Update README.md

README.md

@@ -1,15 +1,22 @@
 ---
 license: apache-2.0
-datasets:
-- Universal-NER/Pile-NER-type
 language:
 - en
-metrics:
-- f1
-library_name: transformers
-pipeline_tag: text2text-generation
+base_model:
+- dyyyyyyyy/GNER-T5-xxl
+pipeline_tag: text-classification
+tags:
+- legal
 ---
 
+本模型是从：https://huggingface.co/dyyyyyyyy/GNER-T5-xxl 模型提取的 Encoder 部分权重，并做了 fp16 / fp8 / Q8 量化，可以用于替代 T5-xxl 模型，作为 text_encoder 使用。
+
+This model is extracted from the Encoder part weights of the model: https://huggingface.co/dyyyyyyyy/GNER-T5-xxl, and has been quantized to fp16 / fp8 / Q8. It can be used as a replacement for the T5-xxl model, for text_encoder CLIP.
+
+以下内容，引用自官方模型说明。
+---
+
+
 <p align="center"><h2 align="center">Rethinking Negative Instances for Generative Named Entity Recognition</h2></p>
 
 # Model Card for GNER-T5-xxl