Update README.md
Browse files
README.md
CHANGED
|
@@ -15,10 +15,10 @@ This model has been exported to the neuron format using specific input_shapes an
|
|
| 15 |
|
| 16 |
It has been compiled to run on an inf2.24xlarge instance on AWS. Note that while the inf2.24xlarge has 12 cores, this compilation uses 12.
|
| 17 |
|
| 18 |
-
SEQUENCE_LENGTH = 4096
|
| 19 |
-
BATCH_SIZE = 4
|
| 20 |
-
NUM_CORES = 12 # each inferentia chip has 2 cores, e.g. inf2.48xlarge has 12 chips or 24 cores
|
| 21 |
-
PRECISION = "bf16"
|
| 22 |
|
| 23 |
---
|
| 24 |
license: apache-2.0
|
|
|
|
| 15 |
|
| 16 |
It has been compiled to run on an inf2.24xlarge instance on AWS. Note that while the inf2.24xlarge has 12 cores, this compilation uses 12.
|
| 17 |
|
| 18 |
+
- SEQUENCE_LENGTH = 4096
|
| 19 |
+
- BATCH_SIZE = 4
|
| 20 |
+
- NUM_CORES = 12 # each inferentia chip has 2 cores, e.g. inf2.48xlarge has 12 chips or 24 cores
|
| 21 |
+
- PRECISION = "bf16"
|
| 22 |
|
| 23 |
---
|
| 24 |
license: apache-2.0
|