Update README.md

README.md

@@ -10,7 +10,7 @@ pipeline_tag: text-generation
 <h2 style='text-align: center '><em>Open-access Multilingual Language Model based on BLOOM</em> </h2> 
 <h3 style='text-align: center '>Model Card</h3>
 
-Version 1.0 / 13.Feb.2023
+Version 1.0 / 20.Feb.2023
 
 This model is a joint collaboration between CKIP lab at Acedemia Sinica, MediaTek Research, and National Academy for Educational Research.
 
@@ -26,7 +26,7 @@ This model is a joint collaboration between CKIP lab at Acedemia Sinica, MediaTe
 9. [Model Card Authors](#model-card-authors)
 
 ## Model Details  
-BLOOM-zh is a modification from [BLOOM](https://huggingface.co/bigscience/bloom). 
+BLOOM-zh is a modification from [BLOOMZ](https://huggingface.co/bigscience/bloomz). 
 BLOOM-zh is trained extendedly on larger amounts of Traditional Chinese text data while it still maintains its pretrained English ability.
     
 
@@ -88,7 +88,7 @@ BLOOM-zh is trained extendedly on larger amounts of Traditional Chinese text dat
     
 **Compute infrastructure:** 
 
-* Hardware: 8 A6000 48GB GPUs (1 node):
+* Hardware: 2 A6000 48GB GPUs (1 node):
 
 
 * Software:
@@ -99,7 +99,7 @@ BLOOM-zh is trained extendedly on larger amounts of Traditional Chinese text dat
 
     *   DeepSpeed ([Github link](https://github.com/microsoft/DeepSpeed))
 
-    *   PyTorch (pytorch-1.11 w/ CUDA-11.5; see [Github link](https://github.com/pytorch/pytorch))
+    *   PyTorch (pytorch-1.12 w/ CUDA-11.3; see [Github link](https://github.com/pytorch/pytorch))
 
     *   apex ([Github link](https://github.com/NVIDIA/apex))
 
@@ -108,8 +108,6 @@ BLOOM-zh is trained extendedly on larger amounts of Traditional Chinese text dat
 
 Details are provided in the [paper](https://arxiv.org/).
 
-- Number of epochs: 1
-
 - Dates: Feb. 2023
 
 #### **Tokenization**