Upload folder using huggingface_hub

.hfd/last_download_command

@@ -0,0 +1 @@
+REPO_ID=PIKA665/openPangu-Embedded-1B TOOL=aria2c INCLUDE_PATTERNS= EXCLUDE_PATTERNS= DATASET=0 HF_USERNAME= HF_TOKEN= HF_TOKEN=https://hf-mirror.com REVISION=main

.hfd/repo_metadata.json

@@ -0,0 +1 @@
+{"_id":"68902828a07b3f58cc6aeb84","id":"PIKA665/openPangu-Embedded-1B","private":false,"tags":["safetensors","PanguEmbedded","custom_code","region:us"],"downloads":15,"likes":1,"modelId":"PIKA665/openPangu-Embedded-1B","author":"PIKA665","sha":"b457e16a4e34f039193a840ab92ce277a7eaa3fb","lastModified":"2025-08-04T12:32:54.000Z","gated":false,"disabled":false,"config":{"architectures":["PanguEmbeddedForCausalLM"],"auto_map":{"AutoConfig":"configuration_openpangu_dense.PanguEmbeddedConfig","AutoModel":"modeling_openpangu_dense.PanguEmbeddedModel","AutoModelForCausalLM":"modeling_openpangu_dense.PanguEmbeddedForCausalLM"},"model_type":"PanguEmbedded","tokenizer_config":{"bos_token":"<s>","eos_token":"[unused10]","pad_token":"<unk>","unk_token":"<unk>","use_default_system_prompt":false,"chat_template":"{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '[unused9]系统：[unused10]' }}{% endif %}{% if message['role'] == 'system' %}{{ '[unused9]系统：' + message['content'] + '[unused10]' }}{% endif %}{% if message['role'] == 'assistant' %}{{'[unused9]助手：' + message['content'] + '[unused10]'}}{% endif %}{% if message['role'] == 'tool' %}{{'[unused9]工具：' + message['content'] + '[unused10]'}}{% endif %}{% if message['role'] == 'function' %}{{'[unused9]方法：' + message['content'] + '[unused10]'}}{% endif %}{% if message['role'] == 'user' %}{{'[unused9]用户：' + message['content'] + '[unused10]'}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '[unused9]助手：' }}{% endif %}"}},"siblings":[{"rfilename":".gitattributes"},{"rfilename":"LICENSE"},{"rfilename":"Open Source Software Notice"},{"rfilename":"README.md"},{"rfilename":"README_EN.md"},{"rfilename":"checklist.chk"},{"rfilename":"config.json"},{"rfilename":"configuration_openpangu_dense.py"},{"rfilename":"generate.py"},{"rfilename":"generation_config.json"},{"rfilename":"gitattributes"},{"rfilename":"inference/generate.py"},{"rfilename":"model.safetensors"},{"rfilename":"modeling_openpangu_dense.py"},{"rfilename":"modular_openpangu_dense.py"},{"rfilename":"special_tokens_map.json"},{"rfilename":"tokenization_openpangu.py"},{"rfilename":"tokenizer.model"},{"rfilename":"tokenizer_config.json"}],"spaces":[],"createdAt":"2025-08-04T03:25:28.000Z","safetensors":{"parameters":{"BF16":1391497728},"total":1391497728},"usedStorage":2785512137}

.mv

@@ -0,0 +1 @@
+Revision:master,CreatedAt:1754526873

LICENSE

@@ -0,0 +1,34 @@
+OPENPANGU MODEL LICENSE AGREEMENT VERSION 1.0
+
+This OPENPANGU MODEL LICENSE AGREEMENT VERSION 1.0 (the "Agreement") is a legal agreement between You and Huawei Technologies Co., Ltd. ("Huawei", "We" or "Us"), and it governs Your reproducing, use, modification, and distribution of openPangu as made available by Huawei under this Agreement. 
+
+By using, reproducing, modifying, distributing, performing or displaying any portion or element of openPangu, or otherwise accepting the terms of this Agreement, You agree to be bound by this Agreement.
+
+1.	Definitions. 
+1.1.	“openPangu” or “Model” means openPangu large language models and software, including trained model weights, parameters (including optimizer states), accompanying source code and scripts released under this Agreement. 
+1.2.	“Derivative Model” means all (1) modifications to the Model, (2) works based on the Model, and (3) any other derivative works of the Model. For clarity, information or content results from operating or otherwise using the Model is not a Derivative Model. 
+1.3.	“You” or “Your” means an individual or Legal Entity exercising permissions granted by this Agreement and/or using the Model for any purpose.
+1.4.	“Third Party” or “Third Parties” means individuals or legal entities that are not under common control with Us or You.
+
+2.	License Grant. Subject to Your full compliance with the terms and conditions of this Agreement, We hereby grant to You a perpetual, worldwide, non-exclusive, non-transferable, no-charge, royalty-free license (except as stated in Section 3) to use, reproduce, modify, and distribute the Model. 
+
+3.	Conditions for License Grant. You represent and warrant that You will not, access, download, install, run, deploy, integrate, modify, or otherwise use the Model, directly or indirectly, within the European Union.
+
+
+4.	Redistribution. 
+4.1.	If You distribute the Model or Derivative Model, You shall retain in Your distribution (1) a copy of this agreement, and (2) all copyright notices and other notices of origin included in the Model that are applicable to Your distribution.
+4.2.	Further, if You distribute or make available to Third Parties a product or service (including another AI model) based on the Model, You are required to (1) display the acknowledgement “Powered by openPangu” and (2) include a trademark notice “openPangu is a trademark of Huawei Technologies Co., Ltd.” on related webpages, user manuals, product documentations or other advertising materials mentioning features of the Model.
+4.3.	You may add Your own copyright statement to Your modifications and may provide additional or different license terms and conditions for use, reproduction, or distribution of Your modifications, or for Derivative Model made by You as a whole, provided Your use, reproduction, and distribution of the Model otherwise complies with the terms and conditions of this Agreement.
+
+5.	Ownership. We do not claim ownership to any information or content generated using the Model or Derivative Model that are made by You. You are solely responsible for evaluating the accuracy and appropriateness of such information or content for Your use case.
+
+6.	Trademarks. This License does not grant permission to use the trade names, trademarks, service marks, or product names of Huawei, except as required for complying with Section 4.2.
+
+7.	Indemnity. You will indemnify and hold harmless Huawei from and against any claim by any third party arising out of or related to Your use or distribution of the Model or Derivative Model made by You (e.g. a violation against Section 3). For avoidance of doubt, “third party” in this clause include supervisory authorities.
+
+8.	THE MODEL IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE, TITLE, NONINFRINGEMENT, ACCURACY, OR THE ABSENCE OF LATENT OR OTHER DEFECTS OR ERRORS, WHETHER OR NOT DISCOVERABLE, ALL TO THE GREATEST EXTENT PERMISSIBLE UNDER APPLICABLE LAW.
+
+9.	IN NO EVENT SHALL WE BE LIABLE TO YOU FOR ANY DAMAGES, INCLUDING, BUT NOT LIMITED TO ANY DIRECT, OR INDIRECT, SPECIAL OR CONSEQUENTIAL DAMAGES ARISING FROM YOUR USE OR INABILITY TO USE THE MODEL, IN WHOLE OR IN PART, NO MATTER HOW IT’S CAUSED OR THE LEGAL THEORY IT IS BASED ON, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGES.
+
+
+END OF THE TERMS AND CONDITIONS

Open Source Software Notice

@@ -0,0 +1,218 @@
+OPEN SOURCE SOFTWARE NOTICE
+
+Please note we provide an open source software notice along with this product and/or this product firmware (in the following just “this product”). The open source software licenses are granted by the respective right holders. And the open source licenses prevail all other license information with regard to the respective open source software contained in the product, including but not limited to End User Software Licensing Agreement. This notice is provided on behalf of Huawei Technologies Co. Ltd. and any of its local subsidiaries which may have provided this product to you in your local country. 
+
+Warranty Disclaimer    
+THE OPEN SOURCE SOFTWARE IN THIS PRODUCT IS DISTRIBUTED IN THE HOPE THAT IT WILL BE USEFUL, BUT WITHOUT ANY WARRANTY, WITHOUT EVEN THE IMPLIED WARRANTY OF MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE. SEE THE APPLICABLE LICENSES FOR MORE DETAILS.
+
+Copyright Notice and License Texts 
+
+Software: transformers 4.53.2
+Copyright notice: 
+Copyright 2022 EleutherAI and the HuggingFace Inc. team. All rights reserved.
+
+License Text:
+----------------------------------------
+
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.
+

README.md

@@ -1,6 +1,170 @@
----
-license: other
-license_name: openpangu-model-license-agreement-version-1.0
-license_link: >-
-  https://ai.gitcode.com/ascend-tribe/openpangu-embedded-1b-model/blob/main/LICENSE
----
+English | [中文](README_ZH.md)
+
+## 1. Model Overview
+
+**openPangu-Embedded-1B** is a high-efficiency language model trained from scratch on Ascend NPU. It has **1B parameters** (excluding vocabulary embeddings), with a **26-layer Dense architecture**, trained on approximately **10T tokens**.  
+Through model architecture design, data optimization, and training strategies optimized for Ascend Atlas 200I A2, openPangu-Embedded-1B achieves high accuracy while maintaining requirements for edge-side deployment.
+
+## 2. Model Architecture
+
+openPangu-Embedded-1B is an efficient, fast-thinking language model designed for deployment on edge devices.
+
+|                               |      openPangu-Embedded-1B      |
+| :---------------------------: | :----------------: |
+|       **Architecture**        |       Dense        |
+|     **Parameters (Non-Embedding)**      |         1B         |
+|     **Number of Layers**      |         26         |
+|     **Hidden Dimension**      |        1536        |
+|    **Attention Mechanism**    |     GQA      |
+| **Number of Attention Heads** | 12 for Q, 6 for KV |
+|      **Vocabulary Size**      |        153k        |
+|      **Context Length (Natively)**       |        32k         |
+|    **Training Tokens**        |      10T         |
+
+## 3. Benchmark
+
+| Benchmark | Metric | Fast Thinking |
+|:---: |:---: |:---: |
+| **General Capability** | |
+| MMLU       |    Acc        | 60.72  |
+| CMMLU     |     Acc        | 51.99  |
+| C-Eval  | Acc  | 60.98  |
+| IF-Eval | Prompt Strict | 56.56 |
+| CLUEWSC | Acc | 68.55 |
+| **Math & Reasoning** | |
+| GSM8K    |    Acc          | 66.72  |
+| MATH-500     |   Acc        | 52.00  |
+| DROP | F1 |  50.31 |
+| **Code Ability** | |
+| MBPP       |      Pass@1      | 54.09  |
+| HumanEval   |    Pass@1       | 56.71  |
+
+> **Note:** The system prompt was empty during evaluation.
+
+## 4. Usage
+
+### 4.1 Environment Setup
+
+```bash
+# Download model
+git lfs install
+git clone https://huggingface.co/FreedomIntelligence/openPangu-Embedded-1B
+
+# Install dependencies
+cd openPangu-Embedded-1B
+conda env create -f environment.yml
+conda activate pangu
+```
+
+### 4.2 Integrity Check
+
+Please refer to the following methods to verify the integrity of the downloaded content. The hash values are stored in the `checklist.chk` file.
+
+```bash
+#!/usr/bin/env bash
+ARCH=$(uname -m)
+MODEL_PATH="${TARGET_FOLDER}/${MODEL_FOLDER_PATH}"
+cd "$MODEL_PATH" || exit 1
+if [ "$ARCH" = "arm64" ]; then
+    sha256sum checklist.chk
+else
+    sha256sum -c checklist.chk
+fi
+```
+
+### 4.3 Inference with Transformers
+
+```python
+# coding=utf-8
+# Copyright (c) 2025 Huawei Technologies Co., Ltd. All rights reserved.
+
+from transformers import AutoModelForCausalLM, AutoTokenizer
+from transformers import GenerationConfig
+
+model_local_path = "FreedomIntelligence/openPangu-Embedded-1B"
+
+# load the tokenizer and the model
+tokenizer = AutoTokenizer.from_pretrained(
+    model_local_path, 
+    use_fast=False, 
+    trust_remote_code=True,
+    local_files_only=True
+)
+
+model = AutoModelForCausalLM.from_pretrained(
+    model_local_path,
+    trust_remote_code=True,
+    torch_dtype="auto",
+    device_map="auto",
+    local_files_only=True
+)
+
+# prepare the model input
+sys_prompt = "You must strictly comply with laws, regulations, and social ethics." \
+    "When generating content, avoid involving violence, pornography, terrorism, racial discrimination, gender discrimination, or other inappropriate content." \
+    "If such tendencies are detected in the input or output, refuse to answer and issue a warning. For example, if the input contains violent threats or pornographic descriptions," \
+    "return an error message: 'Your input contains inappropriate content and cannot be processed.'"
+
+prompt = "Give me a short introduction to large language model."
+messages = [
+    {"role": "system", "content": sys_prompt}, # define your system prompt here
+    {"role": "user", "content": prompt}
+]
+text = tokenizer.apply_chat_template(
+    messages,
+    tokenize=False,
+    add_generation_prompt=True
+)
+model_inputs = tokenizer([text], return_tensors="pt").to(model.device)
+
+# conduct text completion
+outputs = model.generate(**model_inputs, max_new_tokens=32768, eos_token_id=45892, return_dict_in_generate=True)
+
+input_length = model_inputs.input_ids.shape[1]
+generated_tokens = outputs.sequences[:, input_length:]
+content = tokenizer.decode(generated_tokens[0], skip_special_tokens=True)
+
+print("\ncontent:", content)
+```
+
+### 4.4 Inference with vLLM
+
+Start vLLM service:
+```bash
+CUDA_VISIBLE_DEVICES=0 vllm serve FreedomIntelligence/openPangu-Embedded-1B --port 8818 --trust_remote_code --served-model-name openPangu-Embedded-1B
+
+# or
+CUDA_VISIBLE_DEVICES=0 \
+python -m vllm.entrypoints.openai.api_server \
+  --model FreedomIntelligence/openPangu-Embedded-1B \
+  --served-model-name openPangu-Embedded-1B \
+  --trust_remote_code \
+  --port 8818
+```
+
+Send requests to API service:
+```bash
+curl http://localhost:8818/v1/chat/completions -H "Content-Type: application/json" -d '{
+    "model": "openPangu-Embedded-1B",
+    "messages": [
+        {"role": "user", "content": "Give me a short introduction to large language models."}
+    ],
+    "temperature": 0.6,
+    "top_p": 0.95,
+    "top_k": 20,
+    "max_tokens": 8192
+    }'
+```
+
+## 5. Model License
+
+Unless otherwise noted, openPangu-Embedded-7B model is licensed under the terms and conditions of **OPENPANGU MODEL LICENSE AGREEMENT VERSION 1.0**, which is intended to be used permissively and enable the further development of artificial intelligence technologies. Please refer to the LICENSE file located in the root directory of the model repository for details.
+
+## 6. Disclaimer
+
+Due to the technical limitations inherent in the technology on which the openPangu-Embedded-7B (“Model”) relies and the fact that the artificial intelligence generated content is automatically produced by Model, Huawei cannot make any guarantees regarding the following matters:
+- The output of this Model is automatically generated via AI algorithms, it does not rule out the possibility that some of the information may be flawed, unreasonable, or cause discomfort, and the generated content does not represent Huawei's attitude or standpoint;
+- There is no guarantee that this Model is 100% accurate, reliable, functional, timely, secure and safety, error-free, uninterrupted, continuously stable, or free of any faults;
+- The output of this Model does not constitute any advices or decisions for you, and it does not guarantee the authenticity, completeness, accuracy, timeliness, legality, functionality, or practicality of the generated content. The generated content cannot replace professionals in medical, legal, and other fields in answering your questions. The generated content is for your reference only and does not represent any attitude, standpoint, or position of Huawei. You need to make independent judgments based on your actual situation, and Huawei does not assume any responsibilities.
+
+For feedback and suggestions, please submit an issue or contact us ([email protected]).

README_ZH.md

@@ -0,0 +1,167 @@
+中文 | [English](README.md)
+
+## 1. 模型简介
+
+openPangu-Embedded-1B 是基于昇腾 NPU 从零训练的高效语言模型，参数量为 1B（不含词表Embedding），模型结构采用 26 层 Dense 架构，训练了约 10T tokens。通过昇腾 Atlas 200I A2可用的模型架构设计、数据和训练策略优化，openPangu-Embedded-1B 在保持端侧运行的要求下达到了较高的精度。
+
+## 2. 模型架构
+
+openPangu-Embedded-1B 是一个为端侧设备运行而设计的高效快思考语言模型。
+
+|                               |      openPangu-Embedded-1B      |
+| :---------------------------: | :----------------: |
+|       **Architecture**        |       Dense        |
+|     **Parameters (Non-Embedding)**      |         1B         |
+|     **Number of Layers**      |         26         |
+|     **Hidden Dimension**      |        1536        |
+|    **Attention Mechanism**    |     GQA      |
+| **Number of Attention Heads** | 12 for Q, 6 for KV |
+|      **Vocabulary Size**      |        153k        |
+|      **Context Length (Natively)**       |        32k         |
+|    **Training Tokens**        |      10T         |
+
+## 3. 测评结果
+
+| 评测集 | 测评指标 | 快思考   |
+|:---: |:---: |:---: |
+| **通用能力** | |
+| MMLU       |    Acc        | 60.72  |
+| CMMLU     |     Acc        | 51.99  |
+| C-Eval  | Acc  | 60.98  |
+| IF-Eval | Prompt Strict | 56.56 |
+| CLUEWSC | Acc | 68.55 |
+| **数学&推理** | |
+| GSM8K    |    Acc          | 66.72  |
+| MATH-500     |   Acc        | 52.00  |
+| DROP | F1 |  50.31 |
+| **代码能力** | |
+| MBPP       |      Pass@1      | 54.09  |
+| HumanEval   |    Pass@1       | 56.71  |
+
+**注：** 评测过程中system prompt 为空。
+
+## 4. 部署和使用
+
+### 4.1 环境安装
+
+```bash
+# 下载模型
+git lfs install
+git clone https://huggingface.co/FreedomIntelligence/openPangu-Embedded-1B
+
+# 安装依赖
+cd openPangu-Embedded-1B
+conda env create -f environment.yml
+conda activate pangu
+```
+
+### 4.2 权重完整性校验
+
+请参考以下方法对下载内容进行完整性校验，hash 值存储在 `checklist.chk` 文件中。
+
+```bash
+#!/usr/bin/env bash
+ARCH=$(uname -m)
+MODEL_PATH="${TARGET_FOLDER}/${MODEL_FOLDER_PATH}"
+cd "$MODEL_PATH" || exit 1
+if [ "$ARCH" = "arm64" ]; then
+    sha256sum checklist.chk
+else
+    sha256sum -c checklist.chk
+fi
+```
+### 4.3 使用Transformers推理
+
+```python
+# coding=utf-8
+# Copyright (c) 2025 Huawei Technologies Co., Ltd. All rights reserved.
+
+from transformers import AutoModelForCausalLM, AutoTokenizer
+from transformers import GenerationConfig
+
+model_local_path = "FreedomIntelligence/openPangu-Embedded-1B"
+
+# load the tokenizer and the model
+tokenizer = AutoTokenizer.from_pretrained(
+    model_local_path, 
+    use_fast=False, 
+    trust_remote_code=True,
+    local_files_only=True
+)
+
+model = AutoModelForCausalLM.from_pretrained(
+    model_local_path,
+    trust_remote_code=True,
+    torch_dtype="auto",
+    device_map="auto",
+    local_files_only=True
+)
+
+# prepare the model input
+sys_prompt = "你必须严格遵守法律法规和社会道德规范。" \
+    "生成任何内容时，都应避免涉及暴力、色情、恐怖主义、种族歧视、性别歧视等不当内容。" \
+    "一旦检测到输入或输出有此类倾向，应拒绝回答并发出警告。例如，如果输入内容包含暴力威胁或色情描述，" \
+    "应返回错误信息：“您的输入包含不当内容，无法处理。”"
+
+prompt = "Give me a short introduction to large language model."
+messages = [
+    {"role": "system", "content": sys_prompt}, # define your system prompt here
+    {"role": "user", "content": prompt}
+]
+text = tokenizer.apply_chat_template(
+    messages,
+    tokenize=False,
+    add_generation_prompt=True
+)
+model_inputs = tokenizer([text], return_tensors="pt").to(model.device)
+
+# conduct text completion
+outputs = model.generate(**model_inputs, max_new_tokens=32768, eos_token_id=45892, return_dict_in_generate=True)
+
+input_length = model_inputs.input_ids.shape[1]
+generated_tokens = outputs.sequences[:, input_length:]
+content = tokenizer.decode(generated_tokens[0], skip_special_tokens=True)
+
+print("\ncontent:", content)
+```
+
+### 4.4 使用vLLM推理
+
+启动vLLM服务：
+```bash
+CUDA_VISIBLE_DEVICES=0 vllm serve FreedomIntelligence/openPangu-Embedded-1B --port 8818 --trust_remote_code --served-model-name openPangu-Embedded-1B
+
+# 或者
+CUDA_VISIBLE_DEVICES=0 \
+python -m vllm.entrypoints.openai.api_server \
+  --model FreedomIntelligence/openPangu-Embedded-1B \
+  --served-model-name openPangu-Embedded-1B \
+  --trust_remote_code \
+  --port 8818
+```
+
+请求API服务：
+```bash
+curl http://localhost:8818/v1/chat/completions -H "Content-Type: application/json" -d '{
+    "model": "openPangu-Embedded-1B",
+    "messages": [
+        {"role": "user", "content": "Give me a short introduction to large language models."}
+    ],
+    "temperature": 0.6,
+    "top_p": 0.95,
+    "top_k": 20,
+    "max_tokens": 8192
+    }'
+```
+
+## 5. 模型许可证
+
+除文件中对开源许可证另有约定外，openPangu-Embedded-1B 模型根据 **OPENPANGU MODEL LICENSE AGREEMENT VERSION 1.0** 授权，旨在允许使用并促进人工智能技术的进一步发展。有关详细信息，请参阅模型存储库根目录中的 LICENSE 文件。
+
+## 6. 免责声明
+由于 openPangu-Embedded-1B（“模型”）所依赖的技术固有的技术限制，以及人工智能生成的内容是由盘古自动生成的，华为无法对以下事项做出任何保证：
+- 尽管该模型的输出由 AI 算法生成，但不能排除某些信息可能存在缺陷、不合理或引起不适的可能性，生成的内容不代表华为的态度或立场；
+- 无法保证该模型 100% 准确、可靠、功能齐全、及时、安全、无错误、不间断、持续稳定或无任何故障；
+- 该模型的输出内容不构成任何建议或决策，也不保证生成的内容的真实性、完整性、准确性、及时性、合法性、功能性或实用性。生成的内容不能替代医疗、法律等领域的专业人士回答您的问题。生成的内容仅供参考，不代表华为的任何态度、立场或观点。您需要根据实际情况做出独立判断，华为不承担任何责任。
+
+如果有任何意见和建议，请提交issue或联系 [email protected]。

checklist.chk

@@ -0,0 +1,11 @@
+5d0c201df44b8bf3e7f7db5485177ea89327f1b591dedccc79858bde12ebef16 *./config.json
+7694a0e7b59d7ec2eeebc2fd058f02fe4dc4464b27f82839fc9f425a88555a3a *./configuration_openpangu_dense.py
+a12bff27a61421a0dddff6d814d6a512d423d466f7fdec406460e45eaca2e7ce *./generation_config.json
+58f15aa7474fcb08d59156d6ecf28df23f187cc84a912a66b2f1d06053dcc988 *./inference/generate.py
+10b12467031fcfbce46f280245aa7e24959b912bfe8bbd4f6a44168d012b565e *./model.safetensors
+f15eaf322af8a0b0f16b26795eb68af836179413d3dbfa4dc44505db6c8b0d6f *./modeling_openpangu_dense.py
+c1f2d87f855b994039c52b1e83c8a7f3d71a2d1eb52946c4a2e862e99f19d8b3 *./modular_openpangu_dense.py
+b34cf5e7c7660889303b6e2d0a346c440356385c9db551d06f6615cf9fc600d1 *./special_tokens_map.json
+c98602d6d1f61792a8bd3393972bbbe7409a205c0bb6299394c74287c26bd723 *./tokenization_openpangu.py
+6b16f1558c0cd4ae6ef1a2c605713be0a514f50e1ce2d2c878979ce988c148ec *./tokenizer.model
+acb88eac57f8765fedf34e9c10bc16d55c46f0902b0fea74fbf041daca2667ae *./tokenizer_config.json

config.json

@@ -0,0 +1,31 @@
+{
+  "architectures": [
+    "PanguEmbeddedForCausalLM"
+  ],
+  "auto_map": {
+    "AutoConfig": "configuration_openpangu_dense.PanguEmbeddedConfig",
+    "AutoModel": "modeling_openpangu_dense.PanguEmbeddedModel",
+    "AutoModelForCausalLM": "modeling_openpangu_dense.PanguEmbeddedForCausalLM"
+  },
+  "bias": true,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "pad_token_id": 0,
+  "eos_token_id": 45892,
+  "hidden_act": "silu",
+  "hidden_size": 1536,
+  "initializer_range": 0.02,
+  "intermediate_size": 6144,
+  "max_position_embeddings": 32768,
+  "model_type": "PanguEmbedded",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 26,
+  "num_key_value_heads": 6,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 4000000.0,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.53.2",
+  "use_cache": true,
+  "vocab_size": 153376
+}

configuration.json

@@ -0,0 +1 @@
+{"framework":"Pytorch","task":"text-generation"}

configuration_openpangu_dense.py

@@ -0,0 +1,56 @@
+# coding=utf-8
+# Copyright (c) 2025 Huawei Technologies Co., Ltd. All rights reserved.
+
+from transformers.utils import logging
+from transformers.configuration_utils import PretrainedConfig
+
+
+logger = logging.get_logger(__name__)
+
+
+class PanguEmbeddedConfig(PretrainedConfig):
+
+    model_type = "PanguEmbedded"
+    _auto_class = "AutoConfig"
+
+    def __init__(
+        self,
+        vocab_size=153376,
+        hidden_size=4096,
+        intermediate_size=12800,
+        num_hidden_layers=34,
+        num_attention_heads=32,
+        num_key_value_heads=8,
+        hidden_act="silu",
+        max_position_embeddings=32768,
+        initializer_range=0.02,
+        rms_norm_eps=1e-5,
+        use_cache=True,
+        pad_token_id=0,
+        bos_token_id=1,
+        eos_token_id=45892,
+        tie_word_embeddings=False,
+        rope_theta=16000000.0,
+        bias=True,
+        **kwargs,
+    ):
+        self.vocab_size = vocab_size
+        self.max_position_embeddings = max_position_embeddings
+        self.hidden_size = hidden_size
+        self.intermediate_size = intermediate_size
+        self.num_hidden_layers = num_hidden_layers
+        self.num_attention_heads = num_attention_heads
+        self.num_key_value_heads = num_key_value_heads
+        self.hidden_act = hidden_act
+        self.initializer_range = initializer_range
+        self.rms_norm_eps = rms_norm_eps
+        self.use_cache = use_cache
+        self.rope_theta = rope_theta
+        self.bias = bias
+        super().__init__(
+            pad_token_id=pad_token_id,
+            bos_token_id=bos_token_id,
+            eos_token_id=eos_token_id,
+            tie_word_embeddings=tie_word_embeddings,
+            **kwargs,
+        )

environment.yml

@@ -0,0 +1,318 @@
+name: pangu
+channels:
+  - defaults
+dependencies:
+  - _libgcc_mutex=0.1=main
+  - _openmp_mutex=5.1=1_gnu
+  - bzip2=1.0.8=h5eee18b_6
+  - ca-certificates=2025.2.25=h06a4308_0
+  - expat=2.7.1=h6a678d5_0
+  - ld_impl_linux-64=2.40=h12ee557_0
+  - libffi=3.4.4=h6a678d5_1
+  - libgcc-ng=11.2.0=h1234567_1
+  - libgomp=11.2.0=h1234567_1
+  - libstdcxx-ng=11.2.0=h1234567_1
+  - libuuid=1.41.5=h5eee18b_0
+  - libxcb=1.17.0=h9b100fa_0
+  - ncurses=6.4=h6a678d5_0
+  - openssl=3.0.17=h5eee18b_0
+  - pip=25.1=pyhc872135_2
+  - pthread-stubs=0.3=h0ce48e5_1
+  - python=3.10.18=h1a3bd86_0
+  - readline=8.2=h5eee18b_0
+  - setuptools=78.1.1=py310h06a4308_0
+  - sqlite=3.50.2=hb25bd0a_1
+  - tk=8.6.14=h993c535_1
+  - wheel=0.45.1=py310h06a4308_0
+  - xorg-libx11=1.8.12=h9b100fa_1
+  - xorg-libxau=1.0.12=h9b100fa_0
+  - xorg-libxdmcp=1.1.5=h9b100fa_0
+  - xorg-xorgproto=2024.1=h5eee18b_1
+  - xz=5.6.4=h5eee18b_1
+  - zlib=1.2.13=h5eee18b_1
+  - pip:
+      - accelerate==1.9.0
+      - aiofiles==24.1.0
+      - aiohappyeyeballs==2.6.1
+      - aiohttp==3.12.14
+      - aiosignal==1.4.0
+      - albucore==0.0.24
+      - albumentations==2.0.8
+      - altair==5.5.0
+      - annotated-types==0.7.0
+      - antlr4-python3-runtime==4.9.3
+      - anyio==4.9.0
+      - argcomplete==3.6.2
+      - astor==0.8.1
+      - async-timeout==4.0.3
+      - attrs==25.3.0
+      - auto-gptq==0.7.1
+      - backoff==2.2.1
+      - bcrypt==4.3.0
+      - blake3==1.0.5
+      - blinker==1.9.0
+      - boto3==1.39.11
+      - botocore==1.39.11
+      - brotli==1.1.0
+      - build==1.3.0
+      - cachetools==5.5.2
+      - cbor2==5.6.5
+      - certifi==2025.7.14
+      - cffi==1.17.1
+      - charset-normalizer==3.4.2
+      - chromadb==1.0.15
+      - click==8.2.1
+      - cloudpickle==3.1.1
+      - coloredlogs==15.0.1
+      - colorlog==6.9.0
+      - compressed-tensors==0.10.2
+      - contourpy==1.3.2
+      - cryptography==45.0.5
+      - cupy-cuda12x==13.5.1
+      - cycler==0.12.1
+      - dataclasses-json==0.6.7
+      - datasets==4.0.0
+      - depyf==0.19.0
+      - dill==0.3.8
+      - diskcache==5.6.3
+      - distro==1.9.0
+      - dnspython==2.7.0
+      - doclayout-yolo==0.0.2b1
+      - durationpy==0.10
+      - einops==0.8.1
+      - email-validator==2.2.0
+      - exceptiongroup==1.3.0
+      - fast-langdetect==0.2.5
+      - fastapi==0.116.1
+      - fastapi-cli==0.0.8
+      - fastapi-cloud-cli==0.1.4
+      - fastrlock==0.8.3
+      - fasttext-predict==0.9.2.4
+      - ffmpy==0.6.1
+      - filelock==3.18.0
+      - flatbuffers==25.2.10
+      - fonttools==4.59.0
+      - frozenlist==1.7.0
+      - fsspec==2025.3.0
+      - ftfy==6.3.1
+      - gekko==1.3.0
+      - gguf==0.17.1
+      - gitdb==4.0.12
+      - gitpython==3.1.45
+      - google-auth==2.40.3
+      - googleapis-common-protos==1.70.0
+      - gradio==5.38.0
+      - gradio-client==1.11.0
+      - gradio-pdf==0.0.22
+      - greenlet==3.2.3
+      - groovy==0.1.2
+      - grpcio==1.74.0
+      - h11==0.16.0
+      - hf-xet==1.1.5
+      - httpcore==1.0.9
+      - httptools==0.6.4
+      - httpx==0.28.1
+      - httpx-sse==0.4.1
+      - huggingface-hub==0.33.4
+      - humanfriendly==10.0
+      - idna==3.10
+      - importlib-metadata==8.7.0
+      - importlib-resources==6.5.2
+      - interegular==0.3.3
+      - jinja2==3.1.6
+      - jiter==0.10.0
+      - jmespath==1.0.1
+      - joblib==1.5.1
+      - json-repair==0.47.8
+      - jsonpatch==1.33
+      - jsonpointer==3.0.0
+      - jsonschema==4.25.0
+      - jsonschema-specifications==2025.4.1
+      - kiwisolver==1.4.8
+      - kubernetes==33.1.0
+      - langchain==0.3.27
+      - langchain-chroma==0.2.5
+      - langchain-community==0.3.27
+      - langchain-core==0.3.72
+      - langchain-huggingface==0.3.1
+      - langchain-ollama==0.3.6
+      - langchain-openai==0.3.28
+      - langchain-text-splitters==0.3.9
+      - langsmith==0.4.8
+      - lark==1.2.2
+      - llguidance==0.7.30
+      - llvmlite==0.44.0
+      - lm-format-enforcer==0.10.11
+      - loguru==0.7.3
+      - magic-pdf==1.3.12
+      - markdown-it-py==3.0.0
+      - markupsafe==3.0.2
+      - marshmallow==3.26.1
+      - matplotlib==3.10.3
+      - mdurl==0.1.2
+      - mineru==2.1.4
+      - mistral-common==1.8.3
+      - mmh3==5.2.0
+      - modelscope==1.28.0
+      - mpmath==1.3.0
+      - msgpack==1.1.1
+      - msgspec==0.19.0
+      - multidict==6.6.3
+      - multiprocess==0.70.16
+      - mypy-extensions==1.1.0
+      - narwhals==2.0.1
+      - networkx==3.4.2
+      - ninja==1.11.1.4
+      - numba==0.61.2
+      - numpy==2.2.6
+      - nvidia-cublas-cu12==12.6.4.1
+      - nvidia-cuda-cupti-cu12==12.6.80
+      - nvidia-cuda-nvrtc-cu12==12.6.77
+      - nvidia-cuda-runtime-cu12==12.6.77
+      - nvidia-cudnn-cu12==9.5.1.17
+      - nvidia-cufft-cu12==11.3.0.4
+      - nvidia-cufile-cu12==1.11.1.6
+      - nvidia-curand-cu12==10.3.7.77
+      - nvidia-cusolver-cu12==11.7.1.2
+      - nvidia-cusparse-cu12==12.5.4.2
+      - nvidia-cusparselt-cu12==0.6.3
+      - nvidia-nccl-cu12==2.26.2
+      - nvidia-nvjitlink-cu12==12.6.85
+      - nvidia-nvtx-cu12==12.6.77
+      - oauthlib==3.3.1
+      - ollama==0.5.1
+      - omegaconf==2.3.0
+      - onnxruntime==1.22.1
+      - openai==1.88.0
+      - opencv-python==4.12.0.88
+      - opencv-python-headless==4.12.0.88
+      - opentelemetry-api==1.36.0
+      - opentelemetry-exporter-otlp-proto-common==1.36.0
+      - opentelemetry-exporter-otlp-proto-grpc==1.36.0
+      - opentelemetry-proto==1.36.0
+      - opentelemetry-sdk==1.36.0
+      - opentelemetry-semantic-conventions==0.57b0
+      - orjson==3.11.0
+      - outlines-core==0.2.10
+      - overrides==7.7.0
+      - packaging==25.0
+      - pandas==2.3.1
+      - partial-json-parser==0.2.1.1.post6
+      - pdfminer-six==20250506
+      - pdftext==0.6.3
+      - peft==0.16.0
+      - pillow==11.3.0
+      - pipx==1.7.1
+      - platformdirs==4.3.8
+      - posthog==5.4.0
+      - prometheus-client==0.22.1
+      - prometheus-fastapi-instrumentator==7.1.0
+      - propcache==0.3.2
+      - protobuf==6.31.1
+      - psutil==7.0.0
+      - py-cpuinfo==9.0.0
+      - pyarrow==21.0.0
+      - pyasn1==0.6.1
+      - pyasn1-modules==0.4.2
+      - pybase64==1.4.1
+      - pyclipper==1.3.0.post6
+      - pycountry==24.6.1
+      - pycparser==2.22
+      - pydantic==2.10.6
+      - pydantic-core==2.27.2
+      - pydantic-extra-types==2.10.5
+      - pydantic-settings==2.10.1
+      - pydeck==0.9.1
+      - pydub==0.25.1
+      - pygments==2.19.2
+      - pymupdf==1.24.14
+      - pyparsing==3.2.3
+      - pypdf==5.8.0
+      - pypdfium2==4.30.0
+      - pypika==0.48.9
+      - pyproject-hooks==1.2.0
+      - python-dateutil==2.9.0.post0
+      - python-dotenv==1.1.1
+      - python-json-logger==3.3.0
+      - python-multipart==0.0.20
+      - pytz==2025.2
+      - pyyaml==6.0.2
+      - pyzmq==27.0.0
+      - rapid-table==1.0.5
+      - ray==2.48.0
+      - referencing==0.36.2
+      - regex==2024.11.6
+      - reportlab==4.4.2
+      - requests==2.32.4
+      - requests-oauthlib==2.0.0
+      - requests-toolbelt==1.0.0
+      - rich==14.0.0
+      - rich-toolkit==0.14.8
+      - rignore==0.6.4
+      - robust-downloader==0.0.2
+      - rouge==1.0.1
+      - rpds-py==0.26.0
+      - rsa==4.9.1
+      - ruff==0.12.4
+      - s3transfer==0.13.1
+      - safehttpx==0.1.6
+      - safetensors==0.5.3
+      - scikit-learn==1.7.1
+      - scipy==1.15.3
+      - seaborn==0.13.2
+      - semantic-version==2.10.0
+      - sentence-transformers==5.0.0
+      - sentencepiece==0.2.0
+      - sentry-sdk==2.33.2
+      - shapely==2.1.1
+      - shellingham==1.5.4
+      - simsimd==6.5.0
+      - six==1.17.0
+      - smmap==5.0.2
+      - sniffio==1.3.1
+      - soundfile==0.13.1
+      - soxr==0.5.0.post1
+      - sqlalchemy==2.0.41
+      - starlette==0.47.2
+      - streamlit==1.47.1
+      - stringzilla==3.12.5
+      - sympy==1.14.0
+      - tenacity==9.1.2
+      - thop==0.1.1-2209072238
+      - threadpoolctl==3.6.0
+      - tiktoken==0.9.0
+      - tokenizers==0.21.2
+      - toml==0.10.2
+      - tomli==2.2.1
+      - tomlkit==0.13.3
+      - torch==2.7.1
+      - torchaudio==2.7.1
+      - torchvision==0.22.1
+      - tornado==6.5.1
+      - tqdm==4.67.1
+      - transformers==4.53.3
+      - triton==3.3.1
+      - typer==0.16.0
+      - typing-extensions==4.14.1
+      - typing-inspect==0.9.0
+      - typing-inspection==0.4.1
+      - tzdata==2025.2
+      - ultralytics==8.3.169
+      - ultralytics-thop==2.0.14
+      - urllib3==2.5.0
+      - userpath==1.9.2
+      - uvicorn==0.35.0
+      - uvloop==0.21.0
+      - vllm==0.10.0
+      - watchdog==6.0.0
+      - watchfiles==1.1.0
+      - wcwidth==0.2.13
+      - websocket-client==1.8.0
+      - websockets==15.0.1
+      - xformers==0.0.31
+      - xgrammar==0.1.21
+      - xxhash==3.5.0
+      - yarl==1.20.1
+      - zipp==3.23.0
+      - zstandard==0.23.0
+prefix: /root/miniconda3/envs/pangu

generate.py

@@ -0,0 +1,50 @@
+# coding=utf-8
+# Copyright (c) 2025 Huawei Technologies Co., Ltd. All rights reserved.
+
+from transformers import AutoModelForCausalLM, AutoTokenizer
+from transformers import GenerationConfig
+
+model_local_path = "path_to_openPangu-Embedded-1B"
+
+# load the tokenizer and the model
+tokenizer = AutoTokenizer.from_pretrained(
+    model_local_path, 
+    use_fast=False, 
+    trust_remote_code=True,
+    local_files_only=True
+)
+
+model = AutoModelForCausalLM.from_pretrained(
+    model_local_path,
+    trust_remote_code=True,
+    torch_dtype="auto",
+    device_map="auto",
+    local_files_only=True
+)
+
+# prepare the model input
+sys_prompt = "你必须严格遵守法律法规和社会道德规范。" \
+    "生成任何内容时，都应避免涉及暴力、色情、恐怖主义、种族歧视、性别歧视等不当内容。" \
+    "一旦检测到输入或输出有此类倾向，应拒绝回答并发出警告。例如，如果输入内容包含暴力威胁或色情描述，" \
+    "应返回错误信息：“您的输入包含不当内容，无法处理。”"
+
+prompt = "Give me a short introduction to large language model."
+messages = [
+    {"role": "system", "content": sys_prompt}, # define your system prompt here
+    {"role": "user", "content": prompt}
+]
+text = tokenizer.apply_chat_template(
+    messages,
+    tokenize=False,
+    add_generation_prompt=True
+)
+model_inputs = tokenizer([text], return_tensors="pt").to(model.device)
+
+# conduct text completion
+outputs = model.generate(**model_inputs, max_new_tokens=32768, eos_token_id=45892, return_dict_in_generate=True)
+
+input_length = model_inputs.input_ids.shape[1]
+generated_tokens = outputs.sequences[:, input_length:]
+content = tokenizer.decode(generated_tokens[0], skip_special_tokens=True)
+
+print("\ncontent:", content)

generation_config.json

@@ -0,0 +1,11 @@
+{
+  "_from_model_config": true,
+  "do_sample": false,
+  "bos_token_id": 1,
+  "pad_token_id": 0,
+  "eos_token_id": 45892,
+  "temperature": 1.0,
+  "top_k": 0,
+  "top_p": 0.8,
+  "transformers_version": "4.53.2"
+}

gitattributes

@@ -0,0 +1,35 @@
+*.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
+*.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

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10b12467031fcfbce46f280245aa7e24959b912bfe8bbd4f6a44168d012b565e
+size 2783034328

modeling_openpangu_dense.py

@@ -0,0 +1,586 @@
+#                🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨
+#                       This file was automatically generated from modular_openpangu_dense.py.
+#               Do NOT edit this file manually as any edits will be overwritten by the generation of
+#             the file from the modular. If any change should be done, please apply the change to the
+#                          modular_openpangu_dense.py file directly. One of our CI enforces this.
+#                🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨
+
+# coding=utf-8
+# Copyright (c) 2025 Huawei Technologies Co., Ltd. All rights reserved.
+# Copyright 2022 EleutherAI and the HuggingFace Inc. team. All rights reserved.
+#
+# This code is based on EleutherAI's GPT-NeoX library and the GPT-NeoX
+# and OPT implementations in this library. It has been modified from its
+# original forms to accommodate minor architectural differences compared
+# to GPT-NeoX and OPT used by the Meta AI team that trained the model.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+from typing import Callable, Optional, Union
+
+import torch
+from torch import nn
+
+try:
+    import torch_npu
+    from torch_npu.contrib import transfer_to_npu
+    if "910" in torch.npu.get_device_name():
+        NPU_ATTN_INFR = True
+        print("[INFO] torch_npu detected. Using NPU fused infer attention.")
+except ImportError:
+    NPU_ATTN_INFR = False
+
+from transformers.activations import ACT2FN
+from transformers.cache_utils import Cache, DynamicCache
+from transformers.generation import GenerationMixin
+from transformers.masking_utils import create_causal_mask
+from transformers.modeling_flash_attention_utils import FlashAttentionKwargs
+from transformers.modeling_layers import GradientCheckpointingLayer
+from transformers.modeling_outputs import (
+    BaseModelOutputWithPast,
+    CausalLMOutputWithPast,
+    SequenceClassifierOutputWithPast,
+)
+from transformers.modeling_rope_utils import ROPE_INIT_FUNCTIONS, dynamic_rope_update
+from transformers.modeling_utils import ALL_ATTENTION_FUNCTIONS, PreTrainedModel
+from transformers.processing_utils import Unpack
+from transformers.utils import LossKwargs, auto_docstring, can_return_tuple, logging
+from .configuration_openpangu_dense import PanguEmbeddedConfig
+
+
+logger = logging.get_logger(__name__)
+
+
+class PanguEmbeddedRMSNorm(nn.Module):
+    def __init__(self, hidden_size, eps=1e-6):
+        """
+        PanguEmbeddedRMSNorm is equivalent to T5LayerNorm
+        """
+        super().__init__()
+        self.weight = nn.Parameter(torch.ones(hidden_size))
+        self.variance_epsilon = eps
+
+    def forward(self, hidden_states):
+        input_dtype = hidden_states.dtype
+        hidden_states = hidden_states.to(torch.float32)
+        variance = hidden_states.pow(2).mean(-1, keepdim=True)
+        hidden_states = hidden_states * torch.rsqrt(variance + self.variance_epsilon)
+        return self.weight * hidden_states.to(input_dtype)
+
+    def extra_repr(self):
+        return f"{tuple(self.weight.shape)}, eps={self.variance_epsilon}"
+
+
+class PanguEmbeddedRotaryEmbedding(nn.Module):
+    def __init__(self, config: PanguEmbeddedConfig, device=None):
+        super().__init__()
+        # BC: "rope_type" was originally "type"
+        if hasattr(config, "rope_scaling") and config.rope_scaling is not None:
+            self.rope_type = config.rope_scaling.get("rope_type", config.rope_scaling.get("type"))
+        else:
+            self.rope_type = "default"
+        self.max_seq_len_cached = config.max_position_embeddings
+        self.original_max_seq_len = config.max_position_embeddings
+
+        self.config = config
+        self.rope_init_fn = ROPE_INIT_FUNCTIONS[self.rope_type]
+
+        inv_freq, self.attention_scaling = self.rope_init_fn(self.config, device)
+        self.register_buffer("inv_freq", inv_freq, persistent=False)
+        self.original_inv_freq = self.inv_freq
+
+    @torch.no_grad()
+    @dynamic_rope_update  # power user: used with advanced RoPE types (e.g. dynamic rope)
+    def forward(self, x, position_ids):
+        inv_freq_expanded = self.inv_freq[None, :, None].float().expand(position_ids.shape[0], -1, 1).to(x.device)
+        position_ids_expanded = position_ids[:, None, :].float()
+
+        device_type = x.device.type if isinstance(x.device.type, str) and x.device.type != "mps" else "cpu"
+        with torch.autocast(device_type=device_type, enabled=False):  # Force float32
+            freqs = (inv_freq_expanded.float() @ position_ids_expanded.float()).transpose(1, 2)
+            emb = torch.cat((freqs, freqs), dim=-1)
+            cos = emb.cos() * self.attention_scaling
+            sin = emb.sin() * self.attention_scaling
+
+        return cos.to(dtype=x.dtype), sin.to(dtype=x.dtype)
+
+
+def rotate_half(x):
+    """Rotates half the hidden dims of the input."""
+    x1 = x[..., : x.shape[-1] // 2]
+    x2 = x[..., x.shape[-1] // 2 :]
+    return torch.cat((-x2, x1), dim=-1)
+
+
+def apply_rotary_pos_emb(q, k, cos, sin, position_ids=None, unsqueeze_dim=1):
+    """Applies Rotary Position Embedding to the query and key tensors.
+
+    Args:
+        q (`torch.Tensor`): The query tensor.
+        k (`torch.Tensor`): The key tensor.
+        cos (`torch.Tensor`): The cosine part of the rotary embedding.
+        sin (`torch.Tensor`): The sine part of the rotary embedding.
+        position_ids (`torch.Tensor`, *optional*):
+            Deprecated and unused.
+        unsqueeze_dim (`int`, *optional*, defaults to 1):
+            The 'unsqueeze_dim' argument specifies the dimension along which to unsqueeze cos[position_ids] and
+            sin[position_ids] so that they can be properly broadcasted to the dimensions of q and k. For example, note
+            that cos[position_ids] and sin[position_ids] have the shape [batch_size, seq_len, head_dim]. Then, if q and
+            k have the shape [batch_size, heads, seq_len, head_dim], then setting unsqueeze_dim=1 makes
+            cos[position_ids] and sin[position_ids] broadcastable to the shapes of q and k. Similarly, if q and k have
+            the shape [batch_size, seq_len, heads, head_dim], then set unsqueeze_dim=2.
+    Returns:
+        `tuple(torch.Tensor)` comprising of the query and key tensors rotated using the Rotary Position Embedding.
+    """
+    cos = cos.unsqueeze(unsqueeze_dim)
+    sin = sin.unsqueeze(unsqueeze_dim)
+    q_embed = (q * cos) + (rotate_half(q) * sin)
+    k_embed = (k * cos) + (rotate_half(k) * sin)
+    return q_embed, k_embed
+
+
+class PanguEmbeddedMLP(nn.Module):
+    def __init__(self, config):
+        super().__init__()
+        self.config = config
+        self.hidden_size = config.hidden_size
+        self.intermediate_size = config.intermediate_size
+        self.gate_proj = nn.Linear(self.hidden_size, self.intermediate_size, bias=False)
+        self.up_proj = nn.Linear(self.hidden_size, self.intermediate_size, bias=False)
+        self.down_proj = nn.Linear(self.intermediate_size, self.hidden_size, bias=False)
+        self.act_fn = ACT2FN[config.hidden_act]
+
+    def forward(self, x):
+        down_proj = self.down_proj(self.act_fn(self.gate_proj(x)) * self.up_proj(x))
+        return down_proj
+
+
+def repeat_kv(hidden_states: torch.Tensor, n_rep: int) -> torch.Tensor:
+    """
+    This is the equivalent of torch.repeat_interleave(x, dim=1, repeats=n_rep). The hidden states go from (batch,
+    num_key_value_heads, seqlen, head_dim) to (batch, num_attention_heads, seqlen, head_dim)
+    """
+    batch, num_key_value_heads, slen, head_dim = hidden_states.shape
+    if n_rep == 1:
+        return hidden_states
+    hidden_states = hidden_states[:, :, None, :, :].expand(batch, num_key_value_heads, n_rep, slen, head_dim)
+    return hidden_states.reshape(batch, num_key_value_heads * n_rep, slen, head_dim)
+
+
+def eager_attention_forward(
+    module: nn.Module,
+    query: torch.Tensor,
+    key: torch.Tensor,
+    value: torch.Tensor,
+    attention_mask: Optional[torch.Tensor],
+    scaling: float,
+    dropout: float = 0.0,
+    **kwargs,
+):
+    key_states = repeat_kv(key, module.num_key_value_groups)
+    value_states = repeat_kv(value, module.num_key_value_groups)
+
+    attn_weights = torch.matmul(query, key_states.transpose(2, 3)) * scaling
+    if attention_mask is not None:
+        causal_mask = attention_mask[:, :, :, : key_states.shape[-2]]
+        attn_weights = attn_weights + causal_mask
+
+    attn_weights = nn.functional.softmax(attn_weights, dim=-1, dtype=torch.float32).to(query.dtype)
+    attn_weights = nn.functional.dropout(attn_weights, p=dropout, training=module.training)
+    attn_output = torch.matmul(attn_weights, value_states)
+    attn_output = attn_output.transpose(1, 2).contiguous()
+
+    return attn_output, attn_weights
+
+
+class PanguEmbeddedAttention(nn.Module):
+    """Multi-headed attention from 'Attention Is All You Need' paper"""
+
+    def __init__(self, config: PanguEmbeddedConfig, layer_idx: int):
+        super().__init__()
+        self.config = config
+        self.layer_idx = layer_idx
+        self.head_dim = getattr(config, "head_dim", config.hidden_size // config.num_attention_heads)
+        self.num_heads = config.num_attention_heads
+        self.num_key_value_heads = config.num_key_value_heads
+        self.num_key_value_groups = config.num_attention_heads // config.num_key_value_heads
+        self.scaling = self.head_dim**-0.5
+        self.attention_dropout = config.attention_dropout
+        self.is_causal = True
+
+        self.q_proj = nn.Linear(config.hidden_size, config.num_attention_heads * self.head_dim, bias=config.bias)
+        self.k_proj = nn.Linear(config.hidden_size, config.num_key_value_heads * self.head_dim, bias=config.bias)
+        self.v_proj = nn.Linear(config.hidden_size, config.num_key_value_heads * self.head_dim, bias=config.bias)
+        self.o_proj = nn.Linear(config.num_attention_heads * self.head_dim, config.hidden_size, bias=config.bias)
+
+    def forward(
+        self,
+        hidden_states: torch.Tensor,
+        position_embeddings: tuple[torch.Tensor, torch.Tensor],
+        attention_mask: Optional[torch.Tensor],
+        past_key_value: Optional[Cache] = None,
+        cache_position: Optional[torch.LongTensor] = None,
+        **kwargs: Unpack[FlashAttentionKwargs],
+    ) -> tuple[torch.Tensor, Optional[torch.Tensor], Optional[tuple[torch.Tensor]]]:
+        input_shape = hidden_states.shape[:-1]
+        hidden_shape = (*input_shape, -1, self.head_dim)
+
+        query_states = self.q_proj(hidden_states).view(hidden_shape).transpose(1, 2)
+        key_states = self.k_proj(hidden_states).view(hidden_shape).transpose(1, 2)
+        value_states = self.v_proj(hidden_states).view(hidden_shape).transpose(1, 2)
+
+        cos, sin = position_embeddings
+        query_states, key_states = apply_rotary_pos_emb(query_states, key_states, cos, sin)
+
+        if past_key_value is not None:
+            # sin and cos are specific to RoPE models; cache_position needed for the static cache
+            cache_kwargs = {"sin": sin, "cos": cos, "cache_position": cache_position}
+            key_states, value_states = past_key_value.update(key_states, value_states, self.layer_idx, cache_kwargs)
+
+        attention_interface: Callable = eager_attention_forward
+        if self.config._attn_implementation != "eager":
+            attention_interface = ALL_ATTENTION_FUNCTIONS[self.config._attn_implementation]
+        
+        if not self.training and NPU_ATTN_INFR:
+            q_len = input_shape[1]
+            if attention_mask is not None:
+                attention_mask = ~attention_mask.bool()
+            elif q_len > 1:
+                attention_mask = torch.triu(torch.ones([q_len, q_len]), diagonal=1).bool().unsqueeze(0).unsqueeze(0).to(query_states.device)
+
+            attn_output, _ = torch_npu.npu_fused_infer_attention_score(
+                query_states, key_states, value_states,
+                num_heads=self.num_heads, num_key_value_heads=self.num_key_value_heads,
+                input_layout="BNSD", atten_mask=attention_mask, scale=self.scaling)
+            attn_output = attn_output.transpose(1, 2)
+            attn_weights = None
+        else:
+            attn_output, attn_weights = attention_interface(
+                self,
+                query_states,
+                key_states,
+                value_states,
+                attention_mask,
+                dropout=0.0 if not self.training else self.attention_dropout,
+                scaling=self.scaling,
+                **kwargs,
+            )
+
+        attn_output = attn_output.reshape(*input_shape, -1).contiguous()
+        attn_output = self.o_proj(attn_output)
+        return attn_output, attn_weights
+
+
+class PanguEmbeddedDecoderLayer(GradientCheckpointingLayer):
+    def __init__(self, config: PanguEmbeddedConfig, layer_idx: int):
+        super().__init__()
+        self.hidden_size = config.hidden_size
+        self.self_attn = PanguEmbeddedAttention(config=config, layer_idx=layer_idx)
+        self.mlp = PanguEmbeddedMLP(config)
+        self.input_layernorm = PanguEmbeddedRMSNorm(config.hidden_size, eps=config.rms_norm_eps)
+        self.post_attention_layernorm = PanguEmbeddedRMSNorm(config.hidden_size, eps=config.rms_norm_eps)
+
+    def forward(
+        self,
+        hidden_states: torch.Tensor,
+        attention_mask: Optional[torch.Tensor] = None,
+        position_ids: Optional[torch.LongTensor] = None,
+        past_key_value: Optional[Cache] = None,
+        output_attentions: Optional[bool] = False,
+        use_cache: Optional[bool] = False,
+        cache_position: Optional[torch.LongTensor] = None,
+        position_embeddings: Optional[tuple[torch.Tensor, torch.Tensor]] = None,  # necessary, but kept here for BC
+        **kwargs: Unpack[FlashAttentionKwargs],
+    ) -> tuple[torch.FloatTensor, Optional[tuple[torch.FloatTensor, torch.FloatTensor]]]:
+        residual = hidden_states
+        hidden_states = self.input_layernorm(hidden_states)
+
+        # Self Attention
+        hidden_states, self_attn_weights = self.self_attn(
+            hidden_states=hidden_states,
+            attention_mask=attention_mask,
+            position_ids=position_ids,
+            past_key_value=past_key_value,
+            output_attentions=output_attentions,
+            use_cache=use_cache,
+            cache_position=cache_position,
+            position_embeddings=position_embeddings,
+            **kwargs,
+        )
+        hidden_states = residual + hidden_states
+
+        # Fully Connected
+        residual = hidden_states
+        hidden_states = self.post_attention_layernorm(hidden_states)
+        hidden_states = self.mlp(hidden_states)
+        hidden_states = residual + hidden_states
+
+        outputs = (hidden_states,)
+        if output_attentions:
+            outputs += (self_attn_weights,)
+
+        return outputs
+
+
+@auto_docstring
+class PanguEmbeddedPreTrainedModel(PreTrainedModel):
+    config_class = PanguEmbeddedConfig
+    base_model_prefix = "model"
+    supports_gradient_checkpointing = True
+    _no_split_modules = ["PanguEmbeddedDecoderLayer"]
+    _skip_keys_device_placement = ["past_key_values"]
+    _supports_flash_attn_3 = True
+    _supports_flash_attn_2 = True
+    _supports_sdpa = True
+    _supports_flex_attn = True
+    _supports_cache_class = True
+    _supports_quantized_cache = True
+    _supports_static_cache = True
+    _supports_attention_backend = True
+
+    def _init_weights(self, module):
+        std = self.config.initializer_range
+        if isinstance(module, nn.Linear):
+            module.weight.data.normal_(mean=0.0, std=std)
+            if module.bias is not None:
+                module.bias.data.zero_()
+        elif isinstance(module, nn.Embedding):
+            module.weight.data.normal_(mean=0.0, std=std)
+            if module.padding_idx is not None:
+                module.weight.data[module.padding_idx].zero_()
+        elif isinstance(module, PanguEmbeddedRMSNorm):
+            module.weight.data.fill_(1.0)
+
+
+@auto_docstring
+class PanguEmbeddedModel(PanguEmbeddedPreTrainedModel):
+    def __init__(self, config: PanguEmbeddedConfig):
+        super().__init__(config)
+        self.padding_idx = config.pad_token_id
+        self.vocab_size = config.vocab_size
+
+        self.embed_tokens = nn.Embedding(config.vocab_size, config.hidden_size, self.padding_idx)
+        self.layers = nn.ModuleList(
+            [PanguEmbeddedDecoderLayer(config, layer_idx) for layer_idx in range(config.num_hidden_layers)]
+        )
+        self.norm = PanguEmbeddedRMSNorm(config.hidden_size, eps=config.rms_norm_eps)
+        self.rotary_emb = PanguEmbeddedRotaryEmbedding(config=config)
+        self.gradient_checkpointing = False
+
+        # Initialize weights and apply final processing
+        self.post_init()
+
+    def get_input_embeddings(self):
+        return self.embed_tokens
+
+    def set_input_embeddings(self, value):
+        self.embed_tokens = value
+
+    @can_return_tuple
+    @auto_docstring
+    def forward(
+        self,
+        input_ids: Optional[torch.LongTensor] = None,
+        attention_mask: Optional[torch.Tensor] = None,
+        position_ids: Optional[torch.LongTensor] = None,
+        past_key_values: Optional[Cache] = None,
+        inputs_embeds: Optional[torch.FloatTensor] = None,
+        use_cache: Optional[bool] = None,
+        output_attentions: Optional[bool] = None,
+        output_hidden_states: Optional[bool] = None,
+        cache_position: Optional[torch.LongTensor] = None,
+        **flash_attn_kwargs: Unpack[FlashAttentionKwargs],
+    ) -> BaseModelOutputWithPast:
+        output_attentions = output_attentions if output_attentions is not None else self.config.output_attentions
+        output_hidden_states = (
+            output_hidden_states if output_hidden_states is not None else self.config.output_hidden_states
+        )
+        use_cache = use_cache if use_cache is not None else self.config.use_cache
+
+        if (input_ids is None) ^ (inputs_embeds is not None):
+            raise ValueError("You must specify exactly one of input_ids or inputs_embeds")
+
+        if self.gradient_checkpointing and self.training and use_cache:
+            logger.warning_once(
+                "`use_cache=True` is incompatible with gradient checkpointing. Setting `use_cache=False`."
+            )
+            use_cache = False
+
+        # TODO (joao): remove this exception in v4.56 -- it exists for users that try to pass a legacy cache
+        if not isinstance(past_key_values, (type(None), Cache)):
+            raise ValueError("The `past_key_values` should be either a `Cache` object or `None`.")
+
+        if inputs_embeds is None:
+            inputs_embeds = self.embed_tokens(input_ids)
+
+        if use_cache and past_key_values is None:
+            past_key_values = DynamicCache()
+
+        if cache_position is None:
+            past_seen_tokens = past_key_values.get_seq_length() if past_key_values is not None else 0
+            cache_position = torch.arange(
+                past_seen_tokens, past_seen_tokens + inputs_embeds.shape[1], device=inputs_embeds.device
+            )
+
+        if position_ids is None:
+            position_ids = cache_position.unsqueeze(0)
+
+        causal_mask = create_causal_mask(
+            config=self.config,
+            input_embeds=inputs_embeds,
+            attention_mask=attention_mask,
+            cache_position=cache_position,
+            past_key_values=past_key_values,
+            position_ids=position_ids,
+        )
+
+        hidden_states = inputs_embeds
+
+        # create position embeddings to be shared across the decoder layers
+        position_embeddings = self.rotary_emb(hidden_states, position_ids)
+
+        # decoder layers
+        all_hidden_states = () if output_hidden_states else None
+        all_self_attns = () if output_attentions else None
+
+        for decoder_layer in self.layers[: self.config.num_hidden_layers]:
+            if output_hidden_states:
+                all_hidden_states += (hidden_states,)
+
+            layer_outputs = decoder_layer(
+                hidden_states,
+                attention_mask=causal_mask,
+                position_ids=position_ids,
+                past_key_value=past_key_values,
+                output_attentions=output_attentions,
+                use_cache=use_cache,
+                cache_position=cache_position,
+                position_embeddings=position_embeddings,
+                **flash_attn_kwargs,
+            )
+
+            hidden_states = layer_outputs[0]
+
+            if output_attentions:
+                all_self_attns += (layer_outputs[1],)
+
+        hidden_states = self.norm(hidden_states)
+
+        # add hidden states from the last decoder layer
+        if output_hidden_states:
+            all_hidden_states += (hidden_states,)
+
+        return BaseModelOutputWithPast(
+            last_hidden_state=hidden_states,
+            past_key_values=past_key_values if use_cache else None,
+            hidden_states=all_hidden_states,
+            attentions=all_self_attns,
+        )
+
+
+class KwargsForCausalLM(FlashAttentionKwargs, LossKwargs): ...
+
+
+@auto_docstring
+class PanguEmbeddedForCausalLM(PanguEmbeddedPreTrainedModel, GenerationMixin):
+    _tied_weights_keys = ["lm_head.weight"]
+    _tp_plan = {"lm_head": "colwise_rep"}
+    _pp_plan = {"lm_head": (["hidden_states"], ["logits"])}
+
+    def __init__(self, config):
+        super().__init__(config)
+        self.model = PanguEmbeddedModel(config)
+        self.vocab_size = config.vocab_size
+        self.lm_head = nn.Linear(config.hidden_size, config.vocab_size, bias=False)
+
+        # Initialize weights and apply final processing
+        self.post_init()
+
+    def get_input_embeddings(self):
+        return self.model.embed_tokens
+
+    def set_input_embeddings(self, value):
+        self.model.embed_tokens = value
+
+    def get_output_embeddings(self):
+        return self.lm_head
+
+    def set_output_embeddings(self, new_embeddings):
+        self.lm_head = new_embeddings
+
+    def set_decoder(self, decoder):
+        self.model = decoder
+
+    def get_decoder(self):
+        return self.model
+
+    @can_return_tuple
+    @auto_docstring
+    def forward(
+        self,
+        input_ids: Optional[torch.LongTensor] = None,
+        attention_mask: Optional[torch.Tensor] = None,
+        position_ids: Optional[torch.LongTensor] = None,
+        past_key_values: Optional[Cache] = None,
+        inputs_embeds: Optional[torch.FloatTensor] = None,
+        labels: Optional[torch.LongTensor] = None,
+        use_cache: Optional[bool] = None,
+        output_attentions: Optional[bool] = None,
+        output_hidden_states: Optional[bool] = None,
+        cache_position: Optional[torch.LongTensor] = None,
+        logits_to_keep: Union[int, torch.Tensor] = 0,
+        **kwargs: Unpack[KwargsForCausalLM],
+    ) -> CausalLMOutputWithPast:
+ 
+        output_attentions = output_attentions if output_attentions is not None else self.config.output_attentions
+        output_hidden_states = (
+            output_hidden_states if output_hidden_states is not None else self.config.output_hidden_states
+        )
+
+        # decoder outputs consists of (dec_features, layer_state, dec_hidden, dec_attn)
+        outputs: BaseModelOutputWithPast = self.model(
+            input_ids=input_ids,
+            attention_mask=attention_mask,
+            position_ids=position_ids,
+            past_key_values=past_key_values,
+            inputs_embeds=inputs_embeds,
+            use_cache=use_cache,
+            output_attentions=output_attentions,
+            output_hidden_states=output_hidden_states,
+            cache_position=cache_position,
+            **kwargs,
+        )
+
+        hidden_states = outputs.last_hidden_state
+        # Only compute necessary logits, and do not upcast them to float if we are not computing the loss
+        slice_indices = slice(-logits_to_keep, None) if isinstance(logits_to_keep, int) else logits_to_keep
+        logits = self.lm_head(hidden_states[:, slice_indices, :])
+
+        loss = None
+        if labels is not None:
+            loss = self.loss_function(logits=logits, labels=labels, vocab_size=self.config.vocab_size, **kwargs)
+
+        return CausalLMOutputWithPast(
+            loss=loss,
+            logits=logits,
+            past_key_values=outputs.past_key_values,
+            hidden_states=outputs.hidden_states,
+            attentions=outputs.attentions,
+        )
+
+
+__all__ = [
+    "PanguEmbeddedForCausalLM",
+    "PanguEmbeddedModel",
+    "PanguEmbeddedPreTrainedModel",
+]

modular_openpangu_dense.py

@@ -0,0 +1,150 @@
+# coding=utf-8
+# Copyright (c) 2025 Huawei Technologies Co., Ltd. All rights reserved.
+# Copyright 2022 EleutherAI and the HuggingFace Inc. team. All rights reserved.
+#
+# This code is based on EleutherAI's GPT-NeoX library and the GPT-NeoX
+# and OPT implementations in this library. It has been modified from its
+# original forms to accommodate minor architectural differences compared
+# to GPT-NeoX and OPT used by the Meta AI team that trained the model.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+from typing import Callable, Optional, Tuple
+
+import torch
+from torch import nn
+
+try:
+    import torch_npu
+    from torch_npu.contrib import transfer_to_npu
+    if "910" in torch.npu.get_device_name():
+        NPU_ATTN_INFR = True
+        print("[INFO] torch_npu detected. Using NPU fused infer attention.")
+except ImportError:
+    NPU_ATTN_INFR = False
+
+from transformers.cache_utils import Cache
+from transformers.modeling_flash_attention_utils import FlashAttentionKwargs
+from transformers.modeling_utils import ALL_ATTENTION_FUNCTIONS
+from transformers.processing_utils import Unpack
+from transformers.utils import logging
+from transformers.models.llama.modeling_llama import (
+    LlamaAttention,
+    LlamaDecoderLayer,
+    LlamaForCausalLM,
+    LlamaForSequenceClassification,
+    LlamaMLP,
+    LlamaModel,
+    apply_rotary_pos_emb,
+    eager_attention_forward,
+)
+from .configuration_openpangu_dense import PanguEmbeddedConfig
+
+
+logger = logging.get_logger(__name__)
+
+
+class PanguEmbeddedMLP(LlamaMLP):
+    def __init__(self, config):
+        super().__init__(config)
+        self.gate_proj = nn.Linear(self.hidden_size, self.intermediate_size, bias=False)
+        self.up_proj = nn.Linear(self.hidden_size, self.intermediate_size, bias=False)
+        self.down_proj = nn.Linear(self.intermediate_size, self.hidden_size, bias=False)
+
+
+class PanguEmbeddedAttention(LlamaAttention):
+    def __init__(self, config: PanguEmbeddedConfig, layer_idx: int):
+        super().__init__()
+        self.config = config
+        self.layer_idx = layer_idx
+        self.head_dim = getattr(config, "head_dim", config.hidden_size // config.num_attention_heads)
+        self.num_heads = config.num_attention_heads
+        self.num_key_value_heads = config.num_key_value_heads
+        self.num_key_value_groups = config.num_attention_heads // config.num_key_value_heads
+        self.scaling = self.head_dim**-0.5
+        self.attention_dropout = config.attention_dropout
+        self.is_causal = True
+
+        self.q_proj = nn.Linear(config.hidden_size, config.num_attention_heads * self.head_dim, bias=config.bias)
+        self.k_proj = nn.Linear(config.hidden_size, config.num_key_value_heads * self.head_dim, bias=config.bias)
+        self.v_proj = nn.Linear(config.hidden_size, config.num_key_value_heads * self.head_dim, bias=config.bias)
+        self.o_proj = nn.Linear(config.num_attention_heads * self.head_dim, config.hidden_size, bias=config.bias)
+
+    def forward(
+        self,
+        hidden_states: torch.Tensor,
+        position_embeddings: tuple[torch.Tensor, torch.Tensor],
+        attention_mask: Optional[torch.Tensor],
+        past_key_value: Optional[Cache] = None,
+        cache_position: Optional[torch.LongTensor] = None,
+        **kwargs: Unpack[FlashAttentionKwargs],
+    ) -> tuple[torch.Tensor, Optional[torch.Tensor], Optional[tuple[torch.Tensor]]]:
+        input_shape = hidden_states.shape[:-1]
+        hidden_shape = (*input_shape, -1, self.head_dim)
+
+        query_states = self.q_proj(hidden_states).view(hidden_shape).transpose(1, 2)
+        key_states = self.k_proj(hidden_states).view(hidden_shape).transpose(1, 2)
+        value_states = self.v_proj(hidden_states).view(hidden_shape).transpose(1, 2)
+
+        cos, sin = position_embeddings
+        query_states, key_states = apply_rotary_pos_emb(query_states, key_states, cos, sin)
+
+        if past_key_value is not None:
+            # sin and cos are specific to RoPE models; cache_position needed for the static cache
+            cache_kwargs = {"sin": sin, "cos": cos, "cache_position": cache_position}
+            key_states, value_states = past_key_value.update(key_states, value_states, self.layer_idx, cache_kwargs)
+
+        attention_interface: Callable = eager_attention_forward
+        if self.config._attn_implementation != "eager":
+            attention_interface = ALL_ATTENTION_FUNCTIONS[self.config._attn_implementation]
+        
+        if not self.training and NPU_ATTN_INFR:
+            q_len = input_shape[1]
+            if attention_mask is not None:
+                attention_mask = ~attention_mask.bool()
+            elif q_len > 1:
+                attention_mask = torch.triu(torch.ones([q_len, q_len]), diagonal=1).bool().unsqueeze(0).unsqueeze(0).to(query_states.device)
+
+            attn_output, _ = torch_npu.npu_fused_infer_attention_score(
+                query_states, key_states, value_states,
+                num_heads=self.num_heads, num_key_value_heads=self.num_key_value_heads,
+                input_layout="BNSD", atten_mask=attention_mask, scale=self.scaling)
+            attn_output = attn_output.transpose(1, 2)
+            attn_weights = None
+        else:
+            attn_output, attn_weights = attention_interface(
+                self,
+                query_states,
+                key_states,
+                value_states,
+                attention_mask,
+                dropout=0.0 if not self.training else self.attention_dropout,
+                scaling=self.scaling,
+                **kwargs,
+            )
+
+        attn_output = attn_output.reshape(*input_shape, -1).contiguous()
+        attn_output = self.o_proj(attn_output)
+        return attn_output, attn_weights
+            
+
+class PanguEmbeddedDecoderLayer(LlamaDecoderLayer):
+    pass
+    
+
+class PanguEmbeddedModel(LlamaModel):
+    pass
+
+
+class PanguEmbeddedForCausalLM(LlamaForCausalLM):
+    pass

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "[unused10]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenization_openpangu.py

@@ -0,0 +1,273 @@
+# coding=utf-8
+# Copyright (c) 2025 Huawei Technologies Co., Ltd. All rights reserved.
+# Copyright 2022 EleutherAI and the HuggingFace Inc. team. All rights reserved.
+#
+# This code is based on EleutherAI's GPT-NeoX library and the GPT-NeoX
+# and OPT implementations in this library. It has been modified from its
+# original forms to accommodate minor architectural differences compared
+# to GPT-NeoX and OPT used by the Meta AI team that trained the model.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+import os
+from shutil import copyfile
+from typing import Any, Dict, List, Optional, Tuple
+
+import sentencepiece as spm
+
+from transformers.tokenization_utils import PreTrainedTokenizer
+from transformers.utils import logging
+
+
+logger = logging.get_logger(__name__)
+
+VOCAB_FILES_NAMES = {"vocab_file": "./tokenizer.model"}
+
+PRETRAINED_VOCAB_FILES_MAP = {}
+
+
+def convert_bool(string):
+    if isinstance(string, str):
+        if string.lower() == "true":
+            return True
+        elif string.lower() == "false":
+            return False
+        else:
+            return string
+    else:
+        return string
+
+
+class PanguTokenizer(PreTrainedTokenizer):
+    """
+    Construct a  tokenizer. Based on byte-level Byte-Pair-Encoding.
+
+    Args:
+        vocab_file (`str`):
+            Path to the vocabulary file.
+    """
+
+    vocab_files_names = VOCAB_FILES_NAMES
+    pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP
+    model_input_names = ["input_ids", "attention_mask"]
+    _auto_class = "AutoTokenizer"
+
+    def __init__(
+        self,
+        vocab_file,
+        unk_token="<unk>",
+        bos_token="<s>",
+        eos_token="</s>",
+        pad_token="</s>",
+        sp_model_kwargs: Optional[Dict[str, Any]] = None,
+        add_bos_token=True,
+        add_eos_token=False,
+        decode_with_prefix_space=False,
+        clean_up_tokenization_spaces=False,
+        **kwargs,
+    ):
+        self.sp_model_kwargs = {} if sp_model_kwargs is None else sp_model_kwargs
+        self.sp_model = spm.SentencePieceProcessor(**self.sp_model_kwargs)
+        self.sp_model.Load(vocab_file)
+        super().__init__(
+            bos_token=bos_token,
+            eos_token=eos_token,
+            unk_token=unk_token,
+            pad_token=pad_token,
+            clean_up_tokenization_spaces=clean_up_tokenization_spaces,
+            **kwargs,
+        )
+        self.vocab_file = vocab_file
+        self.add_bos_token = convert_bool(add_bos_token)
+        self.add_eos_token = add_eos_token
+        self.decode_with_prefix_space = decode_with_prefix_space
+        self.sp_model = spm.SentencePieceProcessor(**self.sp_model_kwargs)
+        self.sp_model.Load(vocab_file)
+        self._no_prefix_space_tokens = None
+
+        """ Initialisation"""
+
+    @property
+    def no_prefix_space_tokens(self):
+        if self._no_prefix_space_tokens is None:
+            vocab = self.convert_ids_to_tokens(list(range(self.vocab_size)))
+            self._no_prefix_space_tokens = {i for i, tok in enumerate(vocab) if not tok.startswith("▁")}
+        return self._no_prefix_space_tokens
+
+    @property
+    def vocab_size(self):
+        """Returns vocab size"""
+        return self.sp_model.get_piece_size()
+
+    @property
+    def bos_token_id(self) -> Optional[int]:
+        return self.sp_model.bos_id()
+
+    @property
+    def eos_token_id(self) -> Optional[int]:
+        return super().eos_token_id
+
+    def get_vocab(self):
+        """Returns vocab as a dict"""
+        vocab = {self.convert_ids_to_tokens(i): i for i in range(self.vocab_size)}
+        vocab.update(self.added_tokens_encoder)
+        return vocab
+
+    def _tokenize(self, text):
+        """Returns a tokenized string."""
+        return self.sp_model.encode(text, out_type=str)
+
+    def _convert_token_to_id(self, token):
+        """Converts a token (str) in an id using the vocab."""
+        return self.sp_model.piece_to_id(token)
+
+    def _convert_id_to_token(self, index):
+        """Converts an index (integer) in a token (str) using the vocab."""
+        token = self.sp_model.IdToPiece(index)
+        return token
+
+    def _maybe_add_prefix_space(self, tokens, decoded):
+        if tokens and tokens[0] not in self.no_prefix_space_tokens:
+            return " " + decoded
+        else:
+            return decoded
+
+    def convert_tokens_to_string(self, tokens):
+        """Converts a sequence of tokens (string) in a single string."""
+        current_sub_tokens = []
+        out_string = ""
+        prev_is_special = False
+        for token in tokens:
+            # make sure that special tokens are not decoded using sentencepiece model
+            if token in self.all_special_tokens:
+                # Decode the current sub-tokens first
+                if current_sub_tokens:
+                    out_string += self.sp_model.decode(current_sub_tokens)
+                    current_sub_tokens = []
+                # Append the special token without adding extra spaces
+                out_string += token
+                prev_is_special = True
+            else:
+                current_sub_tokens.append(token)
+                prev_is_special = False
+        # Decode any remaining sub-tokens
+        if current_sub_tokens:
+            out_string += self.sp_model.decode(current_sub_tokens)
+        # Clean up leading and trailing spaces
+        if self.clean_up_tokenization_spaces:
+            out_string = self.clean_up_tokenization(out_string)
+        out_string = self._maybe_add_prefix_space(tokens=tokens, decoded=out_string)
+        return out_string[1:]
+
+    # Override decode to set spaces_between_special_tokens to True as default 
+    def decode(self,
+               token_ids,
+               spaces_between_special_tokens: bool = False,
+               **kwargs):
+        return super().decode(
+            token_ids=token_ids,
+            spaces_between_special_tokens=spaces_between_special_tokens,
+            **kwargs,
+        )
+
+    def save_vocabulary(self, save_directory, filename_prefix: Optional[str] = None) -> Tuple[str]:
+        """
+        Save the vocabulary and special tokens file to a directory.
+
+        Args:
+            save_directory (`str`):
+                The directory in which to save the vocabulary.
+
+        Returns:
+            `Tuple(str)`: Paths to the files saved.
+        """
+        if not os.path.isdir(save_directory):
+            logger.error(f"Vocabulary path ({save_directory}) should be a directory")
+            return ("",)
+        out_vocab_file = os.path.join(
+            save_directory, (filename_prefix + "-" if filename_prefix else "") + VOCAB_FILES_NAMES["vocab_file"]
+        )
+
+        if os.path.abspath(self.vocab_file) != os.path.abspath(out_vocab_file) and os.path.isfile(self.vocab_file):
+            copyfile(self.vocab_file, out_vocab_file)
+        elif not os.path.isfile(self.vocab_file):
+            with open(out_vocab_file, "wb") as fi:
+                content_spiece_model = self.sp_model.serialized_model_proto()
+                fi.write(content_spiece_model)
+
+        return (out_vocab_file,)
+
+    def build_inputs_with_special_tokens(self, token_ids_0, token_ids_1=None):
+        if self.add_bos_token:
+            bos_token_ids = [self.bos_token_id]
+        else:
+            bos_token_ids = []
+
+        output = bos_token_ids + token_ids_0
+
+        if token_ids_1 is not None:
+            output = output + token_ids_1
+
+        if self.add_eos_token:
+            output = output + [self.eos_token_id]
+
+        return output
+
+    def get_special_tokens_mask(
+        self, token_ids_0: List[int], token_ids_1: Optional[List[int]] = None, already_has_special_tokens: bool = False
+    ) -> List[int]:
+        """
+        Retrieve sequence ids from a token list that has no special tokens added. This method is called when adding
+        special tokens using the tokenizer `prepare_for_model` method.
+
+        Args:
+            token_ids_0 (`List[int]`):
+                List of IDs.
+            token_ids_1 (`List[int]`, *optional*):
+                Optional second list of IDs for sequence pairs.
+            already_has_special_tokens (`bool`, *optional*, defaults to `False`):
+                Whether or not the token list is already formatted with special tokens for the model.
+
+        Returns:
+            `List[int]`: A list of integers in the range [0, 1]: 1 for a special token, 0 for a sequence token.
+        """
+        if already_has_special_tokens:
+            return super().get_special_tokens_mask(
+                token_ids_0=token_ids_0, token_ids_1=token_ids_1, already_has_special_tokens=True
+            )
+
+        if token_ids_1 is None:
+            return [1] + ([0] * len(token_ids_0)) + [1]
+        return [1] + ([0] * len(token_ids_0)) + [1, 1] + ([0] * len(token_ids_1)) + [1]
+
+    def create_token_type_ids_from_sequences(
+        self, token_ids_0: List[int], token_ids_1: Optional[List[int]] = None
+    ) -> List[int]:
+        """
+        Create a mask from the two sequences passed to be used in a sequence-pair classification task. T5 does not make
+        use of token type ids, therefore a list of zeros is returned.
+
+        Args:
+            token_ids_0 (`List[int]`):
+                List of IDs.
+            token_ids_1 (`List[int]`, *optional*):
+                Optional second list of IDs for sequence pairs.
+
+        Returns:
+            `List[int]`: List of zeros.
+        """
+        eos = [self.eos_token_id]
+
+        if token_ids_1 is None:
+            return len(token_ids_0 + eos) * [0]
+        return len(token_ids_0 + eos + token_ids_1 + eos) * [0]

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b16f1558c0cd4ae6ef1a2c605713be0a514f50e1ce2d2c878979ce988c148ec
+size 2477809

tokenizer_config.json

@@ -0,0 +1 @@
+{"add_bos_token": true, "add_eos_token": false, "add_prefix_space": true, "added_tokens_decoder": {"0": {"content": "<unk>", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true}, "1": {"content": "<s>", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true}, "2": {"content": "</s>", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true}, "45806": {"content": "<|User|>:", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true}, "45813": {"content": "<|Bot|>:", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true}, "45830": {"content": "[unused0]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true}, "45840": {"content": "[unused1]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true}, "45846": {"content": "[unused2]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true}, "45849": {"content": "[unused3]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true}, "45861": {"content": "[unused4]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true}, "45866": {"content": "[unused5]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true}, "45874": {"content": "[unused6]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true}, "45883": {"content": "[unused7]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true}, "45884": {"content": "[unused8]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true}, "45887": {"content": "[unused9]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true}, "45892": {"content": "[unused10]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true}, "45920": {"content": "[unused11]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true}, "45932": {"content": "[unused12]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true}, "45938": {"content": "[unused13]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true}, "45953": {"content": "[unused14]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true}, "45968": {"content": "[unused15]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true}, "45974": {"content": "[unused16]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true}, "45982": {"content": "[unused17]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true}, "45986": {"content": "[unused18]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true}, "46005": {"content": "[unused19]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true}, "46007": {"content": "[unused20]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true}, "46014": {"content": "[unused21]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true}, "46017": {"content": "[unused22]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true}, "46028": {"content": "[unused23]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true}, "46032": {"content": "[unused24]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true}, "46081": {"content": "[unused25]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true}, "46086": {"content": "[unused26]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true}, "46101": {"content": "[unused27]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true}, "46183": {"content": "[unused28]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true}, "46230": {"content": "[unused29]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true}, "46245": {"content": "[unused30]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true}, "46257": {"content": "[unused31]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true}, "144208": {"content": "[unused32]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true}, "144209": {"content": "[unused33]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true}}, "auto_map": {"AutoTokenizer": ["tokenization_openpangu.PanguTokenizer", null]}, "bos_token": "<s>", "clean_up_tokenization_spaces": false, "eos_token": "[unused10]", "legacy": true, "model_max_length": 1000000000000000019884624838656, "pad_token": "<unk>", "sp_model_kwargs": {}, "spaces_between_special_tokens": false, "tokenizer_class": "PanguTokenizer", "unk_token": "<unk>", "use_default_system_prompt": false, "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '[unused9]系统：[unused10]' }}{% endif %}{% if message['role'] == 'system' %}{{ '[unused9]系统：' + message['content'] + '[unused10]' }}{% endif %}{% if message['role'] == 'assistant' %}{{'[unused9]助手：' + message['content'] + '[unused10]'}}{% endif %}{% if message['role'] == 'tool' %}{{'[unused9]工具：' + message['content'] + '[unused10]'}}{% endif %}{% if message['role'] == 'function' %}{{'[unused9]方法：' + message['content'] + '[unused10]'}}{% endif %}{% if message['role'] == 'user' %}{{'[unused9]用户：' + message['content'] + '[unused10]'}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '[unused9]助手：' }}{% endif %}"}