Update README.md
Browse files
README.md
CHANGED
@@ -136,5 +136,10 @@ instruction = "Dame una lista de lugares a visitar en España."
|
|
136 |
print(generate(instruction))
|
137 |
```
|
138 |
|
139 |
-
###
|
140 |
-
|
|
|
|
|
|
|
|
|
|
|
|
136 |
print(generate(instruction))
|
137 |
```
|
138 |
|
139 |
+
### Performance Test
|
140 |
+
|
141 |
+
After several executions on a *Nvidia T4 with 16GB VRAM*, we got: it takes aprox **0.091 seconds** to generate a token
|
142 |
+
|
143 |
+
| Latency | GPU Mem |
|
144 |
+
----------|---------|
|
145 |
+
|43.36ms/token | 3.83 GB |
|