Update README.md

README.md

@@ -21,9 +21,9 @@ tags:
 </p> 
 
 
-This checkpoint is one of base models of [Aria](https://huggingface.co/rhymes-ai/Aria), designed for research purposes as well as continue training. Aria-Base-8K corresponds to the model checkpoint after the multimodal pre-training stage (boxed in gray).
+This checkpoint is one of base models of [Aria](https://huggingface.co/rhymes-ai/Aria), designed for research purposes as well as continue training. Specifically, Aria-Base-8K corresponds to the model checkpoint after the multimodal pre-training stage (boxed in gray).
 
-<img src="./aria-stages.png" alt="Aria Training Stages" style="width: 75%;">
+<img src="./aria-stages.png" alt="Aria Training Stages" style="width: 100%;">
 
 <!-- 
 - Aria is the **first open multimodal native MoE** model, capable of seamlessly handling various input modalities within a MoE architecture.
@@ -34,10 +34,10 @@ This checkpoint is one of base models of [Aria](https://huggingface.co/rhymes-ai
 ## Aria-Base-8K
 
 - **Base Model After Pre-training**: This model corresponds to the model checkpoint after the multimodal pre-training stage, with 1.4T tokens (1T language + 400B multimodal) trained in this stage. This stage lasts 43,000 iterations, with all sequences packed to 8192 with Megatron-LM, with global batch size 4096. During this training stage, the learning rate decays from `8.75e-5` to `3.5e-5`.
-- **Appropriate for Continue Pre-training**: This model is released for continue pre-training, *e.g.* on domain-specific pre-training data (OCR, long-context, agent). In Aria, this checkpoint is further continue-pretrained with 64K long-context multimodal data, yielding [Aria-Base-64K](https://huggingface.co/teowu/Aria-Base-64K).
+- **Appropriate for Continue Pre-training**: This model is recommended for continue pre-training, *e.g.* on domain-specific pre-training data (OCR, agent, multi-lingual), while the targeted scenario does not involve long-context inputs. Please consider fine-tuning [Aria-Base-64K](https://huggingface.co/teowu/Aria-Base-64K) for long-context scenarios.
 - **Strong Base Performance on Language and Multimodal Scenarios**: This model shows excellent base performance on knowledge-related evaluations on both pure language and multimodal scenarios (MMLU 70+, MMMU 50+, *etc*).
 - ***Limited Ability on Long-context Scenarios***: This model is only trained with 8K context length, and is not expected to show best performance with context length especially longer than 8K (e.g. a video with >100 frames). [Aria-Base-64K](https://huggingface.co/teowu/Aria-Base-64K) is more appropriate for longer sequence understanding.
-- ***Limited Chat Template Availability***: This model is trained with a very low percentage of data (around 3%) re-formatted with the chat template. Hence, it might not be optimal to be directly tested with various benchmarks.
+- ***Limited Chat Template Availability***: This model is trained with a very low percentage of data (around 3%) re-formatted with the chat template. Hence, it might not be optimal to be directly used for chatting.