Training Mode
Pre-Train Direct
Enter raw text directly
Pre-Train File
Upload text file
SFT Direct
Enter ChatML directly
SFT File
Upload ChatML file
For pre-training, enter raw text. Model learns to predict next character.
Drop file here or click to browse
.txt, .json, .jsonl supported
.txt, .json, .jsonl supported
.txt - Plain text file:
Your raw training text goes here. It can span multiple lines. The model learns to predict the next token.
Model Architecture
Est. Params:
~21M
(vocab ~1,756)
Tokenizer (BPE)
Higher = larger vocabulary, more compression
Training Configuration
Adam uses adaptive learning rates with momentum. Disable for simple SGD.
Training Controls
Idle
0
Epoch
0
Step
-
Loss
-
Avg Loss
Training Log
Save & Load
Save/load complete training state including model, tokenizer, hyperparameters, and training data.
Export/import just the trained model weights.
Export/import just the trained tokenizer.