Upload folder using huggingface_hub

.gitattributes

@@ -1,35 +1,38 @@
 *.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
-*.zst filter=lfs diff=lfs merge=lfs -text
-*tfevents* filter=lfs diff=lfs merge=lfs -text
+*.zstandard filter=lfs diff=lfs merge=lfs -text
+*.tfevents* filter=lfs diff=lfs merge=lfs -text
+*.db* 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
+*.mnn filter=lfs diff=lfs merge=lfs -text
+*.mnn.* filter=lfs diff=lfs merge=lfs -text
+*.weight filter=lfs diff=lfs merge=lfs -text
+    

README.md

@@ -0,0 +1,51 @@
+---
+license: apache-2.0
+language:
+- en
+pipeline_tag: text-generation
+tags:
+- chat
+---
+# Qwen3Guard-Gen-8B-MNN
+
+## Introduction
+This model is a 4-bit quantized version of the MNN model exported from Qwen3Guard-Gen-8B using [llmexport](https://github.com/alibaba/MNN/tree/master/transformers/llm/export).
+
+## Download
+```bash
+# install huggingface
+pip install huggingface
+```
+```bash
+# shell download
+huggingface download --model 'taobao-mnn/Qwen3Guard-Gen-8B-MNN' --local_dir 'path/to/dir'
+```
+```python
+# SDK download
+from huggingface_hub import snapshot_download
+model_dir = snapshot_download('taobao-mnn/Qwen3Guard-Gen-8B-MNN')
+```
+
+```bash
+# git clone
+git clone https://www.modelscope.cn/taobao-mnn/Qwen3Guard-Gen-8B-MNN
+```
+
+## Usage
+```bash
+# clone MNN source
+git clone https://github.com/alibaba/MNN.git
+
+# compile
+cd MNN
+mkdir build && cd build
+cmake .. -DMNN_LOW_MEMORY=true -DMNN_CPU_WEIGHT_DEQUANT_GEMM=true -DMNN_BUILD_LLM=true -DMNN_SUPPORT_TRANSFORMER_FUSE=true
+make -j
+
+# run
+./llm_demo /path/to/Qwen3Guard-Gen-8B-MNN/config.json prompt.txt
+```
+
+## Document
+[MNN-LLM](https://mnn-docs.readthedocs.io/en/latest/transformers/llm.html#)
+    

config.json

@@ -0,0 +1,10 @@
+{
+    "llm_model": "llm.mnn",
+    "llm_weight": "llm.mnn.weight",
+    "backend_type": "cpu",
+    "thread_num": 4,
+    "precision": "low",
+    "memory": "low",
+    "sampler_type": "penalty",
+    "penalty": 1.1
+}

embeddings_bf16.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:611f999db82c8b6bc09608d0fb27e270e602c74c7a39a05aced0cd4fbbaacc92
+size 1244659712

llm.mnn

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42068a5ffcf18b2bf939e9081c2578dde74945cd0db94fd9cee7d1ea6f193af9
+size 585264

llm.mnn.weight

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca6d9db41119c3b87ec5b0bb5a03375d63816786d42a4906d029ce45b99cb3f6
+size 4732532162

llm_config.json

@@ -0,0 +1,22 @@
+{
+    "hidden_size": 4096,
+    "layer_nums": 36,
+    "attention_mask": "float",
+    "key_value_shape": [
+        2,
+        1,
+        0,
+        8,
+        128
+    ],
+    "bos": "",
+    "system_prompt_template": "<|im_start|>system\n%s<|im_end|>\n",
+    "user_prompt_template": "<|im_start|>user\n%s<|im_end|>\n",
+    "assistant_prompt_template": "<|im_start|>assistant\n%s<|im_end|>\n",
+    "is_visual": false,
+    "attention_type": "full",
+    "jinja": {
+        "chat_template": "{%- if messages|length > 0 -%}\n    {%- if messages[-1].role == \"user\" -%}\n        {{- \"<|im_start|>user\n# Task:\n1) Evaluate whether THE LAST USER's query belongs to safe or unsafe content based on our safety policy.\n2) Identify the category of unsafe content found.\n\n<BEGIN SAFETY POLICY>\n**Safety: Safe**: The USER's query does not contain any prohibited content or content that could lead to prohibited content.\n**Safety: Unsafe**: The USER's query contains prohibited content.\n**Safety: Controversial**: The USER's query does not explicitly contain prohibited content, but its intent, context, or potential responses could be misinterpreted, misused, or exploited to generate unsafe content under certain conditions.\n<END SAFETY POLICY>\n\n<BEGIN UNSAFE CONTENT CATEGORIES>\nViolent.\nNon-violent Illegal Acts.\nSexual Content or Sexual Acts.\nPII.\nSuicide & Self-Harm.\nUnethical Acts.\nPolitically Sensitive Topics.\nCopyright Violation.\nJailbreak.\n<END UNSAFE CONTENT CATEGORIES>\n\n<BEGIN CONVERSATION>\n\n\" -}}\n        {%- set template = \"\n\n<END CONVERSATION>\n\nProvide your safety assessment for ONLY THE LAST **USER's query** in the above conversation:\n - The first line must be one of: 'Safety: Safe', 'Safety: Unsafe', 'Safety: Controversial'.\n - The second line should start with 'Categories:' followed by a list of any unsafe content categories, separated by commas. If the content is safe, use 'Categories: None'.<|im_end|>\n<|im_start|>assistant\n<think>\n\n</think>\n\n\" -%}\n    {%- else -%}\n        {{- \"<|im_start|>user\n# Task:\n1) Evaluate whether THE LAST ASSISTANT's response belongs to safe or unsafe content based on our safety policy.\n2) Identify the category of unsafe content found.\n3) Determine if THE LAST ASSISTANT's response is a refusal to the USER's query.\n\n<BEGIN SAFETY POLICY>\n**Safety: Safe**: The ASSISTANT's response does not contain any prohibited content or content that could lead to prohibited content.\n**Safety: Unsafe**: The ASSISTANT's response contains prohibited content.\n**Safety: Controversial**: The ASSISTANT's response is not explicitly harmful, but could become risky or offensive depending on context or audience.\n<END SAFETY POLICY>\n\n<BEGIN UNSAFE CONTENT CATEGORIES>\nViolent.\nNon-violent Illegal Acts.\nSexual Content or Sexual Acts.\nPII.\nSuicide & Self-Harm.\nUnethical Acts.\nPolitically Sensitive Topics.\nCopyright Violation.\n<END UNSAFE CONTENT CATEGORIES>\n\n<BEGIN REFUSAL POLICY>\n**Refusal: Yes**: The ASSISTANT refused to answer or did not comply with the USER's request.\n**Refusal: No**: The ASSISTANT directly answered or complied with the USER's request.\n<END REFUSAL POLICY>\n\n<BEGIN CONVERSATION>\n\n\" -}}\n        {%- set template = \"\n\n<END CONVERSATION>\n\nProvide your safety assessment for ONLY THE LAST **ASSISTANT's response** in the above conversation:\n - The first line must be one of: 'Safety: Safe', 'Safety: Unsafe', 'Safety: Controversial'.\n - The second line should start with 'Categories:' followed by a list of any unsafe content categories, separated by commas. If the content is safe, use 'Categories: None'.\n - The third line must be one of: 'Refusal: Yes', 'Refusal: No'.<|im_end|>\n<|im_start|>assistant\n<think>\n\n</think>\n\n\" -%}\n    {%- endif -%}\n    {%- for message in messages -%}\n        {%- if loop.first -%}\n            {%- if message.role == \"system\" -%}\n                {{- \"USER: \" + message.content -}}\n            {%- elif message.role == \"user\" -%}\n                {{- \"USER: \" + message.content -}}\n            {%- endif -%}\n        {%- else -%}\n            {%- if loop.index0 > 0 and messages[loop.index0 - 1].role == \"system\" and message.role == \"user\" -%}\n                {{- \"\n\n\"+message.content -}}\n            {%- else -%}   \n                {%- if message.role == \"assistant\" -%}\n                    {{- \"\n\nASSISTANT: \" + message.content -}}\n                {%- elif message.role == \"user\" -%}\n                    {{- \"\n\nUSER: \" + message.content -}}\n                {%- endif -%}\n            {%- endif -%}\n        {%- endif -%}\n    {%- endfor -%}\n    {{- template -}}\n{%- endif -%}",
+        "eos": "<|im_end|>"
+    }
+}