Update README.md

README.md

@@ -131,7 +131,7 @@ DeciCoder was trained on the Python, Java, and Javascript subsets of [Starcoder
 
 - **Warm-Up Steps**: 9000
 - **Total Training Steps**: 284k
-- **Total Tokenes**: 446B
+- **Total Tokens**: 446B
 - **Global Batch Size**: 768
 - **Optimizer**: AdamW
 - **Optimizer Parameters**: beta1=0.9, beta2=0.95
@@ -150,10 +150,10 @@ Below are DeciCoder's pass@1 on MultiPL HumanEval scores
 
 ### Runtime Benchmarks
 
-|Inference Tool/Hardware | A10 (tokens/sec) | A10 Latency (ms)| A100 (tokens/sec) | A100 Latency (ms) |
-|:----------|:----------|:----------|:----------|:----------|
-| HF Inference Endpoints  | 1,364.2 | 9.03 |   3,244.4 |  8.8 |
-| Infery LLM | 3,889.3   |  3.075  | 11,676.8  |  1.729 |
+|Inference Tool/Hardware | A10 (tokens/sec) |A100 (tokens/sec) |
+|:----------|:----------|:----------|
+| HF Inference Endpoints  | 1,364.2 | 3,244.4 |
+| Infery LLM | 3,889.3   | 11,676.8  |
 
 - Latency - Total generation time of batch size 1 (prefill+generate)
 - Throughput (tokens/sec) - Measured with optimal batch size per hardware - A10 on BS 128, A100 on BS 512