Commit History
-
Converter now emits nanochat optimizer shards for an SFT warm-start
Verified signature412ea12 -
Correct optimizer-state notes: SFT needs only the weights; W_O axis is a no-op at d24
Verified signature162df34 -
Add model card, meta.json, logs, tokenizer, training source, and nanochat converter
Verified signature11f07f9 -
Upload folder using huggingface_hub
Verified signaturea669958 -
initial commit
Verified signaturef911c2f