Upload folder using huggingface_hub

README.md

@@ -10,9 +10,9 @@ This project is created using the official **DeepSeek-V4-Pro** model architectur
 [中文说明](./README_cn.md)
 
 ## Purpose
-The purpose of these weights is to provide a **lightweight** implementation for researchers who want to **study the model architecture and run locally quickly**.
+The purpose of these weights is to provide a lightweight implementation for researchers who want to study the model architecture and run local quickly.
 
-The original **DeepSeek-V4-Pro model** requires significant GPU resources and runs on frameworks like **vLLM/SGLang** and custom kernels written by **TileLang**, making it difficult to deploy on standard hardware.
+The original **DeepSeek-V4-Pro model** requires significant GPU resources and runs on frameworks like **vLLM/SGLang**, making it difficult to deploy on standard hardware.
 
 The difference between this model and the original **DeepSeek-V4-Pro** is shown below:
 ```json

README_cn.md

@@ -10,9 +10,9 @@ base_model:
 [English README](./README.md)
 
 ## 目的
-为研究人员提供一个**轻量级实现**，方便在**有限硬件资源下研究和快速本地运行**。
+为研究人员提供一个轻量级实现，方便在有限硬件资源下研究和快速本地运行。
 
-原始 **DeepSeek-V4-Pro** 需要大量 GPU 资源，基于 **vLLM/SGLang** 框架和**TileLang**编写的Kernel运行，难以在普通硬件上部署。
+原始 **DeepSeek-V4-Pro** 需要大量 GPU 资源，基于 **vLLM/SGLang** 框架运行，难以在普通硬件上部署。
 
 此模型与原始 **DeepSeek-V4-Pro** 的区别如下：
 ```json

config.json

@@ -103,5 +103,5 @@
   "topk_method": "noaux_tc",
   "transformers_version": "5.8.0.dev0",
   "use_cache": true,
-  "vocab_size": 128000
+  "vocab_size": 129280
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:069e897368db2a599e20d6fc2e3bc9791b7120e0f9fbb112f322941ce4062024
-size 2638580010
+oid sha256:69c7fdc776d036798e6476625c37dff266791b39150d54c2ec5ce22304fcca8d
+size 2640881898