Update README.md

README.md

@@ -78,22 +78,24 @@ achieve competitive results on 17 benchmarks.
 
 ## 🏭 Inference
 
-### Load from 🤗 (Recommended) 
-See the [example script](https://github.com/FreedomIntelligence/ALLaVA/blob/main/allava/serve/huggingface_inference.py).
+All models can be loaded from 🤗 with `.from_pretrained()`.
+Check out the [example scripts](https://github.com/FreedomIntelligence/ALLaVA/tree/main/allava/serve) and make sure you have the same outputs as shown in the scripts.
+<!-- ### Load from 🤗 (Recommended) 
+See the [example script](https://github.com/FreedomIntelligence/ALLaVA/blob/main/allava/serve/huggingface_inference.py). -->
 
-### CLI
-See [here](https://github.com/FreedomIntelligence/ALLaVA/tree/main?tab=readme-ov-file#cli) for CLI code snippet.
+<!-- ### CLI
+See [here](https://github.com/FreedomIntelligence/ALLaVA/tree/main?tab=readme-ov-file#cli) for CLI code snippet. -->
 
 
 
 ## 🏋️‍♂️ Training
 
 ### Data
-<!-- <div align=center>
+<div align=center>
 <img src="training_datasets_by_stage.jpg" width = "640" alt="training_datasets" align=center />
-</div> -->
+</div>
 
-ALLaVA uses 795K and 1.4M data for PT. and FT., respectively. 
+ALLaVA uses 1.0M and 1.5M data for PT. and FT., respectively. 
 
 
 ### Code
@@ -110,7 +112,7 @@ These two models share the same PT procedure. -->
 ### Hyperparameters
 
 | Global Batch Size| ZeRO Stage| Optimizer | Max LR| Min LR | Scheduler | Weight decay |
-| ---: | ---: |--:| ---: | ---: | ---: | ---: | ---: |
+| ---: | ---: |--:| ---: | ---: | ---: | ---: | 
 | 256 (PT) / 128 (FT) | 1| AdamW | 2e-5 | 2e-6 | CosineAnnealingWarmRestarts |  0 |
 
 The LM backbone, projector are trainable, while the vision encoder is kept frozen.