CLARABY MINESPACE INC.Development Studio ↗
CLARA / INTELLIGENCE

Model workspace.

Build knowledge, train a model and assemble agents in one workspace.

Documents and model state stay in this browser. Browser storage is not encrypted or backed up automatically.

Opening workspace…
Model revision—Persistent checkpoint
Documents learned—Approved training corpus
Transitions—Observed token pairs
Pending queue—Ready to train
01 / SOURCE MATERIAL

Corpus library

Start with the included teaching corpus or import text you have permission to train on.

64 documents · 16,000 characters each · English tokenization

No documents loaded.

02 / LEARNING ENGINE

Train your model

Each batch updates word-level statistics and a compact neural character predictor. Inspect both models and export their checkpoints.

Training coverage
0%0 / 0
Automatic processing

Enabled local training continues while this workspace is open and visible.

Neural parameters890Trainable embedding + softmax
Characters trained—— pending
Neural training loss—Smoothed cross-entropy

Model exports can reveal learned training text. Keep private. Deleting a learned document clears the model and queues the remaining corpus for rebuilding.

03 / AGENT WORKFLOWS

Create an agent

Configure a reusable, read-only agent that uses the selected model.

AGENT OUTPUT

Results will show excerpts with provenance or learned prediction probabilities. Queries are not added to training.

04 / MODEL QUALITY

Evaluate and verify

Held-out perplexity measures next-token prediction on documents not trained into the model.

Held-out perplexity—
Evaluated token pairs—
Neural character perplexity—
Evaluated characters—

Add separate evaluation documents. Lower perplexity is better only for comparable data and vocabulary; it is not a measure of factual accuracy. Neural evaluation uses up to 2,048 held-out characters; independent word and character scores are not directly comparable.

Corpus ingestion beyond this workspace

Operators can import permitted text files and explicitly allowlisted HTTPS plain-text URLs using the bundled private CLI. Hosted batch training can run through optional cron. No arbitrary web crawler runs on the public server.

Read the training guide ↗

Only approved corpus content is learned. Ordinary CLARA projects, enterprise data and your agent queries are not automatically collected. Data policy.