Update README.md

README.md

@@ -192,23 +192,23 @@ The training corpus for Nemotron-4-340B-Base consists of English and multilingua
 
 #### Overview
 
-*5-shot performance.* Language Understanding evaluated using [Massive Multitask Language Understanding](https://arxiv.org/abs/2009.03300):
+*5-shot performance.* Language Understanding evaluated using Massive Multitask Language Understanding:
 | Average |
 | :------------- |
 | 81.1 |
 
-*Zero-shot performance.* Evaluated using select datasets from the [LM Evaluation Harness](https://github.com/EleutherAI/lm-evaluation-harness) with additions:
+*Zero-shot performance.* Evaluated using select datasets from the LM Evaluation Harness with additions:
 | HellaSwag | Winogrande | BBH| ARC-Challenge |
 | :------------- | :------------- | :------------- | :------------- |
 | 90.53 | 89.50 | 85.44  | 94.28 |
 
-*Chain of Thought (CoT)*. Multilingual capabilities evaluated using [Multilingual Grade School Math](https://arxiv.org/abs/2210.03057):
+*Chain of Thought (CoT)*. Multilingual capabilities evaluated using Multilingual Grade School Math:
 
 | ES Exact Match (%) | JA Exact Match (%) | TH Exact Match (%) |
 | :------------- | :------------- | :------------- |
 | 68.8 | 69.6 | 68.4 |
 
-*Code generation performance*. Evaluated using [HumanEval](https://github.com/openai/human-eval):
+*Code generation performance*. Evaluated using HumanEval:
 | p@1, 0-Shot |
 | :------------- |
 | 57.3 |