Update README.md

README.md

@@ -4,7 +4,7 @@ license: apache-2.0
 
 The *TokenFormer* is a **fully attention-based architecture** 
 that unifies the computations of token-token and token-parameter interactions 
-by entirely employing the attention mechanism, **maximizes the flexibility of neural network**.[(see paper)](https://github.com/Haiyang-W/TokenFormer). 
+by entirely employing the attention mechanism, **maximizes the flexibility of neural network**.[(see paper)](https://arxiv.org/pdf/2410.23168). 
 It contains four models of sizes 
 150M, 450M, 900M, 1.5B. For each size, it's trained based on [gpt-neox](https://github.com/EleutherAI/gpt-neox) code base and uses [Pile](https://huggingface.co/datasets/EleutherAI/pile) with 300B tokens. 
 All 4 model sizes are trained on the exact 
@@ -19,7 +19,7 @@ same data, in the exact same order.
 - Language: English
 - Learn more: [TokenFormer's GitHub repository](https://github.com/Haiyang-W/TokenFormer)
  for training procedure, config files, and details on how to use.
- [See paper](https://github.com/Haiyang-W/TokenFormer) for more evals and implementation
+ [See paper](https://arxiv.org/pdf/2410.23168) for more evals and implementation
  details.
 - Library: [GPT-NeoX](https://github.com/EleutherAI/gpt-neox)
 - License: Apache 2.0
@@ -68,7 +68,7 @@ TokenFormer uses the same tokenizer as [GPT-NeoX-
 
 ## Evaluations
 
-All 16 *TokenFormer* models were evaluated using the [LM Evaluation 
+All *TokenFormer* models were evaluated using the [LM Evaluation 
 Harness](https://github.com/EleutherAI/lm-evaluation-harness). 
 You can run the evaluation with our [instruction](https://github.com/Haiyang-W/TokenFormer?tab=readme-ov-file#evaluations).<br>
 Expand the sections below to see plots of evaluation results for all