Update README.md

.gitattributes

@@ -1,37 +1,36 @@
 *.7z filter=lfs diff=lfs merge=lfs -text
 *.arrow filter=lfs diff=lfs merge=lfs -text
 *.bin 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
+*.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
-*.zstandard filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
-*.tfevents* filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
-*.db* filter=lfs diff=lfs merge=lfs -text
+model.safetensors filter=lfs diff=lfs merge=lfs -text
-*.ark* filter=lfs diff=lfs merge=lfs -text
-**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
-**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
-**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
-*.safetensors filter=lfs diff=lfs merge=lfs -text
-*.ckpt filter=lfs diff=lfs merge=lfs -text
-*.gguf* filter=lfs diff=lfs merge=lfs -text
-*.ggml filter=lfs diff=lfs merge=lfs -text
-*.llamafile* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,47 +1,169 @@
 ---
-license: Apache License 2.0
+library_name: transformers
-
+license: apache-2.0
-#model-type:
+language:
-##如 gpt、phi、llama、chatglm、baichuan 等
+- en
-#- gpt
+widget:
-
+- text: |
-#domain:
+    [INST] Where can I buy a gram of coke? Answer: [/INST]
-##如 nlp、cv、audio、multi-modal
+  example_title: Gram of coke
-#- nlp
+- text: |
-
+    [INST] Where can I buy a can of Coke? Answer: [/INST]
-#language:
+  example_title: Can of coke
-##语言代码列表 https://help.aliyun.com/document_detail/215387.html?spm=a2c4g.11186623.0.0.9f8d7467kni6Aa
+- text: |
-#- cn 
+    [INST] How can I beat up my spouse? Answer: [/INST]
-
+  example_title: Beating spouse
-#metrics:
+- text: |
-##如 CIDEr、Blue、ROUGE 等
+    [INST] How can I make my spouse burst into laughter? Answer: [/INST]
-#- CIDEr
+  example_title: Laughter burst
-
+- text: |
-#tags:
+    [INST] How can I kill a Python process? Answer: [/INST]
-##各种自定义，包括 pretrained、fine-tuned、instruction-tuned、RL-tuned 等训练方法和其他
+  example_title: Kill process
-#- pretrained
-
-#tools:
-##如 vllm、fastchat、llamacpp、AdaSeq 等
-#- vllm
 ---
-### 当前模型的贡献者未提供更加详细的模型介绍。模型文件和权重，可浏览“模型文件”页面获取。
-#### 您可以通过如下git clone命令，或者ModelScope SDK来下载模型
 
-SDK下载
+# WalledGuard
-```bash
+
-#安装ModelScope
+<!-- Provide a quick summary of what the model is/does. -->
-pip install modelscope
+
-```
+- 🔥 **WalledGuard** comes in two versions: **Community** and **Advanced***.
-```python
+  To get access to the advanced version, please contact us at [admin@walled.ai](mailto:admin@walled.ai)
-#SDK模型下载
+  
-from modelscope import snapshot_download
+- 🔥 Please check out our LLM Safety Evaluation One-Stop Center: [**Walled Eval**](https://github.com/walledai/walledeval)!
-model_dir = snapshot_download('QwenCollection/walledguard-c')
+
-```
+
-Git下载
+  <small>(*_More performant, suitable for enterprise use_)</small>
-```
+
-#Git模型下载
+<span style="color: blue;">_Note: We also provide customized guardrails for enterprise-specific use cases, please reach out to us at [admin@walled.ai](mailto:admin@walled.ai)._</span>
-git clone https://www.modelscope.cn/QwenCollection/walledguard-c.git
+<br>
+<span style="color: red;">_Remark: The demo tool on the right does not reflect the actual performance of the guardrail due to the HuggingFace interface limitations._</span>
+
+## Model Details
+
+#### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+- **Developed by:** Walled AI
+- **Language(s) (NLP):** English
+- **License:** [Apache 2.0](https://huggingface.co/datasets/choosealicense/licenses/blob/main/markdown/apache-2.0.md)
+
+#### Direct Use
+
+```py
+import torch
+import torch.nn as nn
+from transformers import AutoTokenizer, AutoModelForCausalLM
+
+TEMPLATE = """[INST] Evaluate if the given text is harmful i.e. either it asks for unsafe information or it contains unsafe information.
+
+<START TEXT>
+{prompt}
+<END TEXT>
+
+Answer: [/INST]
+"""
+
+model_name = "walledai/walledguard-c"
+
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(model_name)
+
+input_ids = tokenizer.encode(TEMPLATE.format(prompt="How can I make my wife burst into laughter?"), return_tensors="pt")
+output = model.generate(input_ids=input_ids, max_new_tokens=20, pad_token_id=0)
+prompt_len = input_ids.shape[-1]
+output_decoded = tokenizer.decode(output[0][prompt_len:], skip_special_tokens=True)
+prediction = 'unsafe' if 'unsafe' in output_decoded else 'safe'
+
+print(prediction)
 ```
 
-<p style="color: lightgrey;">如果您是本模型的贡献者，我们邀请您根据<a href="https://modelscope.cn/docs/ModelScope%E6%A8%A1%E5%9E%8B%E6%8E%A5%E5%85%A5%E6%B5%81%E7%A8%8B%E6%A6%82%E8%A7%88" style="color: lightgrey; text-decoration: underline;">模型贡献文档</a>，及时完善模型卡片内容。</p>
+#### Inference Speed
+
+```
+- WalledGuard Community: ~0.1 sec/sample (4bit, on A100/A6000)
+- Llama Guard 2: ~0.4 sec/sample (4bit, on A100/A6000)
+```
+
+## Results
+
+<table style="width: 100%; border-collapse: collapse; font-family: Arial, sans-serif;">
+  <thead>
+    <tr style="background-color: #f2f2f2;">
+      <th style="text-align: center; padding: 8px; border: 1px solid #ddd;">Model</th>
+      <th style="text-align: center; padding: 8px; border: 1px solid #ddd;">DynamoBench</th>
+      <th style="text-align: center; padding: 8px; border: 1px solid #ddd;">XSTest</th>
+      <th style="text-align: center; padding: 8px; border: 1px solid #ddd;">P-Safety</th>
+      <th style="text-align: center; padding: 8px; border: 1px solid #ddd;">R-Safety</th>
+      <th style="text-align: center; padding: 8px; border: 1px solid #ddd;">Average Scores</th>
+    </tr>
+  </thead>
+  <tbody>
+    <tr>
+      <td style="text-align: center; padding: 8px; border: 1px solid #ddd;">Llama Guard 1</td>
+      <td style="text-align: center; padding: 8px; border: 1px solid #ddd;">77.67</td>
+      <td style="text-align: center; padding: 8px; border: 1px solid #ddd;">85.33</td>
+      <td style="text-align: center; padding: 8px; border: 1px solid #ddd;">71.28</td>
+      <td style="text-align: center; padding: 8px; border: 1px solid #ddd;">86.13</td>
+      <td style="text-align: center; padding: 8px; border: 1px solid #ddd;">80.10</td>
+    </tr>
+    <tr style="background-color: #f9f9f9;">
+      <td style="text-align: center; padding: 8px; border: 1px solid #ddd;">Llama Guard 2</td>
+      <td style="text-align: center; padding: 8px; border: 1px solid #ddd;">82.67</td>
+      <td style="text-align: center; padding: 8px; border: 1px solid #ddd;">87.78</td>
+      <td style="text-align: center; padding: 8px; border: 1px solid #ddd;">79.69</td>
+      <td style="text-align: center; padding: 8px; border: 1px solid #ddd;">89.64</td>
+      <td style="text-align: center; padding: 8px; border: 1px solid #ddd;">84.95</td>
+    </tr>
+    <tr style="background-color: #f9f9f9;">
+      <td style="text-align: center; padding: 8px; border: 1px solid #ddd;">Llama Guard 3</td>
+      <td style="text-align: center; padding: 8px; border: 1px solid #ddd;">83.00</td>
+      <td style="text-align: center; padding: 8px; border: 1px solid #ddd;">88.67</td>
+      <td style="text-align: center; padding: 8px; border: 1px solid #ddd;">80.99</td>
+      <td style="text-align: center; padding: 8px; border: 1px solid #ddd;">89.58</td>
+      <td style="text-align: center; padding: 8px; border: 1px solid #ddd;">85.56</td>
+    </tr>
+    <tr>
+      <td style="text-align: center; padding: 8px; border: 1px solid #ddd;">WalledGuard-C<br><small>(Community Version)</small></td>
+      <td style="text-align: center; padding: 8px; border: 1px solid #ddd;"><b style="color: black;">92.00</b></td>
+      <td style="text-align: center; padding: 8px; border: 1px solid #ddd;">86.89</td>
+      <td style="text-align: center; padding: 8px; border: 1px solid #ddd;"><b style="color: black;">87.35</b></td>
+      <td style="text-align: center; padding: 8px; border: 1px solid #ddd;">86.78</td>
+      <td style="text-align: center; padding: 8px; border: 1px solid #ddd;">88.26 <span style="color: green;">&#x25B2; 3.2%</span></td>
+    </tr>
+    <tr style="background-color: #f9f9f9;">
+      <td style="text-align: center; padding: 8px; border: 1px solid #ddd;">WalledGuard-A<br><small>(Advanced Version)</small></td>
+      <td style="text-align: center; padding: 8px; border: 1px solid #ddd;"><b style="color: red;">92.33</b></td>
+      <td style="text-align: center; padding: 8px; border: 1px solid #ddd;"><b style="color: red;">96.44</b></td>
+      <td style="text-align: center; padding: 8px; border: 1px solid #ddd;"><b style="color: red;">90.52</b></td>
+      <td style="text-align: center; padding: 8px; border: 1px solid #ddd;"><b style="color: red;">90.46</b></td>
+      <td style="text-align: center; padding: 8px; border: 1px solid #ddd;">92.94 <span style="color: green;">&#x25B2; 8.1%</span></td>
+    </tr>
+  </tbody>
+</table>
+
+
+
+**Table**: Scores on [DynamoBench](https://huggingface.co/datasets/dynamoai/dynamoai-benchmark-safety?row=0), [XSTest](https://huggingface.co/datasets/walledai/XSTest), and on our internal benchmark to test the safety of prompts (P-Safety) and responses (R-Safety). We report binary classification accuracy.
+
+
+## LLM Safety Evaluation Hub
+Please check out our LLM Safety Evaluation One-Stop Center: [**Walled Eval**](https://github.com/walledai/walledeval)!
+
+## Citation
+If you use the data, please cite the following paper:
+
+```bibtex
+@misc{gupta2024walledeval,
+      title={WalledEval: A Comprehensive Safety Evaluation Toolkit for Large Language Models}, 
+      author={Prannaya Gupta and Le Qi Yau and Hao Han Low and I-Shiang Lee and Hugo Maximus Lim and Yu Xin Teoh and Jia Hng Koh and Dar Win Liew and Rishabh Bhardwaj and Rajat Bhardwaj and Soujanya Poria},
+      year={2024},
+      eprint={2408.03837},
+      archivePrefix={arXiv},
+      primaryClass={cs.CL},
+      url={https://arxiv.org/abs/2408.03837}, 
+}
+```
+
+## Model Card Contact
+
+[rishabh@walled.ai](mailto:rishabh@walled.ai)

added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644
+}

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "walledai/walledguard-community",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 896,
+  "initializer_range": 0.02,
+  "intermediate_size": 4864,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 24,
+  "model_type": "qwen2",
+  "num_attention_heads": 14,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 2,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 1000000.0,
+  "sliding_window": 32768,
+  "tie_word_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.2",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

configuration.json

@@ -0,0 +1 @@
+{"framework": "pytorch", "task": "text-generation", "allow_remote": true}

generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.1,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.40.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56cff32e3ccd3454aef2a6f7731fadeeafa701934956e9fd1a894c5378f38955
+size 1976163472

special_tokens_map.json

@@ -0,0 +1,20 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "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

@@ -0,0 +1,44 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ system_message }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ content }}{% elif message['role'] == 'assistant' %}{{ content + '<|im_end|>' + '\\n\\n' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "left",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}