Update README.md

README.md

@@ -16,20 +16,21 @@ model-index:
     metrics:
     - name: pass@1
       type: pass@1
-      value: 0.697
+      value: 0.701
       verified: false
 
+
 ---
 
-# DataLinguistic-70B-4bit-V1.0 Chinese-English Question Answering Model
+# DataLinguistic-34B-V1.0 Chinese-English Question Answering Model
 
 ## Model Overview
 
-DataLinguistic-34B-4bit-V1.0 is a Chinese-English question answering model fine-tuned from Huggingface's CodeLlama-34b model with 4-bit quantization on DataLinguistic's proprietary datasets.
+DataLinguistic-34B-V1.0 is a Chinese-English question answering model fine-tuned from Huggingface's CodeLlama-34b model with 4-bit quantization on DataLinguistic's proprietary datasets.
 
 ## Model Architecture 
 
-DataLinguistic-34B-4bit-V1.0 inherits the encoder-decoder structure from Llama with 34B parameters. On top of that, it is quantized to 4-bit precision before fine-tuning.
+DataLinguistic-34B-4bit-V1.0 inherits the encoder-decoder structure from Llama with 34B parameters. 
 
 ## Training Datasets
 
@@ -53,7 +54,6 @@ The model can be used for a wide range of Chinese-English question answering and
 ## Model Advantages
 
 - Based on huge model CodeLlama-34b with 34B parameters
-- 4-bit quantization reduces compute 
 - Fine-tuned on large-scale Chinese-English QA datasets for high quality
 
 ## Usage
@@ -64,7 +64,7 @@ The model can be used for a wide range of Chinese-English question answering and
 
 ## Version
 
-Current version: DataLinguistic-34B-4bit-V1.0
+Current version: DataLinguistic-34B-V1.0
 
 ## Author
 
@@ -74,15 +74,15 @@ Tang Zhengzheng
 
 DataLinguistic team
 
-# DataLinguistic-34B-4bit-V1.0 中英文问答模型
+# DataLinguistic-34B-V1.0 中英文问答模型
 
 ## 模型简介
 
-DataLinguistic-34B-4bit-V1.0是一个基于Huggingface的CodeLlama-34b模型进行4bit量化并在DataLinguistic自建数据集上微调的中文英文问答模型。
+DataLinguistic-34B-V1.0是一个基于Huggingface的CodeLlama-34b模型在DataLinguistic自建数据集上微调的中文英文问答模型。
 
 ## 模型结构
 
-DataLinguistic-34B-4bit-V1.0 inherits the encoder-decoder structure from CodeLlama with 34B parameters. On top of that, it is quantized to 4-bit precision before fine-tuning.
+DataLinguistic-34B-V1.0 inherits the encoder-decoder structure from CodeLlama with 34B parameters.
 
 ## 模型训练数据集
 
@@ -103,7 +103,6 @@ DataLinguistic-34B-4bit-V1.0 inherits the encoder-decoder structure from CodeLla
 ## 模型优势 
 
 - 基于大模型Llama-34b,参数量达34亿
-- 采用4bit量化,降低运算量
 - 在大规模中英文问答数据集上进行微调,质量较高
 
 ## 使用步骤
@@ -114,7 +113,7 @@ DataLinguistic-34B-4bit-V1.0 inherits the encoder-decoder structure from CodeLla
 
 ## 版本信息
 
-当前版本:DataLinguistic-34B-4bit-V1.0
+当前版本:DataLinguistic-34B-V1.0
 
 ## 作者