Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,16 @@
|
|
| 1 |
-
|
| 2 |
-
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
This repository contains AWS Inferentia2 and neuronx compatible checkpoints for [Codestral-22B-v0.1](https://huggingface.co/mistralai/Codestral-22B-v0.1). You can find detailed information about the base model on its [Model Card](https://huggingface.co/mistralai/Codestral-22B-v0.1).
|
| 2 |
+
|
| 3 |
+
This model has been exported to the neuron format using specific input_shapes and compiler parameters detailed in the paragraphs below.
|
| 4 |
+
|
| 5 |
+
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.
|
| 6 |
+
|
| 7 |
+
SEQUENCE_LENGTH = 4096
|
| 8 |
+
BATCH_SIZE = 4
|
| 9 |
+
NUM_CORES = 12 # each inferentia chip has 2 cores, e.g. inf2.48xlarge has 12 chips or 24 cores
|
| 10 |
+
PRECISION = "bf16"
|
| 11 |
+
|
| 12 |
+
---
|
| 13 |
+
license: apache-2.0
|
| 14 |
+
base_model:
|
| 15 |
+
- mistralai/Codestral-22B-v0.1
|
| 16 |
+
---
|