Hugging Face's logo

ChrisMcCormick
/
decoderstack-d24

English
decoderstack
nanochat
pretraining
Model card Files
xet
 Community
decoderstack-d24 / base_checkpoints /d24_decoderstack /meta_005568.json

Commit History

  1. meta_005568.json: add user_config so chat_sft inherits the run's LRs

    ChrisMcCormick
    Verified signature
    3768187

  2. Correct optimizer-state notes: SFT needs only the weights; W_O axis is a no-op at d24

    ChrisMcCormick
    Verified signature
    162df34

  3. Add model card, meta.json, logs, tokenizer, training source, and nanochat converter

    ChrisMcCormick
    Verified signature
    11f07f9