From e3f4374e81d41aef96edd28be91560ec06cb31e8 Mon Sep 17 00:00:00 2001 From: Jan Wassenberg Date: Fri, 7 Jun 2024 01:31:43 -0700 Subject: [PATCH] Fix fix for weight type define, refs #198 GEMMA_WEIGHT_T is indeed the correct flag for the C++ compiler, but the readme references CMake, and there the correct flag name is WEIGHT_TYPE. PiperOrigin-RevId: 641170380 --- README.md | 12 +++++++----- 1 file changed, 7 insertions(+), 5 deletions(-) diff --git a/README.md b/README.md index 4626e3fa..1240616f 100644 --- a/README.md +++ b/README.md @@ -151,13 +151,15 @@ cmake -B build **or** if you downloaded bfloat16 weights (any model *without* `-sfp` in the name), instead of running cmake with no options as above, run cmake with -GEMMA_WEIGHT_T set to [highway's](https://github.com/google/highway) -`hwy::bfloat16_t` type. We intend to soon support all weight types without -requiring compiler flags. Note that we recommend using `-sfp` weights instead of -bfloat16 for faster inference. +WEIGHT_TYPE set to [highway's](https://github.com/google/highway) +`hwy::bfloat16_t` type. Alternatively, you can also add +`-DGEMMA_WEIGHT_T=hwy::bfloat16_t` to the C++ compiler flags. + +We intend to soon support all weight types without requiring extra flags. Note +that we recommend using `-sfp` weights instead of bfloat16 for faster inference. ```sh -cmake -B build -DGEMMA_WEIGHT_T=hwy::bfloat16_t +cmake -B build -DWEIGHT_TYPE=hwy::bfloat16_t ``` After running whichever of the above `cmake` invocations that is appropriate for