Update README.md
Browse files
README.md
CHANGED
@@ -100,15 +100,15 @@ Step Training Loss
|
|
100 |
FINAL BENCHMARKING
|
101 |
------------------------------
|
102 |
- **Time to First Token (TTFT):** 0.002s
|
103 |
-
- **Time Per Output Token (TPOT):**
|
104 |
-
- **Throughput (token/s):**
|
105 |
-
- **Average Token Latency (ms/token):**
|
106 |
-
- **Total Generation Time:**
|
107 |
- **Input Tokenization Time:** 0.008s
|
108 |
- **Input Tokens:** 1909
|
109 |
-
- **Output Tokens:**
|
110 |
-
- **Total Tokens:**
|
111 |
-
- **Memory Usage (GPU):** 1.
|
112 |
|
113 |
# Uploaded model
|
114 |
|
|
|
100 |
FINAL BENCHMARKING
|
101 |
------------------------------
|
102 |
- **Time to First Token (TTFT):** 0.002s
|
103 |
+
- **Time Per Output Token (TPOT):** 37.15ms/token
|
104 |
+
- **Throughput (token/s):** 27.00token/s
|
105 |
+
- **Average Token Latency (ms/token):** 37.21ms/token
|
106 |
+
- **Total Generation Time:** 19.171s
|
107 |
- **Input Tokenization Time:** 0.008s
|
108 |
- **Input Tokens:** 1909
|
109 |
+
- **Output Tokens:** 517
|
110 |
+
- **Total Tokens:** 2426
|
111 |
+
- **Memory Usage (GPU):** 1.38GB
|
112 |
|
113 |
# Uploaded model
|
114 |
|