home/categories/data-analysis/letta-ai-skills-letta-benchmarks-trajectory-only-count-dataset-tokens-skill-md
data-analysisdata-ai

count-dataset-tokens

This skill provides guidance for counting tokens in datasets using specific tokenizers. It should be used when tasks involve tokenizing dataset content, filtering data by domain or category, and aggregating token counts. Common triggers include requests to count tokens in HuggingFace datasets, filter datasets by specific fields, or use particular tokenizers (e.g., Qwen, DeepSeek, GPT).

letta-ai
maintainer
letta-ai
Mis à jour 1/19/2026
Étoiles
31
Forks
5
quick start

Installation and usage

This skill provides guidance for counting tokens in datasets using specific tokenizers. It should be used when tasks involve tokenizing dataset content, filtering data by domain or category, and aggregating token counts. Common triggers include requests to count tokens in HuggingFace datasets, filter datasets by specific fields, or use particular tokenizers (e.g., Qwen, DeepSeek, GPT).

Installation
$ install --globalskills.sh
Utilisation

Après l'installation, vous pouvez utiliser ce skill en exécutant la commande suivante dans votre terminal :

skills use count-dataset-tokens