Commit Graph

8 Commits

Author SHA1 Message Date
Meng Zhang a1cf66ea94 working in cpu, metal buggy 2023-09-15 18:45:43 +08:00
Meng Zhang ab13d071e1 store mqa directly 2023-09-15 14:18:36 +08:00
Meng Zhang dac31da489 fix comments 2023-09-15 12:57:38 +08:00
Meng Zhang 0be15e162c fix head count kv 2023-09-15 12:56:20 +08:00
Meng Zhang 2683611944 set n_positions to max_positioin_embeddings 2023-09-15 12:35:46 +08:00
Meng Zhang 166a259f67 set head_count_kv = 1 2023-09-15 12:12:27 +08:00
Meng Zhang 76d32cca59 convert MQA to MHA 2023-09-15 11:42:16 +08:00
Meng Zhang eb7f0eba3e support convert starcoder weights to gguf 2023-09-15 11:24:24 +08:00