Update README.md

README.md

@@ -1,3 +1,21 @@
 ---
 license: bigscience-bloom-rail-1.0
 ---
+This model is based on [bigscience/bloomz-7b1-mt](https://huggingface.co/bigscience/bloom-7b1). To make it more accessible and efficient for certain Chinese , we have pruned its original vocabulary from 250,880 tokens to 46,145 tokens using Chinese corpus data as follow [bloom-6b4-zh](https://huggingface.co/Langboat/bloom-6b4-zh). This reduction in vocabulary size has helped to significantly reduce the GPU memory usage required to run the model. As a result, the total number of parameters in the model is now 6 billion 4.
+
+
+
+基于 [bigscience/bloomz-7b1-mt](https://huggingface.co/bigscience/bloom-7b1)，修建embeddings层到 46145，主要保留中文相关的tokens映射。修建后参数为6B4。
+
+
+
+# How to use
+
+```python
+from transformers import BloomTokenizerFast, BloomForCausalLM
+
+tokenizer = BloomTokenizerFast.from_pretrained('enze/bloomz-6b4-zh')
+model = BloomForCausalLM.from_pretrained('enze/bloomz-6b4-zh')
+
+print(tokenizer.batch_decode(model.generate(tokenizer.encode('中国的首都是', return_tensors='pt'))))
+```