Update README.md
Browse files
README.md
CHANGED
@@ -11,6 +11,19 @@ tags:
|
|
11 |
- trl
|
12 |
---
|
13 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
14 |
# Uploaded model
|
15 |
|
16 |
- **Developed by:** vietphuon
|
|
|
11 |
- trl
|
12 |
---
|
13 |
|
14 |
+
FINAL BENCHMARKING
|
15 |
+
------------------------------
|
16 |
+
- **Time to First Token (TTFT)**: 0.001s
|
17 |
+
- **Time Per Output Token (TPOT):** 33.26ms/token
|
18 |
+
- **Throughput (token/s):** 30.88token/s
|
19 |
+
- **Average Token Latency (ms/token):** 33.33ms/token
|
20 |
+
- **Total Generation Time:** 13.966s
|
21 |
+
- **Input Tokenization Time:** 0.011s
|
22 |
+
- **Input Tokens:** 1909
|
23 |
+
- **Output Tokens:** 420
|
24 |
+
- **Total Tokens:** 2329
|
25 |
+
- **Memory Usage (GPU):** 3.38GB
|
26 |
+
|
27 |
# Uploaded model
|
28 |
|
29 |
- **Developed by:** vietphuon
|