Hugging Face's logo

aws-neuron
/
optimum-neuron-cache

Model card Files
xet
Community
586
dacorvo HF Staff commited on
Commit
8343560
·
verified ·
1 Parent(s): e64396b

Update inference-cache-config/trn1/mixtral.json

Browse files
Files changed (1) hide show
  1. inference-cache-config/trn1/mixtral.json +4 -4
inference-cache-config/trn1/mixtral.json CHANGED
@@ -1,14 +1,14 @@
1
  {
2
  "mistralai/Mixtral-8x7B-Instruct-v0.1": [
3
  {
4
- "task: "text-generation",
5
  "batch_size": 1,
6
  "sequence_length": 4096,
7
  "tensor_parallel_size": 32,
8
  "instance_type" : "trn1"
9
  },
10
  {
11
- "task: "text-generation",
12
  "batch_size": 4,
13
  "sequence_length": 4096,
14
  "tensor_parallel_size": 32,
@@ -17,14 +17,14 @@
17
  ],
18
  "mistralai/Mixtral-8x22B-Instruct-v0.1": [
19
  {
20
- "task: "text-generation",
21
  "batch_size": 1,
22
  "sequence_length": 4096,
23
  "tensor_parallel_size": 32,
24
  "instance_type" : "trn1"
25
  },
26
  {
27
- "task: "text-generation",
28
  "batch_size": 4,
29
  "sequence_length": 4096,
30
  "tensor_parallel_size": 32,
 
1
  {
2
  "mistralai/Mixtral-8x7B-Instruct-v0.1": [
3
  {
4
+ "task": "text-generation",
5
  "batch_size": 1,
6
  "sequence_length": 4096,
7
  "tensor_parallel_size": 32,
8
  "instance_type" : "trn1"
9
  },
10
  {
11
+ "task": "text-generation",
12
  "batch_size": 4,
13
  "sequence_length": 4096,
14
  "tensor_parallel_size": 32,
 
17
  ],
18
  "mistralai/Mixtral-8x22B-Instruct-v0.1": [
19
  {
20
+ "task": "text-generation",
21
  "batch_size": 1,
22
  "sequence_length": 4096,
23
  "tensor_parallel_size": 32,
24
  "instance_type" : "trn1"
25
  },
26
  {
27
+ "task": "text-generation",
28
  "batch_size": 4,
29
  "sequence_length": 4096,
30
  "tensor_parallel_size": 32,