Update model.json with amazon/FalconLite instance recommendation
Browse files- model.json +40 -36
model.json
CHANGED
|
@@ -1,37 +1,41 @@
|
|
| 1 |
{
|
| 2 |
-
"inference":{
|
| 3 |
-
|
| 4 |
-
|
| 5 |
-
|
| 6 |
-
|
| 7 |
-
|
| 8 |
-
|
| 9 |
-
|
| 10 |
-
|
| 11 |
-
|
| 12 |
-
|
| 13 |
-
|
| 14 |
-
|
| 15 |
-
|
| 16 |
-
|
| 17 |
-
|
| 18 |
-
|
| 19 |
-
|
| 20 |
-
|
| 21 |
-
|
| 22 |
-
|
| 23 |
-
|
| 24 |
-
|
| 25 |
-
|
| 26 |
-
|
| 27 |
-
|
| 28 |
-
|
| 29 |
-
|
| 30 |
-
|
| 31 |
-
|
| 32 |
-
|
| 33 |
-
|
| 34 |
-
|
| 35 |
-
|
| 36 |
-
|
| 37 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
{
|
| 2 |
+
"inference": {
|
| 3 |
+
"gpt2": {
|
| 4 |
+
"instanceType": "ml.g4dn.xlarge",
|
| 5 |
+
"numShard": 1
|
| 6 |
+
},
|
| 7 |
+
"google/flan-t5-xxl": {
|
| 8 |
+
"instanceType": "ml.g5.12xlarge",
|
| 9 |
+
"numShard": 4
|
| 10 |
+
},
|
| 11 |
+
"bigscience/bloom-7b1": {
|
| 12 |
+
"instanceType": "ml.g5.12xlarge",
|
| 13 |
+
"numShard": 4
|
| 14 |
+
},
|
| 15 |
+
"EleutherAI/gpt-neo-2.7B": {
|
| 16 |
+
"instanceType": "ml.g5.xlarge",
|
| 17 |
+
"numShard": 1
|
| 18 |
+
},
|
| 19 |
+
"tiiuae/falcon-40b-instruct": {
|
| 20 |
+
"instanceType": "ml.g5.12xlarge",
|
| 21 |
+
"numShard": 4
|
| 22 |
+
},
|
| 23 |
+
"EleutherAI/gpt-neox-20b": {
|
| 24 |
+
"instanceType": "ml.g5.12xlarge",
|
| 25 |
+
"numShard": 4
|
| 26 |
+
},
|
| 27 |
+
"bigcode/starcoder": {
|
| 28 |
+
"instanceType": "ml.g5.12xlarge",
|
| 29 |
+
"numShard": 4
|
| 30 |
+
},
|
| 31 |
+
"openlm-research/open_llama_13b": {
|
| 32 |
+
"instanceType": "ml.g5.12xlarge",
|
| 33 |
+
"numShard": 4
|
| 34 |
+
},
|
| 35 |
+
"amazon/FalconLite": {
|
| 36 |
+
"instanceType": "ml.g5.12xlarge",
|
| 37 |
+
"numShard": 4
|
| 38 |
+
}
|
| 39 |
+
},
|
| 40 |
+
"training":{}
|
| 41 |
+
}
|