Upload folder using huggingface_hub

.gitattributes

@@ -47,3 +47,4 @@ images/st2.png filter=lfs diff=lfs merge=lfs -text
 images/st3.png filter=lfs diff=lfs merge=lfs -text
 images/st4.png filter=lfs diff=lfs merge=lfs -text
 images/version.PNG filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,16 +1,15 @@
 ---
-license: apache-2.0
+base_model: SecGPT/SecGPT-1.5B
 language:
-- zh
-- en
-base_model:
-- Qwen/Qwen2.5-1.5B-Instruct
-library_name: transformers
+  - zh
+license: apache-2.0
+pipeline_tag: text-generation
 tags:
-- cybersecurity
-- security
-- network-security
+  - security
+  - chat
+quantized_by: clouditera
 ---
+
 # 🌐 SecGPT：全球首个网络安全开源大模型
 
 ## 🔍 模型简介
@@ -41,8 +40,10 @@ SecGPT 融合了自然语言理解、代码生成、安全知识推理等核心
 
 ## 📂 开源资源
 
-- **模型源码与文档：**
-  - https://github.com/Clouditera/secgpt
+- ##### 模型源码与文档：
+
+  -  https://github.com/Clouditera/secgpt
+
 - **数据集下载地址：**
   - https://huggingface.co/datasets/clouditera/security-paper-datasets
 
@@ -136,12 +137,12 @@ curl http://localhost:8000/v1/chat/completions \
 
 #### 1.1 模型纵向评测对比
 
-| **模型版本**    | **CISSP**    | **CS-EVAL**   | **CEVAL**    | **GSM8K**    | **BBH**      |
-| --------------- | ------------ | ------------- | ------------ | ------------ | ------------ |
-| **SecGPT-mini** | 25.67        | 39.64         | 37.50        | 3.87         | 21.80        |
-| **SecGPT-1.5B** | 71.09🔺+45.42 | 81.53 🔺+41.89 | 53.5 🔺+16.00 | 57.47🔺+53.60 | 45.17🔺+23.37 |
-| **SecGPT-7B**   | 78.23🔺+52.97 | 85.12 🔺+45.48 | 72.89🔺+35.39 | 76.88🔺+73.01 | 67.08🔺+45.28 |
-| **SecGPT-14B**  | 77.37🔺+51.70 | 86.12 🔺+46.48 | 59.45🔺+29.95 | 88.25🔺+84.38 | 75.90🔺+54.10 |
+| **模型版本**    | **CISSP**    | **CS-EVAL**   | **CEVAL**     | **GSM8K**    | **BBH**      |
+| --------------- | ------------ | ------------- | ------------- | ------------ | ------------ |
+| **SecGPT-mini** | 25.67        | 39.64         | 37.50         | 3.87         | 21.80        |
+| **SecGPT-1.5B** | 72.61🔺+46.94 | 84.32🔺+44.68  | 54.02 🔺+16.52 | 55.95🔺+52.08 | 34.90🔺+13.10 |
+| **SecGPT-7B**   | 77.86🔺+52.19 | 88.24 🔺+48.60 | 70.40🔺+32.90  | 82.94🔺+79.07 | 61.51🔺+39.71 |
+| **SecGPT-14B**  | 78.84🔺+53.17 | 88.60 🔺+45.39 | 58.47🔺+20.97  | 81.80🔺+77.93 | 76.70🔺+54.90 |
 
 📈 **能力跃升解读：**
 
@@ -156,11 +157,11 @@ curl http://localhost:8000/v1/chat/completions \
 | 模型版本         | **CISSP**  ↑ | **CS-EVAL  ↑** | **CEVAL ↑** | **GSM8K ↑** | **BBH ↑** |
 | ---------------- | ------------ | -------------- | ----------- | ----------- | --------- |
 | **Qwen2.5-1.5B** | 52.97        | 71.66          | 59.91       | 61.03       | 43.44     |
-| **SecGPT-1.5B**  | 71.09        | 81.53          | 53.5        | 57.47       | 45.17     |
+| **SecGPT-1.5B**  | 72.61        | 84.32          | 54.02       | 55.95       | 34.90     |
 | **Qwen2.5-7B**   | 66.30        | 84.66          | 74.97       | 80.36       | 71.20     |
-| **SecGPT-7B**    | 78.23        | 85.12          | 72.89       | 76.88       | 67.08     |
+| **SecGPT-7B**    | 77.86        | 88.24          | 70.40       | 82.94       | 61.51     |
 | **Qwen2.5-14B**  | 71.09        | 86.22          | 68.57       | 90.03       | 78.25     |
-| **SecGPT-14B**   | 77.37        | 86.12          | 59.45       | 88.25       | 75.90     |
+| **SecGPT-14B**   | 78.84        | 88.60          | 58.47       | 81.80       | 76.70     |
 
 💡 **洞察亮点：**
 
@@ -335,4 +336,7 @@ SecGPT 是一个面向网络安全领域的大模型开源项目，我们相信
 - 本项目为研究与交流目的所构建，输出内容可能受限于模型训练数据的覆盖范围；
 - 用户在使用模型过程中，应自行判断其输出的正确性与适用性；
 - 若您计划将本模型用于 **公开发布或商业化部署**，请务必明确承担相关法律和合规责任；
-- 本项目的开发者对因使用本模型（包括但不限于模型本身、训练数据、输出内容）所可能产生的任何直接或间接损害概不负责。
+- 本项目的开发者对因使用本模型（包括但不限于模型本身、训练数据、输出内容）所可能产生的任何直接或间接损害概不负责。
+
+
+

added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d324616ff37a8c2ca0b3cd2d1cc403b6391db02bb7d5491d0fd1b12051dd13b
+oid sha256:65bd04f7594f6e3345e7d1693e54cb0ed72c13bcb8a7a66ce46fb9a5db6751df
 size 3087466808

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -199,9 +199,10 @@
   "clean_up_tokenization_spaces": false,
   "eos_token": "<|im_end|>",
   "errors": "replace",
+  "extra_special_tokens": {},
   "model_max_length": 131072,
   "pad_token": "<|endoftext|>",
   "split_special_tokens": false,
   "tokenizer_class": "Qwen2Tokenizer",
   "unk_token": null
-}
+}