happyz
/
llama.cpp
mirror of https://github.com/ggerganov/llama.cpp.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity
3,004 Commits 514 Branches 5,076 Tags 1 GiB
Commit Graph

7 Commits

Author SHA1 Message Date
Heiner 9a0629d545 Don't multiply embeddings with embedding_multiplier_scale as it happens in llama.cpp. 2024-05-25 13:27:43 +02:00
Heiner ef671c693d Address review comments by foldl. 2024-05-25 13:27:43 +02:00
Heiner d894497a96 Move print to logging: Fixes. 2024-05-25 13:27:43 +02:00
Brian 5bc4f10ee9 Update convert_grok.py to use logging module 2024-05-25 13:27:43 +02:00
Heiner 08427630c3 Use only one list of weight names, with values from the gguf module. 
This saves weights in the order in which they are in the Grok-1 files.
Since we operate weight-by-weight now, we no longer need caches and
name2key translations.

Per reviewer request, I also moved to using keys in gguf.TENSOR_NAMES.
 2024-05-25 13:27:43 +02:00
Heiner 3c57743874 Don't split MoE weights. 
As per https://github.com/ggerganov/llama.cpp/pull/7058#issuecomment-2092967508.
This helps avoid a memcopy when running.
 2024-05-25 13:27:43 +02:00
Heiner 6ddf93b286 Script to convert Grok-1 weights from raw JAX pickle files. 2024-05-25 13:27:43 +02:00