ee8d1c025bb43533ed755152", "fetched_at": "2026-08-29T08:15:53.897187+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/tokenizers/api/input-sequences"}, {"content_hash": "6d1245fb5b914178f31b6964d550c57f6029a010c8779ae8ebf86bd4ba289a70", "fetched_at": "2026-08-29T08:15:53.898872+00:00", "kind": "registry_crates", "missing": false, "url": "https://crates.io/api/v1/crates/tokenizers"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:10:44.983948+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:10:44.983948+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-29T17:17:14.628665+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "881ffd60cc273e9acb8518ee9cb282e4f81368dabbef755a0701a91fb89c83fa", "fetched_at": "2026-08-28T04:10:44.983948+00:00", "kind": "readme", "missing": false, "url": "https://github.com/huggingface/tokenizers"}, {"content_hash": "a898559213331f0f1a360974874d7399e6e0c47f7767b424798a6289abdcaebc", "fetched_at": "2026-08-29T08:15:53.879326+00:00", "kind": "homepage", "missing": false, "url": "https://huggingface.co/docs/tokenizers"}, {"content_hash": "bdec26667b98a2700d86b15044cf944ca1f17f4ab8579c3d27a3e627603b9ae8", "fetched_at": "2026-08-29T08:15:53.882044+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs"}, {"content_hash": "9ffd467231687f3cacf235fccbeee5a6e7a263ef88afb084feecf2448cbac5b6", "fetched_at": "2026-08-29T08:15:53.886329+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/tokenizers/quicktour"}, {"content_hash": "120e11ad6eb6201579ea6e643e83ca8c9c008e61a503e7363499f7a476da508e", "fetched_at": "2026-08-29T08:15:53.888228+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/tokenizers/installation"}, {"content_hash": "969882ba95f065d1af6598b908e396c3b25c583059370e087449901266c31188", "fetched_at": "2026-08-29T08:15:53.890159+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/tokenizers/pipeline"}, {"content_hash": "8a1b71b2e1a07c4597aeed0cf552653bda77337696ae54d05289efb8ff85da52", "fetched_at": "2026-08-29T08:15:53.893153+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/tokenizers/components"}, {"content_hash": "c02abec9c9b627326d48d01f7d28ca80aeddeddde55d60e16b1b2b0d6a4697bc", "fetched_at": "2026-08-29T08:15:53.895162+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/tokenizers/training_from_memory"}, {"content_hash": "21cbf2ad7e53efae73a5c7292daf294927d57a53ee8d1c025bb43533ed755152", "fetched_at": "2026-08-29T08:15:53.897187+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/tokenizers/api/input-sequences"}, {"content_hash": "6d1245fb5b914178f31b6964d550c57f6029a010c8779ae8ebf86bd4ba289a70", "fetched_at": "2026-08-29T08:15:53.898872+00:00", "kind": "registry_crates", "missing": false, "url": "https://crates.io/api/v1/crates/tokenizers"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-29T17:17:14.628665+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "881ffd60cc273e9acb8518ee9cb282e4f81368dabbef755a0701a91fb89c83fa", "fetched_at": "2026-08-28T04:10:44.983948+00:00", "kind": "readme", "missing": false, "url": "https://github.com/huggingface/tokenizers"}, {"content_hash": "a898559213331f0f1a360974874d7399e6e0c47f7767b424798a6289abdcaebc", "fetched_at": "2026-08-29T08:15:53.879326+00:00", "kind": "homepage", "missing": false, "url": "https://huggingface.co/docs/tokenizers"}, {"content_hash": "bdec26667b98a2700d86b15044cf944ca1f17f4ab8579c3d27a3e627603b9ae8", "fetched_at": "2026-08-29T08:15:53.882044+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs"}, {"content_hash": "9ffd467231687f3cacf235fccbeee5a6e7a263ef88afb084feecf2448cbac5b6", "fetched_at": "2026-08-29T08:15:53.886329+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/tokenizers/quicktour"}, {"content_hash": "120e11ad6eb6201579ea6e643e83ca8c9c008e61a503e7363499f7a476da508e", "fetched_at": "2026-08-29T08:15:53.888228+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/tokenizers/installation"}, {"content_hash": "969882ba95f065d1af6598b908e396c3b25c583059370e087449901266c31188", "fetched_at": "2026-08-29T08:15:53.890159+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/tokenizers/pipeline"}, {"content_hash": "8a1b71b2e1a07c4597aeed0cf552653bda77337696ae54d05289efb8ff85da52", "fetched_at": "2026-08-29T08:15:53.893153+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/tokenizers/components"}, {"content_hash": "c02abec9c9b627326d48d01f7d28ca80aeddeddde55d60e16b1b2b0d6a4697bc", "fetched_at": "2026-08-29T08:15:53.895162+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/tokenizers/training_from_memory"}, {"content_hash": "21cbf2ad7e53efae73a5c7292daf294927d57a53ee8d1c025bb43533ed755152", "fetched_at": "2026-08-29T08:15:53.897187+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/tokenizers/api/input-sequences"}, {"content_hash": "6d1245fb5b914178f31b6964d550c57f6029a010c8779ae8ebf86bd4ba289a70", "fetched_at": "2026-08-29T08:15:53.898872+00:00", "kind": "registry_crates", "missing": false, "url": "https://crates.io/api/v1/crates/tokenizers"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-29T17:17:14.628665+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "881ffd60cc273e9acb8518ee9cb282e4f81368dabbef755a0701a91fb89c83fa", "fetched_at": "2026-08-28T04:10:44.983948+00:00", "kind": "readme", "missing": false, "url": "https://github.com/huggingface/tokenizers"}, {"content_hash": "a898559213331f0f1a360974874d7399e6e0c47f7767b424798a6289abdcaebc", "fetched_at": "2026-08-29T08:15:53.879326+00:00", "kind": "homepage", "missing": false, "url": "https://huggingface.co/docs/tokenizers"}, {"content_hash": "bdec26667b98a2700d86b15044cf944ca1f17f4ab8579c3d27a3e627603b9ae8", "fetched_at": "2026-08-29T08:15:53.882044+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs"}, {"content_hash": "9ffd467231687f3cacf235fccbeee5a6e7a263ef88afb084feecf2448cbac5b6", "fetched_at": "2026-08-29T08:15:53.886329+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/tokenizers/quicktour"}, {"content_hash": "120e11ad6eb6201579ea6e643e83ca8c9c008e61a503e7363499f7a476da508e", "fetched_at": "2026-08-29T08:15:53.888228+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/tokenizers/installation"}, {"content_hash": "969882ba95f065d1af6598b908e396c3b25c583059370e087449901266c31188", "fetched_at": "2026-08-29T08:15:53.890159+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/tokenizers/pipeline"}, {"content_hash": "8a1b71b2e1a07c4597aeed0cf552653bda77337696ae54d05289efb8ff85da52", "fetched_at": "2026-08-29T08:15:53.893153+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/tokenizers/components"}, {"content_hash": "c02abec9c9b627326d48d01f7d28ca80aeddeddde55d60e16b1b2b0d6a4697bc", "fetched_at": "2026-08-29T08:15:53.895162+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/tokenizers/training_from_memory"}, {"content_hash": "21cbf2ad7e53efae73a5c7292daf294927d57a53ee8d1c025bb43533ed755152", "fetched_at": "2026-08-29T08:15:53.897187+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/tokenizers/api/input-sequences"}, {"content_hash": "6d1245fb5b914178f31b6964d550c57f6029a010c8779ae8ebf86bd4ba289a70", "fetched_at": "2026-08-29T08:15:53.898872+00:00", "kind": "registry_crates", "missing": false, "url": "https://crates.io/api/v1/crates/tokenizers"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-29T17:17:14.628665+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "881ffd60cc273e9acb8518ee9cb282e4f81368dabbef755a0701a91fb89c83fa", "fetched_at": "2026-08-28T04:10:44.983948+00:00", "kind": "readme", "missing": false, "url": "https://github.com/huggingface/tokenizers"}, {"content_hash": "a898559213331f0f1a360974874d7399e6e0c47f7767b424798a6289abdcaebc", "fetched_at": "2026-08-29T08:15:53.879326+00:00", "kind": "homepage", "missing": false, "url": "https://huggingface.co/docs/tokenizers"}, {"content_hash": "bdec26667b98a2700d86b15044cf944ca1f17f4ab8579c3d27a3e627603b9ae8", "fetched_at": "2026-08-29T08:15:53.882044+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs"}, {"content_hash": "9ffd467231687f3cacf235fccbeee5a6e7a263ef88afb084feecf2448cbac5b6", "fetched_at": "2026-08-29T08:15:53.886329+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/tokenizers/quicktour"}, {"content_hash": "120e11ad6eb6201579ea6e643e83ca8c9c008e61a503e7363499f7a476da508e", "fetched_at": "2026-08-29T08:15:53.888228+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/tokenizers/installation"}, {"content_hash": "969882ba95f065d1af6598b908e396c3b25c583059370e087449901266c31188", "fetched_at": "2026-08-29T08:15:53.890159+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/tokenizers/pipeline"}, {"content_hash": "8a1b71b2e1a07c4597aeed0cf552653bda77337696ae54d05289efb8ff85da52", "fetched_at": "2026-08-29T08:15:53.893153+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/tokenizers/components"}, {"content_hash": "c02abec9c9b627326d48d01f7d28ca80aeddeddde55d60e16b1b2b0d6a4697bc", "fetched_at": "2026-08-29T08:15:53.895162+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/tokenizers/training_from_memory"}, {"content_hash": "21cbf2ad7e53efae73a5c7292daf294927d57a53ee8d1c025bb43533ed755152", "fetched_at": "2026-08-29T08:15:53.897187+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/tokenizers/api/input-sequences"}, {"content_hash": "6d1245fb5b914178f31b6964d550c57f6029a010c8779ae8ebf86bd4ba289a70", "fetched_at": "2026-08-29T08:15:53.898872+00:00", "kind": "registry_crates", "missing": false, "url": "https://crates.io/api/v1/crates/tokenizers"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 99, "longevity": 100, "rhythm": 81}, "computed_at": "2026-09-03T02:20:16.233290+00:00", "flags": [], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 2497, "days_push": 7, "days_rel": 128, "gap_med": 25, "n_releases_24m": 12}, "score": 93, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}