Commit History

tokenizer: fix bos_token to <|im_start|> (was duplicate-keyed null)
79d0501
verified

AntonXue commited on

tokenizer: set bos_token=<|im_start|> (matches model config bos_token_id=151644)
781c80b
verified

AntonXue commited on

tokenizer: set bos_token=<|im_start|> (matches model config bos_token_id=151644)
f82c77f
verified

AntonXue commited on

README: report 50k training steps (matches truncated log + SWA window)
0cdeb73
verified

AntonXue commited on

Initial release: SWA-averaged Stage-1 endpoint (steps 46k-50k, 1k stride)
4a4735e
verified

AntonXue commited on

initial commit
8ce2705
verified

AntonXue commited on