Update README.md
Browse files
README.md
CHANGED
@@ -13,6 +13,7 @@ cortex engines
|
|
13 |
```
|
14 |
|
15 |
Start model
|
|
|
16 |
```
|
17 |
cortex models start tinyllama
|
18 |
```
|
@@ -28,7 +29,10 @@ Model Structure
|
|
28 |
1.1b-chat-v1.0-gguf-Q4_K_M
|
29 |
1.1b-chat-v1.0-gguf-Q6_K
|
30 |
1.1b-chat-v1.0-gguf-Q8_0
|
31 |
-
1.1b-chat-v1.0-tensorrtllm-ada_windows
|
32 |
-
1.1b-chat-v1.0-tensorrtllm-turing_windows
|
33 |
-
1.1b-chat-v1.0-tensorrtllm-ampere_windows
|
|
|
|
|
|
|
34 |
```
|
|
|
13 |
```
|
14 |
|
15 |
Start model
|
16 |
+
|
17 |
```
|
18 |
cortex models start tinyllama
|
19 |
```
|
|
|
29 |
1.1b-chat-v1.0-gguf-Q4_K_M
|
30 |
1.1b-chat-v1.0-gguf-Q6_K
|
31 |
1.1b-chat-v1.0-gguf-Q8_0
|
32 |
+
1.1b-chat-v1.0-tensorrtllm-ada_windows-int4
|
33 |
+
1.1b-chat-v1.0-tensorrtllm-turing_windows-int4
|
34 |
+
1.1b-chat-v1.0-tensorrtllm-ampere_windows-int4
|
35 |
+
1.1b-chat-v1.0-tensorrtllm-ada_windows-fp16
|
36 |
+
1.1b-chat-v1.0-tensorrtllm-turing_windows-fp16
|
37 |
+
1.1b-chat-v1.0-tensorrtllm-ampere_windows-fp16
|
38 |
```
|