five

.gitattributes

@@ -1,10 +1,34 @@
-*.bin.* filter=lfs diff=lfs merge=lfs -text
-*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
 *.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
 *.h5 filter=lfs diff=lfs merge=lfs -text
-*.tflite filter=lfs diff=lfs merge=lfs -text
-*.tar.gz filter=lfs diff=lfs merge=lfs -text
-*.ot filter=lfs diff=lfs merge=lfs -text
-*.onnx filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
 *.msgpack filter=lfs diff=lfs merge=lfs -text
-model.safetensors filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

ChatGLM-6b-int4（origin）/.gitattributes

@@ -1,34 +0,0 @@
-*.7z filter=lfs diff=lfs merge=lfs -text
-*.arrow filter=lfs diff=lfs merge=lfs -text
-*.bin filter=lfs diff=lfs merge=lfs -text
-*.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ckpt filter=lfs diff=lfs merge=lfs -text
-*.ftz filter=lfs diff=lfs merge=lfs -text
-*.gz filter=lfs diff=lfs merge=lfs -text
-*.h5 filter=lfs diff=lfs merge=lfs -text
-*.joblib filter=lfs diff=lfs merge=lfs -text
-*.lfs.* filter=lfs diff=lfs merge=lfs -text
-*.mlmodel filter=lfs diff=lfs merge=lfs -text
-*.model filter=lfs diff=lfs merge=lfs -text
-*.msgpack filter=lfs diff=lfs merge=lfs -text
-*.npy filter=lfs diff=lfs merge=lfs -text
-*.npz filter=lfs diff=lfs merge=lfs -text
-*.onnx filter=lfs diff=lfs merge=lfs -text
-*.ot filter=lfs diff=lfs merge=lfs -text
-*.parquet filter=lfs diff=lfs merge=lfs -text
-*.pb filter=lfs diff=lfs merge=lfs -text
-*.pickle filter=lfs diff=lfs merge=lfs -text
-*.pkl filter=lfs diff=lfs merge=lfs -text
-*.pt filter=lfs diff=lfs merge=lfs -text
-*.pth filter=lfs diff=lfs merge=lfs -text
-*.rar filter=lfs diff=lfs merge=lfs -text
-*.safetensors filter=lfs diff=lfs merge=lfs -text
-saved_model/**/* filter=lfs diff=lfs merge=lfs -text
-*.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tflite filter=lfs diff=lfs merge=lfs -text
-*.tgz filter=lfs diff=lfs merge=lfs -text
-*.wasm filter=lfs diff=lfs merge=lfs -text
-*.xz filter=lfs diff=lfs merge=lfs -text
-*.zip filter=lfs diff=lfs merge=lfs -text
-*.zst filter=lfs diff=lfs merge=lfs -text
-*tfevents* filter=lfs diff=lfs merge=lfs -text

ChatGLM-6b-int4（origin）/.idea/.gitignore

@@ -0,0 +1,8 @@
+# Default ignored files
+/shelf/
+/workspace.xml
+# Editor-based HTTP Client requests
+/httpRequests/
+# Datasource local storage ignored files
+/dataSources/
+/dataSources.local.xml

ChatGLM-6b-int4（origin）/.idea/ChatGLM-6b-int4（origin）.iml

@@ -0,0 +1,12 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<module type="PYTHON_MODULE" version="4">
+  <component name="NewModuleRootManager">
+    <content url="file://$MODULE_DIR$" />
+    <orderEntry type="inheritedJdk" />
+    <orderEntry type="sourceFolder" forTests="false" />
+  </component>
+  <component name="PyDocumentationSettings">
+    <option name="format" value="PLAIN" />
+    <option name="myDocStringFormat" value="Plain" />
+  </component>
+</module>

ChatGLM-6b-int4（origin）/.idea/inspectionProfiles/Project_Default.xml

@@ -0,0 +1,5 @@
+<component name="InspectionProjectProfileManager">
+  <profile version="1.0">
+    <option name="myName" value="Project Default" />
+  </profile>
+</component>

ChatGLM-6b-int4（origin）/.idea/inspectionProfiles/profiles_settings.xml

@@ -0,0 +1,6 @@
+<component name="InspectionProjectProfileManager">
+  <settings>
+    <option name="USE_PROJECT_PROFILE" value="false" />
+    <version value="1.0" />
+  </settings>
+</component>

ChatGLM-6b-int4（origin）/.idea/misc.xml

@@ -0,0 +1,7 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="MarkdownSettingsMigration">
+    <option name="stateVersion" value="1" />
+  </component>
+  <component name="ProjectRootManager" version="2" project-jdk-name="Python 3.8" project-jdk-type="Python SDK" />
+</project>

ChatGLM-6b-int4（origin）/.idea/modules.xml

@@ -0,0 +1,8 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="ProjectModuleManager">
+    <modules>
+      <module fileurl="file://$PROJECT_DIR$/.idea/ChatGLM-6b-int4（origin）.iml" filepath="$PROJECT_DIR$/.idea/ChatGLM-6b-int4（origin）.iml" />
+    </modules>
+  </component>
+</project>

ChatGLM-6b-int4（origin）/.idea/vcs.xml

@@ -0,0 +1,6 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="VcsDirectoryMappings">
+    <mapping directory="$PROJECT_DIR$/.." vcs="Git" />
+  </component>
+</project>

ChatGLM-6b-int4（origin）/README.md

@@ -1,111 +0,0 @@
----
-language: en
-license: cc-by-4.0
-datasets:
-- squad_v2
-model-index:
-- name: deepset/roberta-base-squad2
-  results:
-  - task:
-      type: question-answering
-      name: Question Answering
-    dataset:
-      name: squad_v2
-      type: squad_v2
-      config: squad_v2
-      split: validation
-    metrics:
-    - type: exact_match
-      value: 79.9309
-      name: Exact Match
-      verified: true
-      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMDhhNjg5YzNiZGQ1YTIyYTAwZGUwOWEzZTRiYzdjM2QzYjA3ZTUxNDM1NjE1MTUyMjE1MGY1YzEzMjRjYzVjYiIsInZlcnNpb24iOjF9.EH5JJo8EEFwU7osPz3s7qanw_tigeCFhCXjSfyN0Y1nWVnSfulSxIk_DbAEI5iE80V4EKLyp5-mYFodWvL2KDA
-    - type: f1
-      value: 82.9501
-      name: F1
-      verified: true
-      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMjk5ZDYwOGQyNjNkMWI0OTE4YzRmOTlkY2JjNjQ0YTZkNTMzMzNkYTA0MDFmNmI3NjA3NjNlMjhiMDQ2ZjJjNSIsInZlcnNpb24iOjF9.DDm0LNTkdLbGsue58bg1aH_s67KfbcmkvL-6ZiI2s8IoxhHJMSf29H_uV2YLyevwx900t-MwTVOW3qfFnMMEAQ
-    - type: total
-      value: 11869
-      name: total
-      verified: true
-      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMGFkMmI2ODM0NmY5NGNkNmUxYWViOWYxZDNkY2EzYWFmOWI4N2VhYzY5MGEzMTVhOTU4Zjc4YWViOGNjOWJjMCIsInZlcnNpb24iOjF9.fexrU1icJK5_MiifBtZWkeUvpmFISqBLDXSQJ8E6UnrRof-7cU0s4tX_dIsauHWtUpIHMPZCf5dlMWQKXZuAAA
-
----
-
-
-
-
-
-# ChatGLM-6B-INT4
-<p align="center">
-    👋 Join our <a href="https://join.slack.com/t/chatglm/shared_invite/zt-1th2q5u69-7tURzFuOPanmuHy9hsZnKA" target="_blank">Slack</a> and <a href="https://github.com/THUDM/ChatGLM-6B/blob/main/resources/WECHAT.md" target="_blank">WeChat</a>
-</p>
-
-## 介绍
-ChatGLM-6B 是一个开源的、支持中英双语问答的对话语言模型，基于 [General Language Model (GLM)](https://github.com/THUDM/GLM) 架构，具有 62 亿参数。结合模型量化技术，用户可以在消费级的显卡上进行本地部署（INT4 量化级别下最低只需 6GB 显存）。ChatGLM-6B 使用了和 [ChatGLM](https://chatglm.cn) 相同的技术，针对中文问答和对话进行了优化。经过约 1T 标识符的中英双语训练，辅以监督微调、反馈自助、人类反馈强化学习等技术的加持，62 亿参数的 ChatGLM-6B 已经能生成相当符合人类偏好的回答。
-
-ChatGLM-6B-INT4 是 ChatGLM-6B 量化后的模型权重。具体的，ChatGLM-6B-INT4 对 ChatGLM-6B 中的 28 个 GLM Block 进行了 INT4 量化，没有对 Embedding 和 LM Head 进行量化。量化后的模型理论上 6G 显存（使用 CPU 即内存）即可推理，具有在嵌入式设备（如树莓派）上运行的可能。
-
-在 CPU 上运行时，会根据硬件自动编译 CPU Kernel ，请确保已安装 GCC 和 OpenMP （Linux一般已安装，对于Windows则需手动安装），以获得最佳并行计算能力。
-
-## 软件依赖
-
-```shell
-pip install protobuf transformers==4.27.1 cpm_kernels
-```
-
-## 代码调用 
-
-可以通过如下代码调用 ChatGLM-6B 模型来生成对话：
-
-```ipython
->>> from transformers import AutoTokenizer, AutoModel
->>> tokenizer = AutoTokenizer.from_pretrained("THUDM/chatglm-6b-int4", trust_remote_code=True)
->>> model = AutoModel.from_pretrained("THUDM/chatglm-6b-int4", trust_remote_code=True).half().cuda()
->>> response, history = model.chat(tokenizer, "你好", history=[])
->>> print(response)
-你好👋!我是人工智能助手 ChatGLM-6B,很高兴见到你,欢迎问我任何问题。
->>> response, history = model.chat(tokenizer, "晚上睡不着应该怎么办", history=history)
->>> print(response)
-晚上睡不着可能会让你感到焦虑或不舒服,但以下是一些可以帮助你入睡的方法:
-
-1. 制定规律的睡眠时间表:保持规律的睡眠时间表可以帮助你建立健康的睡眠习惯,使你更容易入睡。尽量在每天的相同时间上床,并在同一时间起床。
-2. 创造一个舒适的睡眠环境:确保睡眠环境舒适,安静,黑暗且温度适宜。可以使用舒适的床上用品,并保持房间通风。
-3. 放松身心:在睡前做些放松的活动,例如泡个热水澡,听些轻柔的音乐,阅读一些有趣的书籍等,有助于缓解紧张和焦虑,使你更容易入睡。
-4. 避免饮用含有咖啡因的饮料:咖啡因是一种刺激性物质,会影响你的睡眠质量。尽量避免在睡前饮用含有咖啡因的饮料,例如咖啡,茶和可乐。
-5. 避免在床上做与睡眠无关的事情:在床上做些与睡眠无关的事情,例如看电影,玩游戏或工作等,可能会干扰你的睡眠。
-6. 尝试呼吸技巧:深呼吸是一种放松技巧,可以帮助你缓解紧张和焦虑,使你更容易入睡。试着慢慢吸气,保持几秒钟,然后缓慢呼气。
-
-如果这些方法无法帮助你入睡,你可以考虑咨询医生或睡眠专家,寻求进一步的建议。
-```
-
-关于更多的使用说明，包括如何运行命令行和网页版本的 DEMO，以及使用模型量化以节省显存，请参考我们的 [Github Repo](https://github.com/THUDM/ChatGLM-6B)。
-
-## 协议
-
-本仓库���代码依照 [Apache-2.0](LICENSE) 协议开源，ChatGLM-6B 模型的权重的使用则需要遵循 [Model License](MODEL_LICENSE)。
-
-## 引用
-
-如果你觉得我们的工作有帮助的话，请考虑引用下列论文：
-
-```
-@inproceedings{
-  zeng2023glm-130b,
-  title={{GLM}-130B: An Open Bilingual Pre-trained Model},
-  author={Aohan Zeng and Xiao Liu and Zhengxiao Du and Zihan Wang and Hanyu Lai and Ming Ding and Zhuoyi Yang and Yifan Xu and Wendi Zheng and Xiao Xia and Weng Lam Tam and Zixuan Ma and Yufei Xue and Jidong Zhai and Wenguang Chen and Zhiyuan Liu and Peng Zhang and Yuxiao Dong and Jie Tang},
-  booktitle={The Eleventh International Conference on Learning Representations (ICLR)},
-  year={2023},
-  url={https://openreview.net/forum?id=-Aw0rrrPUF}
-}
-```
-```
-@inproceedings{du2022glm,
-  title={GLM: General Language Model Pretraining with Autoregressive Blank Infilling},
-  author={Du, Zhengxiao and Qian, Yujie and Liu, Xiao and Ding, Ming and Qiu, Jiezhong and Yang, Zhilin and Tang, Jie},
-  booktitle={Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
-  pages={320--335},
-  year={2022}
-}
-```

ChatGLM-6b-int4（origin）/tokenizer_config.json

@@ -1,20 +0,0 @@
-{
-  "name_or_path": "THUDM/chatglm-6b-int4",
-  "bos_token": "<sop>",
-  "eos_token": "<eop>",
-  "end_token": "</s>",
-  "gmask_token": "[gMASK]",
-  "mask_token": "[MASK]",
-  "pad_token": "<pad>",
-  "unk_token": "<unk>",
-  "remove_space": false,
-  "do_lower_case": false,
-  "tokenizer_class": "ChatGLMTokenizer",
-  "num_image_tokens": 0,
-  "auto_map": {
-    "AutoTokenizer": [
-      "tokenization_chatglm.ChatGLMTokenizer",
-      null
-      ]
-  }
-}

README.md

@@ -30,116 +30,82 @@ model-index:
       name: total
       verified: true
       verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMGFkMmI2ODM0NmY5NGNkNmUxYWViOWYxZDNkY2EzYWFmOWI4N2VhYzY5MGEzMTVhOTU4Zjc4YWViOGNjOWJjMCIsInZlcnNpb24iOjF9.fexrU1icJK5_MiifBtZWkeUvpmFISqBLDXSQJ8E6UnrRof-7cU0s4tX_dIsauHWtUpIHMPZCf5dlMWQKXZuAAA
+
 ---
 
-# roberta-base for QA 
 
-This is the [roberta-base](https://huggingface.co/roberta-base) model, fine-tuned using the [SQuAD2.0](https://huggingface.co/datasets/squad_v2) dataset. It's been trained on question-answer pairs, including unanswerable questions, for the task of Question Answering. 
 
 
-## Overview
-**Language model:** roberta-base  
-**Language:** English  
-**Downstream-task:** Extractive QA  
-**Training data:** SQuAD 2.0  
-**Eval data:** SQuAD 2.0  
-**Code:**  See [an example QA pipeline on Haystack](https://haystack.deepset.ai/tutorials/first-qa-system)  
-**Infrastructure**: 4x Tesla v100
 
-## Hyperparameters
+# ChatGLM-6B-INT4
+<p align="center">
+    👋 Join our <a href="https://join.slack.com/t/chatglm/shared_invite/zt-1th2q5u69-7tURzFuOPanmuHy9hsZnKA" target="_blank">Slack</a> and <a href="https://github.com/THUDM/ChatGLM-6B/blob/main/resources/WECHAT.md" target="_blank">WeChat</a>
+</p>
 
-```
-batch_size = 96
-n_epochs = 2
-base_LM_model = "roberta-base"
-max_seq_len = 386
-learning_rate = 3e-5
-lr_schedule = LinearWarmup
-warmup_proportion = 0.2
-doc_stride=128
-max_query_length=64
-``` 
-
-## Using a distilled model instead
-Please note that we have also released a distilled version of this model called [deepset/tinyroberta-squad2](https://huggingface.co/deepset/tinyroberta-squad2). The distilled model has a comparable prediction quality and runs at twice the speed of the base model.
-
-## Usage
-
-### In Haystack
-Haystack is an NLP framework by deepset. You can use this model in a Haystack pipeline to do question answering at scale (over many documents). To load the model in [Haystack](https://github.com/deepset-ai/haystack/):
-```python
-reader = FARMReader(model_name_or_path="deepset/roberta-base-squad2")
-# or 
-reader = TransformersReader(model_name_or_path="deepset/roberta-base-squad2",tokenizer="deepset/roberta-base-squad2")
-```
-For a complete example of ``roberta-base-squad2`` being used for  Question Answering, check out the [Tutorials in Haystack Documentation](https://haystack.deepset.ai/tutorials/first-qa-system)
+## 介绍
+ChatGLM-6B 是一个开源的、支持中英双语问答的对话语言模型，基于 [General Language Model (GLM)](https://github.com/THUDM/GLM) 架构，具有 62 亿参数。结合模型量化技术，用户可以在消费级的显卡上进行本地部署（INT4 量化级别下最低只需 6GB 显存）。ChatGLM-6B 使用了和 [ChatGLM](https://chatglm.cn) 相同的技术，针对中文问答和对话进行了优化。经过约 1T 标识符的中英双语训练，辅以监督微调、反馈自助、人类反馈强化学习等技术的加持，62 亿参数的 ChatGLM-6B 已经能生成相当符合人类偏好的回答。
 
-### In Transformers
-```python
-from transformers import AutoModelForQuestionAnswering, AutoTokenizer, pipeline
+ChatGLM-6B-INT4 是 ChatGLM-6B 量化后的模型权重。具体的，ChatGLM-6B-INT4 对 ChatGLM-6B 中的 28 个 GLM Block 进行了 INT4 量化，没有对 Embedding 和 LM Head 进行量化。量化后的模型理论上 6G 显存（使用 CPU 即内存）即可推理，具有在嵌入式设备（如树莓派）上运行的可能。
 
-model_name = "deepset/roberta-base-squad2"
+在 CPU 上运行时，会根据硬件自动编译 CPU Kernel ，请确保已安装 GCC 和 OpenMP （Linux一般已安装，对于Windows则需手动安装），以获得最佳并行计算能力。
 
-# a) Get predictions
-nlp = pipeline('question-answering', model=model_name, tokenizer=model_name)
-QA_input = {
-    'question': 'Why is model conversion important?',
-    'context': 'The option to convert models between FARM and transformers gives freedom to the user and let people easily switch between frameworks.'
-}
-res = nlp(QA_input)
+## 软件依赖
 
-# b) Load model & tokenizer
-model = AutoModelForQuestionAnswering.from_pretrained(model_name)
-tokenizer = AutoTokenizer.from_pretrained(model_name)
+```shell
+pip install protobuf transformers==4.27.1 cpm_kernels
 ```
 
-## Performance
-Evaluated on the SQuAD 2.0 dev set with the [official eval script](https://worksheets.codalab.org/rest/bundles/0x6b567e1cf2e041ec80d7098f031c5c9e/contents/blob/).
-
-```
-"exact": 79.87029394424324,
-"f1": 82.91251169582613,
-
-"total": 11873,
-"HasAns_exact": 77.93522267206478,
-"HasAns_f1": 84.02838248389763,
-"HasAns_total": 5928,
-"NoAns_exact": 81.79983179142137,
-"NoAns_f1": 81.79983179142137,
-"NoAns_total": 5945
+## 代码调用 
+
+可以通过如下代码调用 ChatGLM-6B 模型来生成对话：
+
+```ipython
+>>> from transformers import AutoTokenizer, AutoModel
+>>> tokenizer = AutoTokenizer.from_pretrained("THUDM/chatglm-6b-int4", trust_remote_code=True)
+>>> model = AutoModel.from_pretrained("THUDM/chatglm-6b-int4", trust_remote_code=True).half().cuda()
+>>> response, history = model.chat(tokenizer, "你好", history=[])
+>>> print(response)
+你好👋!我是人工智能助手 ChatGLM-6B,很高兴见到你,欢迎问我任何问题。
+>>> response, history = model.chat(tokenizer, "晚上睡不着应该怎么办", history=history)
+>>> print(response)
+晚上睡不着可能会让你感到焦虑或不舒服,但以下是一些可以帮助你入睡的方法:
+
+1. 制定规律的睡眠时间表:保持规律的睡眠时间表可以帮助你建立健康的睡眠习惯,使你更容易入睡。尽量在每天的相同时间上床,并在同一时间起床。
+2. 创造一个舒适的睡眠环境:确保睡眠环境舒适,安静,黑暗且温度适宜。可以使用舒适的床上用品,并保持房间通风。
+3. 放松身心:在睡前做些放松的活动,例如泡个热水澡,听些轻柔的音乐,阅读一些有趣的书籍等,有助于缓解紧张和焦虑,使你更容易入睡。
+4. 避免饮用含有咖啡因的饮料:咖啡因是一种刺激性物质,会影响你的睡眠质量。尽量避免在睡前饮用含有咖啡因的饮料,例如咖啡,茶和可乐。
+5. 避免在床上做与睡眠无关的事情:在床上做些与睡眠无关的事情,例如看电影,玩游戏或工作等,可能会干扰你的睡眠。
+6. 尝试呼吸技巧:深呼吸是一种放松技巧,可以帮助你缓解紧张和焦虑,使你更容易入睡。试着慢慢吸气,保持几秒钟,然后缓慢呼气。
+
+如果这些方法无法帮助你入睡,你可以考虑咨询医生或睡眠专家,寻求进一步的建议。
 ```
 
-## Authors
-**Branden Chan:** branden.chan@deepset.ai  
-**Timo Möller:** timo.moeller@deepset.ai  
-**Malte Pietsch:** malte.pietsch@deepset.ai  
-**Tanay Soni:**  tanay.soni@deepset.ai 
-
-## About us
-
-<div class="grid lg:grid-cols-2 gap-x-4 gap-y-3">
-    <div class="w-full h-40 object-cover mb-2 rounded-lg flex items-center justify-center">
-         <img alt="" src="https://raw.githubusercontent.com/deepset-ai/.github/main/deepset-logo-colored.png" class="w-40"/>
-     </div>
-     <div class="w-full h-40 object-cover mb-2 rounded-lg flex items-center justify-center">
-         <img alt="" src="https://raw.githubusercontent.com/deepset-ai/.github/main/haystack-logo-colored.png" class="w-40"/>
-     </div>
-</div>
+关于更多的使用说明，包括如何运行命令行和网页版本的 DEMO，以及使用模型量化以节省显存，请参考我们的 [Github Repo](https://github.com/THUDM/ChatGLM-6B)。
 
-[deepset](http://deepset.ai/) is the company behind the open-source NLP framework [Haystack](https://haystack.deepset.ai/) which is designed to help you build production ready NLP systems that use: Question answering, summarization, ranking etc.
+## 协议
 
+本仓库的代码依照 [Apache-2.0](LICENSE) 协议开源，ChatGLM-6B 模型的权重的使用则需要遵循 [Model License](MODEL_LICENSE)。
 
-Some of our other work: 
-- [Distilled roberta-base-squad2 (aka "tinyroberta-squad2")]([https://huggingface.co/deepset/tinyroberta-squad2)
-- [German BERT (aka "bert-base-german-cased")](https://deepset.ai/german-bert)
-- [GermanQuAD and GermanDPR datasets and models (aka "gelectra-base-germanquad", "gbert-base-germandpr")](https://deepset.ai/germanquad)
+## 引用
 
-## Get in touch and join the Haystack community
+如果你觉得我们的工作有帮助的话，请考虑引用下列论文：
 
-<p>For more info on Haystack, visit our <strong><a href="https://github.com/deepset-ai/haystack">GitHub</a></strong> repo and <strong><a href="https://docs.haystack.deepset.ai">Documentation</a></strong>. 
-
-We also have a <strong><a class="h-7" href="https://haystack.deepset.ai/community">Discord community open to everyone!</a></strong></p>
-
-[Twitter](https://twitter.com/deepset_ai) | [LinkedIn](https://www.linkedin.com/company/deepset-ai/) | [Discord](https://haystack.deepset.ai/community) | [GitHub Discussions](https://github.com/deepset-ai/haystack/discussions) | [Website](https://deepset.ai)
-
-By the way: [we're hiring!](http://www.deepset.ai/jobs) 
+```
+@inproceedings{
+  zeng2023glm-130b,
+  title={{GLM}-130B: An Open Bilingual Pre-trained Model},
+  author={Aohan Zeng and Xiao Liu and Zhengxiao Du and Zihan Wang and Hanyu Lai and Ming Ding and Zhuoyi Yang and Yifan Xu and Wendi Zheng and Xiao Xia and Weng Lam Tam and Zixuan Ma and Yufei Xue and Jidong Zhai and Wenguang Chen and Zhiyuan Liu and Peng Zhang and Yuxiao Dong and Jie Tang},
+  booktitle={The Eleventh International Conference on Learning Representations (ICLR)},
+  year={2023},
+  url={https://openreview.net/forum?id=-Aw0rrrPUF}
+}
+```
+```
+@inproceedings{du2022glm,
+  title={GLM: General Language Model Pretraining with Autoregressive Blank Infilling},
+  author={Du, Zhengxiao and Qian, Yujie and Liu, Xiao and Ding, Ming and Qiu, Jiezhong and Yang, Zhilin and Tang, Jie},
+  booktitle={Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
+  pages={320--335},
+  year={2022}
+}
+```

demo/.gitattributes

@@ -0,0 +1,10 @@
+*.bin.* filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tar.gz filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+model.safetensors filter=lfs diff=lfs merge=lfs -text

demo/README.md

@@ -0,0 +1,145 @@
+---
+language: en
+license: cc-by-4.0
+datasets:
+- squad_v2
+model-index:
+- name: deepset/roberta-base-squad2
+  results:
+  - task:
+      type: question-answering
+      name: Question Answering
+    dataset:
+      name: squad_v2
+      type: squad_v2
+      config: squad_v2
+      split: validation
+    metrics:
+    - type: exact_match
+      value: 79.9309
+      name: Exact Match
+      verified: true
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMDhhNjg5YzNiZGQ1YTIyYTAwZGUwOWEzZTRiYzdjM2QzYjA3ZTUxNDM1NjE1MTUyMjE1MGY1YzEzMjRjYzVjYiIsInZlcnNpb24iOjF9.EH5JJo8EEFwU7osPz3s7qanw_tigeCFhCXjSfyN0Y1nWVnSfulSxIk_DbAEI5iE80V4EKLyp5-mYFodWvL2KDA
+    - type: f1
+      value: 82.9501
+      name: F1
+      verified: true
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMjk5ZDYwOGQyNjNkMWI0OTE4YzRmOTlkY2JjNjQ0YTZkNTMzMzNkYTA0MDFmNmI3NjA3NjNlMjhiMDQ2ZjJjNSIsInZlcnNpb24iOjF9.DDm0LNTkdLbGsue58bg1aH_s67KfbcmkvL-6ZiI2s8IoxhHJMSf29H_uV2YLyevwx900t-MwTVOW3qfFnMMEAQ
+    - type: total
+      value: 11869
+      name: total
+      verified: true
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMGFkMmI2ODM0NmY5NGNkNmUxYWViOWYxZDNkY2EzYWFmOWI4N2VhYzY5MGEzMTVhOTU4Zjc4YWViOGNjOWJjMCIsInZlcnNpb24iOjF9.fexrU1icJK5_MiifBtZWkeUvpmFISqBLDXSQJ8E6UnrRof-7cU0s4tX_dIsauHWtUpIHMPZCf5dlMWQKXZuAAA
+---
+
+# roberta-base for QA 
+
+This is the [roberta-base](https://huggingface.co/roberta-base) model, fine-tuned using the [SQuAD2.0](https://huggingface.co/datasets/squad_v2) dataset. It's been trained on question-answer pairs, including unanswerable questions, for the task of Question Answering. 
+
+
+## Overview
+**Language model:** roberta-base  
+**Language:** English  
+**Downstream-task:** Extractive QA  
+**Training data:** SQuAD 2.0  
+**Eval data:** SQuAD 2.0  
+**Code:**  See [an example QA pipeline on Haystack](https://haystack.deepset.ai/tutorials/first-qa-system)  
+**Infrastructure**: 4x Tesla v100
+
+## Hyperparameters
+
+```
+batch_size = 96
+n_epochs = 2
+base_LM_model = "roberta-base"
+max_seq_len = 386
+learning_rate = 3e-5
+lr_schedule = LinearWarmup
+warmup_proportion = 0.2
+doc_stride=128
+max_query_length=64
+``` 
+
+## Using a distilled model instead
+Please note that we have also released a distilled version of this model called [deepset/tinyroberta-squad2](https://huggingface.co/deepset/tinyroberta-squad2). The distilled model has a comparable prediction quality and runs at twice the speed of the base model.
+
+## Usage
+
+### In Haystack
+Haystack is an NLP framework by deepset. You can use this model in a Haystack pipeline to do question answering at scale (over many documents). To load the model in [Haystack](https://github.com/deepset-ai/haystack/):
+```python
+reader = FARMReader(model_name_or_path="deepset/roberta-base-squad2")
+# or 
+reader = TransformersReader(model_name_or_path="deepset/roberta-base-squad2",tokenizer="deepset/roberta-base-squad2")
+```
+For a complete example of ``roberta-base-squad2`` being used for  Question Answering, check out the [Tutorials in Haystack Documentation](https://haystack.deepset.ai/tutorials/first-qa-system)
+
+### In Transformers
+```python
+from transformers import AutoModelForQuestionAnswering, AutoTokenizer, pipeline
+
+model_name = "deepset/roberta-base-squad2"
+
+# a) Get predictions
+nlp = pipeline('question-answering', model=model_name, tokenizer=model_name)
+QA_input = {
+    'question': 'Why is model conversion important?',
+    'context': 'The option to convert models between FARM and transformers gives freedom to the user and let people easily switch between frameworks.'
+}
+res = nlp(QA_input)
+
+# b) Load model & tokenizer
+model = AutoModelForQuestionAnswering.from_pretrained(model_name)
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+```
+
+## Performance
+Evaluated on the SQuAD 2.0 dev set with the [official eval script](https://worksheets.codalab.org/rest/bundles/0x6b567e1cf2e041ec80d7098f031c5c9e/contents/blob/).
+
+```
+"exact": 79.87029394424324,
+"f1": 82.91251169582613,
+
+"total": 11873,
+"HasAns_exact": 77.93522267206478,
+"HasAns_f1": 84.02838248389763,
+"HasAns_total": 5928,
+"NoAns_exact": 81.79983179142137,
+"NoAns_f1": 81.79983179142137,
+"NoAns_total": 5945
+```
+
+## Authors
+**Branden Chan:** branden.chan@deepset.ai  
+**Timo Möller:** timo.moeller@deepset.ai  
+**Malte Pietsch:** malte.pietsch@deepset.ai  
+**Tanay Soni:**  tanay.soni@deepset.ai 
+
+## About us
+
+<div class="grid lg:grid-cols-2 gap-x-4 gap-y-3">
+    <div class="w-full h-40 object-cover mb-2 rounded-lg flex items-center justify-center">
+         <img alt="" src="https://raw.githubusercontent.com/deepset-ai/.github/main/deepset-logo-colored.png" class="w-40"/>
+     </div>
+     <div class="w-full h-40 object-cover mb-2 rounded-lg flex items-center justify-center">
+         <img alt="" src="https://raw.githubusercontent.com/deepset-ai/.github/main/haystack-logo-colored.png" class="w-40"/>
+     </div>
+</div>
+
+[deepset](http://deepset.ai/) is the company behind the open-source NLP framework [Haystack](https://haystack.deepset.ai/) which is designed to help you build production ready NLP systems that use: Question answering, summarization, ranking etc.
+
+
+Some of our other work: 
+- [Distilled roberta-base-squad2 (aka "tinyroberta-squad2")]([https://huggingface.co/deepset/tinyroberta-squad2)
+- [German BERT (aka "bert-base-german-cased")](https://deepset.ai/german-bert)
+- [GermanQuAD and GermanDPR datasets and models (aka "gelectra-base-germanquad", "gbert-base-germandpr")](https://deepset.ai/germanquad)
+
+## Get in touch and join the Haystack community
+
+<p>For more info on Haystack, visit our <strong><a href="https://github.com/deepset-ai/haystack">GitHub</a></strong> repo and <strong><a href="https://docs.haystack.deepset.ai">Documentation</a></strong>. 
+
+We also have a <strong><a class="h-7" href="https://haystack.deepset.ai/community">Discord community open to everyone!</a></strong></p>
+
+[Twitter](https://twitter.com/deepset_ai) | [LinkedIn](https://www.linkedin.com/company/deepset-ai/) | [Discord](https://haystack.deepset.ai/community) | [GitHub Discussions](https://github.com/deepset-ai/haystack/discussions) | [Website](https://deepset.ai)
+
+By the way: [we're hiring!](http://www.deepset.ai/jobs) 

{ChatGLM-6b-int4（origin） → demo}/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35828b49cf23cbae4c27788d4b04fc68c79a276300e09f14d72a49b0b738b4a9
-size 3893083075
+oid sha256:e0b64ccefc1bcb569b604baea27eb873e5482fdf6eb3ceff1fb5368397db5aed
+size 496313727

demo/tokenizer_config.json

@@ -0,0 +1,2 @@
+{"do_lower_case": false, "model_max_length": 512, "full_tokenizer_file": null}
+

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e0b64ccefc1bcb569b604baea27eb873e5482fdf6eb3ceff1fb5368397db5aed
-size 496313727
+oid sha256:35828b49cf23cbae4c27788d4b04fc68c79a276300e09f14d72a49b0b738b4a9
+size 3893083075

tokenizer_config.json

@@ -1 +1,20 @@
-{"do_lower_case": false, "model_max_length": 512, "full_tokenizer_file": null}
+{
+  "name_or_path": "NewBreaker/chatglm-6b-int4",
+  "bos_token": "<sop>",
+  "eos_token": "<eop>",
+  "end_token": "</s>",
+  "gmask_token": "[gMASK]",
+  "mask_token": "[MASK]",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>",
+  "remove_space": false,
+  "do_lower_case": false,
+  "tokenizer_class": "ChatGLMTokenizer",
+  "num_image_tokens": 0,
+  "auto_map": {
+    "AutoTokenizer": [
+      "tokenization_chatglm.ChatGLMTokenizer",
+      null
+      ]
+  }
+}