初始化项目，由ModelHub XC社区提供模型

Model: microsoft/phi-1
Source: Original Platform

.gitattributes

@@ -0,0 +1,49 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bin.* filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.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
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack 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
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zstandard filter=lfs diff=lfs merge=lfs -text
+*.tfevents* filter=lfs diff=lfs merge=lfs -text
+*.db* filter=lfs diff=lfs merge=lfs -text
+*.ark* filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.gguf* filter=lfs diff=lfs merge=lfs -text
+*.ggml filter=lfs diff=lfs merge=lfs -text
+*.llamafile* filter=lfs diff=lfs merge=lfs -text
+*.pt2 filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

CODE_OF_CONDUCT.md

@@ -0,0 +1,9 @@
+# Microsoft Open Source Code of Conduct
+
+This project has adopted the [Microsoft Open Source Code of Conduct](https://opensource.microsoft.com/codeofconduct/).
+
+Resources:
+
+- [Microsoft Open Source Code of Conduct](https://opensource.microsoft.com/codeofconduct/)
+- [Microsoft Code of Conduct FAQ](https://opensource.microsoft.com/codeofconduct/faq/)
+- Contact [opencode@microsoft.com](mailto:opencode@microsoft.com) with questions or concerns

LICENSE

@@ -0,0 +1,22 @@
+Microsoft.
+Copyright (c) Microsoft Corporation.
+
+MIT License
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE 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 AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

NOTICE.md

@@ -0,0 +1,38 @@
+NOTICES AND INFORMATION
+Do Not Translate or Localize
+
+This software incorporates material from third parties.
+
+**Component.** https://github.com/Dao-AILab/flash-attention
+
+**Open Source License/Copyright Notice.**
+
+BSD 3-Clause License
+
+Copyright (c) 2022, the respective contributors, as shown by the AUTHORS file.
+All rights reserved.
+
+Redistribution and use in source and binary forms, with or without
+modification, are permitted provided that the following conditions are met:
+
+* Redistributions of source code must retain the above copyright notice, this
+  list of conditions and the following disclaimer.
+
+* Redistributions in binary form must reproduce the above copyright notice,
+  this list of conditions and the following disclaimer in the documentation
+  and/or other materials provided with the distribution.
+
+* Neither the name of the copyright holder nor the names of its
+  contributors may be used to endorse or promote products derived from
+  this software without specific prior written permission.
+
+THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE
+FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
+SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
+CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
+OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.

README.md

@@ -0,0 +1,141 @@
+---
+license: mit
+license_link: https://huggingface.co/microsoft/phi-1/resolve/main/LICENSE
+language:
+  - en
+pipeline_tag: text-generation
+tags:
+- code
+---
+
+## Model Summary
+
+The language model Phi-1 is a Transformer with 1.3 billion parameters, specialized for basic Python coding. Its training involved a variety of data sources, including subsets of Python codes from [The Stack v1.2](https://huggingface.co/datasets/bigcode/the-stack), Q&A content from [StackOverflow](https://archive.org/download/stackexchange), competition code from [code_contests](https://github.com/deepmind/code_contests), and synthetic Python textbooks and exercises generated by [gpt-3.5-turbo-0301](https://platform.openai.com/docs/models/gpt-3-5). Even though the model and the datasets are relatively small compared to contemporary Large Language Models (LLMs), Phi-1 has demonstrated an impressive accuracy rate exceeding 50% on the simple Python coding benchmark, HumanEval.
+
+## How to Use
+
+Phi-1 has been integrated in the `transformers` version 4.37.0, please ensure that you are using a version equal or higher than it.
+
+## Intended Uses
+
+Given the nature of the training data, Phi-1 is best suited for prompts using the code format:
+
+### Code Format:
+
+```python
+def print_prime(n):
+   """
+   Print all primes between 1 and n
+   """
+   for num in range(2, n+1):
+       for i in range(2, num):
+           if num % i == 0:
+               break
+       else:
+           print(num)
+```
+
+where the model generates the code after the comments. (Note: This is a legitimate and correct use of the else statement in Python loops.)
+
+**Notes:**
+
+* Phi-1 is intended for code purposes. The model-generated code should be treated as a starting point rather than a definitive solution for potential use cases. Users should be cautious when employing this model in their applications.
+
+* Direct adoption for production coding tasks is out of the scope of this research project. As a result, Phi-1 has not been tested to ensure that it performs adequately for production-level code. Please refer to the limitation sections of this document for more details.
+
+## Sample Code
+
+```python
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+torch.set_default_device("cuda")
+
+model = AutoModelForCausalLM.from_pretrained("microsoft/phi-1", torch_dtype="auto")
+tokenizer = AutoTokenizer.from_pretrained("microsoft/phi-1")
+
+inputs = tokenizer('''def print_prime(n):
+   """
+   Print all primes between 1 and n
+   """''', return_tensors="pt", return_attention_mask=False)
+
+outputs = model.generate(**inputs, max_length=200)
+text = tokenizer.batch_decode(outputs)[0]
+print(text)
+```
+
+## Limitations of Phi-1
+
+* Limited Scope: 99.8% of the Python scripts in our fine-tuning dataset use only the packages "typing, math, random, collections, datetime, itertools". If the model generates Python scripts that utilize other packages, we strongly recommend users manually verify all API uses.
+
+* Replicate Scripts Online: As our model is trained on Python scripts found online, there is a small chance it may replicate such scripts, especially if they appear repetitively across different online sources.
+
+* Generate Inaccurate Code: The model frequently generates incorrect code. We suggest that users view these outputs as a source of inspiration rather than definitive solutions.
+
+* Unreliable Responses to Alternate Formats: Despite appearing to comprehend instructions in formats like Q&A or chat, our models often respond with inaccurate answers, even when seeming confident. Their capabilities with non-code formats are significantly more limited.
+
+* Limitations on Natural Language Comprehension. As a coding bot, Phi-1's main focus is to help with coding-related questions. While it may have some natural language comprehension capabilities, its primary function is not to engage in general conversations or demonstrate common sense like a general AI assistant. Its strength lies in providing assistance and guidance in the context of programming and software development.
+
+* Potential Biases: Phi-1, like other AI models, is trained on web and synthetic data. This data can contain biases and errors that might affect the AI's performance. Biases could stem from various sources like unbalanced representation, stereotypes, or controversial opinions present in the training data. As a result, the model might sometimes generate responses that reflect these biases or errors. 
+
+## Warning about Security Risks
+
+When leveraging Phi-1, it's paramount to be vigilant. The model, though powerful, can inadvertently introduce security vulnerabilities in the generated code. Examples include, but are not limited to:
+
+* Directory Traversal: The code might fail to implement safe checks against directory traversal attacks, potentially allowing unauthorized access to sensitive files on your system.
+
+* Injection Attacks: There could be lapses in escaping strings properly, making the application susceptible to SQL, OS commands, or other injection attacks.
+
+* Misunderstanding Requirements: The model might sometimes misunderstand or oversimplify user requirements, leading to incomplete or insecure solutions.
+
+* Lack of Input Validation: In some cases, the model might neglect to incorporate input validation or sanitize user inputs, opening doors to attacks like Cross-Site Scripting (XSS).
+
+* Insecure Defaults: The model might recommend or generate code with insecure default settings, such as weak password requirements or unencrypted data transmissions.
+
+* Failure in Error Handling: Improper error handling can inadvertently reveal sensitive information about the system or the application's internal workings.
+
+Given these potential pitfalls, and others not explicitly mentioned, it's essential to thoroughly review, test, and verify the generated code before deploying it in any application, especially those that are security-sensitive. Always consult with security experts or perform rigorous penetration testing when in doubt.
+
+## Training
+
+### Model
+
+* Architecture: a Transformer-based model with next-word prediction objective
+
+* Training tokens: 54B tokens (7B unique tokens)
+
+* Precision: fp16
+
+* GPUs: 8 A100
+
+* Training time: 6 days
+
+### Software
+
+* [PyTorch](https://github.com/pytorch/pytorch)
+
+* [DeepSpeed](https://github.com/microsoft/DeepSpeed)
+
+* [Flash-Attention](https://github.com/HazyResearch/flash-attention)
+
+### License
+
+The model is licensed under the [MIT license](https://huggingface.co/microsoft/phi-1/resolve/main/LICENSE).
+
+### Citation
+
+```bib
+@article{gunasekar2023textbooks,
+  title={Textbooks Are All You Need},
+  author={Gunasekar, Suriya and Zhang, Yi and Aneja, Jyoti and Mendes, Caio C{\'e}sar Teodoro and Del Giorno, Allie and Gopi, Sivakanth and Javaheripi, Mojan and Kauffmann, Piero and de Rosa, Gustavo and Saarikivi, Olli and others},
+  journal={arXiv preprint arXiv:2306.11644},
+  year={2023}
+}
+```
+
+## Trademarks
+
+This project may contain trademarks or logos for projects, products, or services. Authorized use of Microsoft trademarks or logos is subject to and must follow [Microsoft’s Trademark & Brand Guidelines](https://www.microsoft.com/en-us/legal/intellectualproperty/trademarks). Use of Microsoft trademarks or logos in modified versions of this project must not cause confusion or imply Microsoft sponsorship. Any use of third-party trademarks or logos are subject to those third-party’s policies.
+
+## Data Summary 
+https://huggingface.co/microsoft/phi-1/blob/main/data_summary_card.md

SECURITY.md

@@ -0,0 +1,41 @@
+<!-- BEGIN MICROSOFT SECURITY.MD V0.0.9 BLOCK -->
+
+## Security
+
+Microsoft takes the security of our software products and services seriously, which includes all source code repositories managed through our GitHub organizations, which include [Microsoft](https://github.com/Microsoft), [Azure](https://github.com/Azure), [DotNet](https://github.com/dotnet), [AspNet](https://github.com/aspnet) and [Xamarin](https://github.com/xamarin).
+
+If you believe you have found a security vulnerability in any Microsoft-owned repository that meets [Microsoft's definition of a security vulnerability](https://aka.ms/security.md/definition), please report it to us as described below.
+
+## Reporting Security Issues
+
+**Please do not report security vulnerabilities through public GitHub issues.**
+
+Instead, please report them to the Microsoft Security Response Center (MSRC) at [https://msrc.microsoft.com/create-report](https://aka.ms/security.md/msrc/create-report).
+
+If you prefer to submit without logging in, send email to [secure@microsoft.com](mailto:secure@microsoft.com).  If possible, encrypt your message with our PGP key; please download it from the [Microsoft Security Response Center PGP Key page](https://aka.ms/security.md/msrc/pgp).
+
+You should receive a response within 24 hours. If for some reason you do not, please follow up via email to ensure we received your original message. Additional information can be found at [microsoft.com/msrc](https://www.microsoft.com/msrc). 
+
+Please include the requested information listed below (as much as you can provide) to help us better understand the nature and scope of the possible issue:
+
+  * Type of issue (e.g. buffer overflow, SQL injection, cross-site scripting, etc.)
+  * Full paths of source file(s) related to the manifestation of the issue
+  * The location of the affected source code (tag/branch/commit or direct URL)
+  * Any special configuration required to reproduce the issue
+  * Step-by-step instructions to reproduce the issue
+  * Proof-of-concept or exploit code (if possible)
+  * Impact of the issue, including how an attacker might exploit the issue
+
+This information will help us triage your report more quickly.
+
+If you are reporting for a bug bounty, more complete reports can contribute to a higher bounty award. Please visit our [Microsoft Bug Bounty Program](https://aka.ms/security.md/msrc/bounty) page for more details about our active programs.
+
+## Preferred Languages
+
+We prefer all communications to be in English.
+
+## Policy
+
+Microsoft follows the principle of [Coordinated Vulnerability Disclosure](https://aka.ms/security.md/cvd).
+
+<!-- END MICROSOFT SECURITY.MD BLOCK -->

added_tokens.json

@@ -0,0 +1,40 @@
+{
+  "\t\t": 50294,
+  "\t\t\t": 50293,
+  "\t\t\t\t": 50292,
+  "\t\t\t\t\t": 50291,
+  "\t\t\t\t\t\t": 50290,
+  "\t\t\t\t\t\t\t": 50289,
+  "\t\t\t\t\t\t\t\t": 50288,
+  "\t\t\t\t\t\t\t\t\t": 50287,
+  "  ": 50286,
+  "   ": 50285,
+  "    ": 50284,
+  "     ": 50283,
+  "      ": 50282,
+  "       ": 50281,
+  "        ": 50280,
+  "         ": 50279,
+  "          ": 50278,
+  "           ": 50277,
+  "            ": 50276,
+  "             ": 50275,
+  "              ": 50274,
+  "               ": 50273,
+  "                ": 50272,
+  "                 ": 50271,
+  "                  ": 50270,
+  "                   ": 50269,
+  "                    ": 50268,
+  "                     ": 50267,
+  "                      ": 50266,
+  "                       ": 50265,
+  "                        ": 50264,
+  "                         ": 50263,
+  "                          ": 50262,
+  "                           ": 50261,
+  "                            ": 50260,
+  "                             ": 50259,
+  "                              ": 50258,
+  "                               ": 50257
+}

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "microsoft/phi-1",
+  "architectures": [
+    "PhiForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": null,
+  "embd_pdrop": 0.0,
+  "eos_token_id": null,
+  "hidden_act": "gelu_new",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 2048,
+  "model_type": "phi",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": null,
+  "partial_rotary_factor": 0.5,
+  "qk_layernorm": false,
+  "resid_pdrop": 0.0,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.37.0",
+  "use_cache": true,
+  "vocab_size": 51200
+}

configuration.json

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

data_summary_card.md

@@ -0,0 +1,149 @@
+ 
+
+# Data Summary for microsoft_phi-1 
+
+ 
+
+ 
+
+## 1. General information 
+
+**1.0.1 Version of the Summary:** 1.0 
+
+ 
+
+**1.0.2 Last update:** 21-Nov-2025 
+
+ 
+
+## 1.1 Model Developer Identification 
+
+**1.1.1 Model Developer name and contact details:** Microsoft Corporation at One Microsoft Way, Redmond, WA 98052. Tel: 425-882-8080 
+
+ 
+
+## 1.2 Model Identification 
+
+**1.2.1 Versioned model name(s):** phi-1 
+
+ 
+
+**1.2.2 Model release date:** 10-Sep-2023 
+
+ 
+
+## 1.3 Overall training data size and characteristics 
+
+### 1.3.1 Size of dataset and characteristics 
+
+**1.3.1.A Text training data size:** 1 billion to 1 trillion tokens 
+
+ 
+
+ 
+
+**1.3.1.B Text training data content:** Variety of data sources, including subsets of Python codes from The Stack v1.2, Q&A content from StackOverflow, competition code from code_contests, and synthetic Python textbooks and exercises generated by gpt-3.5-turbo-0301. 
+
+ 
+
+**1.3.1.C Image training data size:** Not applicable. Images are not part of the training data 
+
+ 
+
+**1.3.1.D Image training data content:** Not applicable 
+
+ 
+
+**1.3.1.E Audio training data size:** Not applicable. Audio data is not part of the training data 
+
+ 
+
+**1.3.1.F Audio training data content:** Not applicable 
+
+ 
+
+**1.3.1.G Video training data size:** Not applicable. Video data is not part of the training data 
+
+ 
+
+**1.3.1.H Video training data content:** Not applicable 
+
+ 
+
+**1.3.1.I Other training data size:** Not applicable 
+
+ 
+
+**1.3.1.J Other training data content:** Not applicable 
+
+ 
+
+**1.3.2 Latest date of data acquisition/collection for model training:** 31-Aug-2023 
+
+ 
+
+**1.3.3 Is data collection ongoing to update the model with new data collection after deployment?** No 
+
+ 
+
+**1.3.4 Date the training dataset was first used to train the model:** 01-Sep-2023 
+
+ 
+
+**1.3.5 Rationale or purpose of data selection:** Datasets emphasize clear, self-contained, instructive, and balanced coding examples to teach basic Python reasoning and algorithmic skills. A filtered subset of The Stack and StackOverflow was combined with diverse synthetic textbooks and exercises to improve learning efficiency and performance on code-generation tasks 
+
+ 
+
+## 2. List of data sources 
+
+### 2.1 Publicly available datasets 
+
+**2.1.1 Have you used publicly available datasets to train the model?** Yes 
+
+ 
+
+## 2.2 Private non-publicly available datasets obtained from third parties 
+
+### 2.2.1 Datasets commercially licensed by rights holders or their representatives 
+
+**2.2.1.A Have you concluded transactional commercial licensing agreement(s) with rights holder(s) or with their representatives?** No 
+
+ 
+
+### 2.2.2 Private datasets obtained from other third-parties 
+
+**2.2.2.A Have you obtained private datasets from third parties that are not licensed as described in Section 2.2.1, such as data obtained from providers of private databases, or data intermediaries?** No 
+
+ 
+
+## 2.3 Personal Information 
+
+**2.3.1 Was personal data used to train the model?** Microsoft follows all relevant laws and regulations pertaining to personal information 
+
+ 
+
+## 2.4 Synthetic data 
+
+**2.4.1 Was any synthetic AI-generated data used to train the model?** Yes 
+
+ 
+
+## 3. Data processing aspects 
+
+### 3.1 Respect of reservation of rights from text and data mining exception or limitation 
+
+**3.1.1 Does this dataset include any data protected by copyright, trademark, or patent?** Microsoft follows all required regulations and laws for processing data protected by copyright, trademark, or patent 
+
+ 
+
+## 3.2 Other information 
+
+**3.2.1 Does the dataset include information about consumer groups without revealing individual consumer identities?** Microsoft follows all required regulations and laws for protecting consumer identities 
+
+ 
+
+**3.2.2 Was the dataset cleaned or modified before model training?** Yes 
+
+ 
+
+ 

generation_config.json

@@ -0,0 +1,4 @@
+{
+  "_from_model_config": true,
+  "transformers_version": "4.37.0.dev0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04edc8656c418161222bc706d4f3524ef628e61cbb473b6a2451683e2cd1d8b7
+size 2836578696

special_tokens_map.json

@@ -0,0 +1,5 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:337da36be7a71a6e88aa9148967a7bc8736f4b47c7de8e19ba92b89e80734cfc
+size 2114924

tokenizer_config.json

@@ -0,0 +1,9 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 2048,
+  "tokenizer_class": "CodeGenTokenizer",
+  "unk_token": "<|endoftext|>"
+}