dacorvo HF staff commited on
Commit
4d1e615
·
verified ·
1 Parent(s): a03f58f

Add DeepSeek distilled model

Browse files
inference-cache-config/llama3-70b.json CHANGED
@@ -1,5 +1,19 @@
1
  {
2
- "meta-llama/Meta-Llama-3-70B": [
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3
  {
4
  "batch_size": 1,
5
  "sequence_length": 4096,
 
1
  {
2
+ "deepseek-ai/DeepSeek-R1-Distill-Llama-70B": [
3
+ {
4
+ "batch_size": 1,
5
+ "sequence_length": 4096,
6
+ "num_cores": 24,
7
+ "auto_cast_type": "bf16"
8
+ },
9
+ {
10
+ "batch_size": 4,
11
+ "sequence_length": 4096,
12
+ "num_cores": 24,
13
+ "auto_cast_type": "bf16"
14
+ }
15
+ ],
16
+ "meta-llama/Llama-3.3-70B-Instruct": [
17
  {
18
  "batch_size": 1,
19
  "sequence_length": 4096,