MCPcopy
hub / github.com/karpathy/nanochat / chat_sft.py

File chat_sft.py

scripts/chat_sft.py:None–None  ·  view source on GitHub ↗

Source from the content-addressed store, hash-verified

1"""
2Supervised fine-tuning (SFT) the model.
3Run as:
4

Callers

nothing calls this directly

Calls 15

autodetect_device_typeFunction · 0.90
compute_initFunction · 0.90
print0Function · 0.90
get_peak_flopsFunction · 0.90
DummyWandbClass · 0.90
load_modelFunction · 0.90
get_token_bytesFunction · 0.90
get_base_dirFunction · 0.90
load_optimizer_stateFunction · 0.90
SmolTalkClass · 0.90
CustomJSONClass · 0.90
MMLUClass · 0.90

Tested by

no test coverage detected