From 4f2c8ef59f9268b7f3aae0c127b52a45d4c1c706 Mon Sep 17 00:00:00 2001 From: Pete Walsh Date: Sun, 17 Nov 2024 13:13:21 -0800 Subject: [PATCH] Update README.md --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index 3effcfc6..9979d4fa 100644 --- a/README.md +++ b/README.md @@ -37,7 +37,7 @@ To see the exact usage for each script, run the script without any arguments. Throughput numbers from these scripts with various different configuration settings are reported below, measured on a cluster with NVIDIA H100 GPUs. -| Model size | Model arch | Context length | Precision | Throughput[^1] | Training script | Commandline overrides                                    | +| Model size | Model arch.   | Context length | Precision | Throughput[^1] | Training script | Commandline overrides                                    | | :--------: | :--------: | :------------: | :-------: | -----------: | :----------- | :-------- | | **1B** | OLMo-1124 | 4096 | BF16 | 55,000 TPS | `OLMo-1B.py` | | | | | 4096 | BF16/FP8[^2] | 65,000 TPS | `OLMo-1B.py` | `--model.float8_config.enabled=true` |