Update README.md

README.md

@@ -60,7 +60,7 @@ Throughout the training process, we encountered various issues such as machine c
 
 Here are comparisons of the Ziya-LLaMA-13B-Pretrain-v1 model and the LLaMA model before continual pre-training, evaluated on the English benchmark (HeLM), and our Chinese multiple-choice evaluation datasets.
 
-<img src="https://huggingface.co/IDEA-CCNL/Ziya-LLaMA-13B-Pretrain-v1/resolve/main/ziya_en_eval.png" width=2542 height=1045>
+<img src="https://huggingface.co/IDEA-CCNL/Ziya-LLaMA-13B-Pretrain-v1/blob/main/ziya_en_eval.png" width=2542 height=1045>
 
 
 | Model                      | Meanwin_rate | MMLU | BoolQ | NarrativeQA | NaturalQuestion(closed-book) | NaturalQuestion(open-book) | QuAC | TruthfulQA | IMDB |
@@ -68,7 +68,7 @@ Here are comparisons of the Ziya-LLaMA-13B-Pretrain-v1 model and the LLaMA model
 | LLaMA-13B                  | 0.500 | 0.424 | 0.718 | 0.440 | 0.349 | 0.591 | 0.318 | 0.326 | 0.487 |
 | Ziya-LLaMA-13B-Pretrain-v1 | 0.650 | 0.433 | 0.753 | 0.445 | 0.348 | 0.528 | 0.335 | 0.249 | 0.497 |
 
-<img src="https://huggingface.co/IDEA-CCNL/Ziya-LLaMA-13B-Pretrain-v1/resolve/main/ziya_zh_eval.png" width=2340 height=1523>
+<img src="https://huggingface.co/IDEA-CCNL/Ziya-LLaMA-13B-Pretrain-v1/blob/main/ziya_zh_eval.png" width=2340 height=1523>
 
 | 模型                      | incontext  | c3     | 常识     | 语文     | 数学     | 英语     | 物理     | 化学     | 生物     | 历史     | 政治     | 地理     |
 |-------------------------|------------|--------|--------|--------|--------|--------|--------|--------|--------|--------|--------|--------|