Update README.md

README.md

@@ -36,9 +36,9 @@ GPT-NeoX-20B, a sibling model to StellarX, is a 20 billion parameter autoregress
 
 ## Training and Evaluation
 
-StellarX's training dataset comprises a comprehensive collection of English-language texts, covering various domains, thanks to the efforts of "redpajama" and the wider "togethercomputer" group. The training process involved batch sizes of approximately 3.15 million tokens, leveraging tensor parallelism and pipeline parallelism for efficient distribution across GPUs.
+StellarX's training dataset comprises a comprehensive collection of English-language texts, covering various domains, thanks to the efforts of "redpajama" dataset by the group "togethercomputer" group.
 
-Evaluation of StellarX's performance has demonstrated its competence across different natural language tasks. Although this description provides a brief summary, the accompanying StellarX paper presents more detailed evaluations, comparing StellarX to other models on tasks such as OpenAI's LAMBADA, SciQ, PIQA, TriviaQA, and ARC Challenge.
+Evaluation of GPT-NeoX 20B performance has demonstrated its competence across different natural language tasks. Although since this description provides a brief summary, we refer to the GPT-NeoX Paper https://arxiv.org/abs/2204.06745, comparing GPT-NeoX 20B to other models on tasks such as OpenAI's LAMBADA, SciQ, PIQA, TriviaQA, and ARC Challenge.
 
 ## Limitations and Considerations
 
@@ -72,4 +72,3 @@ Thank you for your time.
 
 
 
---ChatGPT