File tree Expand file tree Collapse file tree 1 file changed +1
-1
lines changed Expand file tree Collapse file tree 1 file changed +1
-1
lines changed Original file line number Diff line number Diff line change @@ -37,7 +37,7 @@ To see the exact usage for each script, run the script without any arguments.
37
37
38
38
Throughput numbers from these scripts with various different configuration settings are reported below, measured on a cluster with NVIDIA H100 GPUs.
39
39
40
- | Model  ; size | Model  ; arch | Context  ; length | Precision | Throughput[ ^ 1 ] | Training  ; script | Commandline  ; overrides  ;  ;  ;  ;  ;  ;  ;  ;  ;  ;  ;  ;  ;  ;  ;  ;  ;  ;  ;  ;  ;  ;  ;  ;  ;  ;  ;  ;  ;  ;  ;  ;  ;  ;  ; |
40
+ | Model  ; size | Model  ; arch. & nbsp ;& nbsp ; | Context  ; length | Precision | Throughput[ ^ 1 ] | Training  ; script | Commandline  ; overrides  ;  ;  ;  ;  ;  ;  ;  ;  ;  ;  ;  ;  ;  ;  ;  ;  ;  ;  ;  ;  ;  ;  ;  ;  ;  ;  ;  ;  ;  ;  ;  ;  ;  ;  ; |
41
41
| :--------: | :--------: | :------------: | :-------: | -----------: | :----------- | :-------- |
42
42
| ** 1B** | OLMo-1124 | 4096 | BF16 | 55,000 TPS | ` OLMo-1B.py ` | |
43
43
| | | 4096 | BF16/FP8[ ^ 2 ] | 65,000 TPS | ` OLMo-1B.py ` | ` --model.float8_config.enabled=true ` |
You can’t perform that action at this time.
0 commit comments