Automate end-to-end training of small language models with the Distil Labs CLI.
npx skills add https://github.com/distil-labs/distil-cli-skill --skill distil-cli
Please help me install this Agent Skill. Skill: distil-cli Source: https://github.com/distil-labs/distil-cli-skill/tree/main Command: npx skills add https://github.com/distil-labs/distil-cli-skill --skill distil-cli
The Distil CLI Skill automates end-to-end training of task-specific small language models (SLMs) using the Distil Labs CLI, reducing manual steps and enabling rapid experimentation.
Install the Distil Labs CLI, authenticate, create a model, upload data, run teacher evaluation, run training, and download the trained model.
High-intent search queries and answers about installing and using this skill.
Prepare datasets for classification, QA, or tool-calling tasks by using the Distil CLI to generate and format training data, which structures raw inputs into the schema required for distilling small language models.
You need to install the Distil Labs CLI, authenticate your account, and create a model definition before uploading data and running teacher evaluations for local training.
Teacher evaluation in distilling small language models is the process of running a larger model to assess and generate outputs on your dataset, which the Distil CLI uses to guide the training of the smaller model.
Prepare datasets for classification or tool-calling model training by using the Distil CLI to generate and format data, ensuring inputs match the schema required for distilling task-specific models.
kengzExecute deep reinforcement learning benchmarks in the SLM-Lab framework.
RachasumanthDeploy trained machine learning models for inference using vLLM, TGI, Ollama, and llama.cpp.
surus-latGenerate synthetic benchmark datasets as JSONL input-output pairs from task specifications.
Supporter09Compress large language models via teacher-to-student knowledge distillation.
