"megatron/training/tokenizer/tokenizer.py" did not exist on "dedb2ef78cdf54a54b6986ac0e8fc0045dd4fa07"
-
Li Zhang authored
* add GQA for llama2 * fix model conversion * fix lint & remove dev log * update news * minor * fix allocation size * fix split_dim for w_qkv.bias
f07b697b
