.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

1/model.py

@@ -1,252 +0,0 @@
-"""
-[Transformer-LLM 백엔드 가이드]
-
-본 파일은 NVIDIA Triton Server에서 Hugging Face `AutoModelForCausalLM` 기반 모델을 손쉽게 배포하기 위해 제공되는 커스텀 Python 백엔드 템플릿입니다.
-
-1. 모델 호환성
-   - Hugging Face의 `AutoModelForCausalLM` 클래스와 호환되는 모든 Causal Language Model을 지원합니다.
-   - [확인] 배포할 모델 `config.json`의 `architectures` 항목이 `...ForCausalLM` 형식인지 확인.
-2. 토크나이저 호환성
-   - `AutoTokenizer`와 호환되는 토크나이저를 지원하며, 모델과 동일한 경로에서 자동으로 로드됩니다.
-
-3. 커스터마이징 안내
-   - 본 템플릿은 범용적인 사용을 위해 작성되었습니다.
-   - 특정 모델의 동작 방식이나 예외 처리가 필요한 경우, 이 파일(`model.py`)과 설정 파일(`config.pbtxt`)을 직접 수정하여 사용하시기 바랍니다.
-"""
-
-import json
-import torch
-import numpy as np
-import triton_python_backend_utils as pb_utils
-import uuid
-from typing import List, Dict, Any, Union, Tuple
-
-from transformers import (
-    AutoModelForCausalLM,
-    AutoTokenizer,
-    GenerationConfig,
-    BitsAndBytesConfig,
-)
-from peft import PeftModel, PeftConfig
-
-class TritonPythonModel:
-    def initialize(self, args: Dict[str, str]):
-        """
-        모델 초기화: 설정 로드, 로거 설정, 모델 및 토크나이저 로드
-        """
-        self.logger = pb_utils.Logger
-        self.model_config = json.loads(args["model_config"])
-        self.model_name = args["model_name"]
-
-        # 설정 파라미터 로드
-        self.base_model_path = self._get_config_param("base_model_path")
-        self.is_adapter_model = self._get_config_param("is_adapter_model", "false").lower() == "true"
-        self.adapter_model_path = self._get_config_param("adapter_model_path")
-        self.quantization = self._get_config_param("quantization")
-        self.device = "cuda" if torch.cuda.is_available() else "cpu"
-
-        # 설정 로그 출력
-        self.logger.log_info(f"================ {self.model_name} Setup ================")
-        self.logger.log_info(f"Base Model: {self.base_model_path}")
-        self.logger.log_info(f"Adapter Mode: {self.is_adapter_model} ({self.adapter_model_path})")
-        self.logger.log_info(f"Quantization: {self.quantization}")
-        self.logger.log_info(f"Device: {self.device}")
-
-        self._load_model_and_tokenizer()
-        self.logger.log_info(f"Model initialized successfully.")
-
-    def _load_model_and_tokenizer(self):
-        """모델과 토크나이저를 로드하고 설정합니다."""
-        # 1. Quantization 설정
-        bnb_config = self._get_bnb_config()
-
-        # 2. Base Model 로드
-        load_path = self.base_model_path
-        if self.is_adapter_model:
-            peft_config = PeftConfig.from_pretrained(self.adapter_model_path)
-            load_path = peft_config.base_model_name_or_path
-
-        try:
-            self.model = AutoModelForCausalLM.from_pretrained(
-                load_path,
-                torch_dtype="auto",
-                quantization_config=bnb_config,
-                device_map="auto",
-                local_files_only=True,
-                trust_remote_code=True
-            )
-        except Exception as e:
-            self.logger.log_error(f"Failed to load base model: {e}")
-            raise e
-
-        # 3. Adapter 병합 (필요 시)
-        if self.is_adapter_model:
-            self.model = PeftModel.from_pretrained(self.model, self.adapter_model_path)
-
-        self.model.eval()
-
-        # 4. Tokenizer 로드
-        self.tokenizer = AutoTokenizer.from_pretrained(load_path, trust_remote_code=True)
-
-        if self.tokenizer.pad_token is None:
-            self.tokenizer.pad_token = self.tokenizer.eos_token
-            self.tokenizer.pad_token_id = self.tokenizer.eos_token_id
-            self.logger.log_info("Pad token was None. Set to EOS token.")
-
-        self.supports_chat_template = (
-            hasattr(self.tokenizer, "chat_template") and
-            self.tokenizer.chat_template is not None
-        )
-
-        self.logger.log_info(f"Supports Chat Template: {self.supports_chat_template}")
-        if self.supports_chat_template:
-            self.logger.log_info(f"Chat Template Content:\n{self.tokenizer.chat_template}")
-
-    def _get_bnb_config(self) -> Union[BitsAndBytesConfig, None]:
-        if self.quantization == "int4":
-            return BitsAndBytesConfig(
-                load_in_4bit=True,
-                bnb_4bit_use_double_quant=True,
-                bnb_4bit_quant_type="nf4",
-                bnb_4bit_compute_dtype=torch.float16
-            )
-        elif self.quantization == "int8":
-            return BitsAndBytesConfig(
-                load_in_8bit=True,
-                llm_int8_threshold=6.0,
-                llm_int8_has_fp16_weight=True
-            )
-        return None
-
-    def execute(self, requests):
-        """Triton Inference Request 처리 메인 루프"""
-        responses = []
-
-        for request in requests:
-            # [ID 생성 로직] - 로그 추적용으로 유지 (Response에는 포함 X)
-            request_id = request.request_id()
-            if not request_id:
-                request_id = str(uuid.uuid4())
-
-            try:
-                # 1. 입력 데이터 파싱
-                input_data, is_chat = self._parse_input(request)
-
-                # [LOGGING] Request ID 포함하여 로그 출력
-                log_input_str = json.dumps(input_data, ensure_ascii=False) if isinstance(input_data, (list, dict)) else str(input_data)
-                self.logger.log_info(f"\n[RID: {request_id}] >>> [{'CHAT' if is_chat else 'TEXT'}][Input]: {log_input_str}")
-
-                # 2. Generation Config 생성
-                gen_config = self._create_generation_config(request)
-
-                # 3. 토크나이징
-                inputs = self._tokenize(input_data, is_chat)
-
-                # 4. 모델 추론 (Generate)
-                output_text = self._generate(inputs, gen_config)
-
-                # [LOGGING] Request ID 포함하여 결과 출력
-                self.logger.log_info(f"\n[RID: {request_id}] <<< [Output]: {output_text}")
-
-                # 5. 응답 생성
-                responses.append(self._create_response(output_text, request_id))
-
-            except Exception as e:
-                self.logger.log_error(f"[RID: {request_id}] Error during execution: {e}")
-                err_tensor = pb_utils.Tensor("text_output", np.array([str(e).encode('utf-8')], dtype=np.bytes_))
-                responses.append(pb_utils.InferenceResponse(output_tensors=[err_tensor]))
-
-        return responses
-
-    def _parse_input(self, request) -> Tuple[Union[str, List[Dict]], bool]:
-        input_text = self._get_input_scalar(request, "text_input")
-        try:
-            conversation = json.loads(input_text)
-            if isinstance(conversation, list):
-                return conversation, True
-        except (json.JSONDecodeError, TypeError):
-            pass
-        return input_text, False
-
-    def _tokenize(self, input_data, is_chat: bool):
-        if self.supports_chat_template and is_chat:
-            return self.tokenizer.apply_chat_template(
-                input_data,
-                tokenize=True,
-                add_generation_prompt=True,
-                return_tensors="pt",
-                return_dict=True
-            ).to(self.device)
-        else:
-            if is_chat:
-                 input_data = str(input_data)
-            return self.tokenizer(input_data, return_tensors="pt").to(self.device)
-
-    def _generate(self, inputs, gen_config: GenerationConfig) -> str:
-        input_ids = inputs["input_ids"]
-        input_len = input_ids.shape[-1]
-
-        with torch.no_grad():
-            outputs = self.model.generate(
-                **inputs,
-                generation_config=gen_config,
-                pad_token_id=self.tokenizer.pad_token_id,
-                eos_token_id=self.tokenizer.eos_token_id
-            )
-
-        generated_tokens = outputs[0][input_len:]
-        decoded_output = self.tokenizer.decode(generated_tokens, skip_special_tokens=True)
-        return decoded_output.strip()
-
-    def _create_generation_config(self, request) -> GenerationConfig:
-        def get_param(name, default=None, cast_type=None):
-            val = self._get_input_scalar(request, name, default)
-            if val is not None and cast_type:
-                return cast_type(val)
-            return val
-
-        return GenerationConfig(
-            max_length=get_param("max_length", 1024, int),
-            max_new_tokens=get_param("max_new_tokens", 256, int),
-            temperature=get_param("temperature", 1.0, float),
-            do_sample=get_param("do_sample", False, bool),
-            top_k=get_param("top_k", 50, int),
-            top_p=get_param("top_p", 1.0, float),
-            repetition_penalty=get_param("repetition_penalty", 1.0, float),
-        )
-
-    def _create_response(self, output_text: str, request_id: str):
-        """생성된 텍스트를 Triton Response 객체로 변환"""
-        output_tensor = pb_utils.Tensor(
-            "text_output",
-            np.array([output_text.encode('utf-8')], dtype=np.bytes_)
-        )
-        return pb_utils.InferenceResponse(output_tensors=[output_tensor])
-
-    def _get_config_param(self, key: str, default: str = None) -> str:
-        params = self.model_config.get('parameters', {})
-        if key in params:
-            return params[key].get('string_value', default)
-        return default
-
-    def _get_input_scalar(self, request, name: str, default=None):
-        tensor = pb_utils.get_input_tensor_by_name(request, name)
-        if tensor is None:
-            return default
-        return self._np_decoder(tensor.as_numpy()[0])
-
-    def _np_decoder(self, obj):
-        if isinstance(obj, bytes):
-           return obj.decode('utf-8')
-        if np.issubdtype(obj, np.integer):
-           return int(obj)
-        if np.issubdtype(obj, np.floating):
-           return round(float(obj), 3)
-        if isinstance(obj, np.bool_):
-           return bool(obj)
-
-    def finalize(self):
-        self.logger.log_info(f"Finalizing model {self.model_name}")
-        self.model = None
-        self.tokenizer = None
-        torch.cuda.empty_cache()

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 +1,161 @@
+---
+license: mit
+license_link: https://huggingface.co/microsoft/phi-1_5/resolve/main/LICENSE
+language:
+- en
+pipeline_tag: text-generation
+tags:
+- nlp
+- code
+---
+## Model Summary
+
+The language model Phi-1.5 is a Transformer with **1.3 billion** parameters. It was trained using the same data sources as [phi-1](https://huggingface.co/microsoft/phi-1), augmented with a new data source that consists of various NLP synthetic texts. When assessed against benchmarks testing common sense, language understanding, and logical reasoning, Phi-1.5 demonstrates a nearly state-of-the-art performance among models with less than 10 billion parameters.
+
+We **did not** fine-tune Phi-1.5 either for **instruction following or through reinforcement learning from human feedback**. The intention behind crafting this open-source model is to provide the research community with a non-restricted small model to explore vital safety challenges, such as reducing toxicity, understanding societal biases, enhancing controllability, and more.
+
+For a safer model release, we exclude generic web-crawl data sources such as common-crawl from the training. This strategy prevents direct exposure to potentially harmful online content, enhancing the model's safety without RLHF. However, the model is still vulnerable to generating harmful content. We hope the model can help the research community to further study the safety of language models.
+
+Phi-1.5 can write poems, draft emails, create stories, summarize texts, write Python code (such as downloading a Hugging Face transformer model), etc.
+
+## How to Use
+
+Phi-1.5 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-1.5 is best suited for prompts using the QA format, the chat format, and the code format. Note that Phi-1.5, being a base model, often produces irrelevant text following the main answer. In the following example, we've truncated the answer for illustrative purposes only.
+
+### QA Format:
+
+```markdown
+Write a detailed analogy between mathematics and a lighthouse.
+
+Answer: Mathematics is like a lighthouse, guiding us through the vast ocean of numbers and calculations. Just as a lighthouse illuminates the darkness, mathematics provides us with a clear path to navigate through complex problems. It helps us make sense of the world around us, just like a lighthouse helps ships find their way home.
+```
+
+where the model generates the text after "Answer:".
+
+### Chat Format:
+
+```markdown
+Alice: I don't know why, I'm struggling to maintain focus while studying. Any suggestions?
+
+Bob: Have you tried using a timer? It can help you stay on track and avoid distractions.
+
+Alice: That's a good idea. I'll give it a try.
+
+Charlie: Another thing that can help is to break up your study sessions into smaller chunks. It's easier to concentrate on one thing at a time.
+
+Alice: That makes sense. I'll try that too.
+
+Bob: And don't forget to take breaks! It's important to give your brain a rest so you can come back to your studies with a fresh perspective.
+
+Alice: Thanks for the advice, guys. I feel more motivated now.
+
+Charlie: No problem, Alice. We're all in this together.
+
+Bob: Yeah, and remember that it's okay to ask for help if you need it. We're here to support each other.
+```
+
+where the model generates the text after the first "Bob:".
+
+### Code Format:
+
+```python
+def print_prime(n):
+   """
+   Print all primes between 1 and n
+   """
+   primes = []
+   for num in range(2, n+1):
+       is_prime = True
+       for i in range(2, int(math.sqrt(num))+1):
+           if num % i == 0:
+               is_prime = False
+               break
+       if is_prime:
+           primes.append(num)
+   print(primes)
+```
+
+where the model generates the text after the comments.
+
+**Notes:**
+
+* Phi-1.5-generated text/code should be treated as a starting point rather than a definitive solution for potential use cases. Users should be cautious when employing these models in their applications.
+
+* Phi-1.5 has not been tested to ensure that it performs adequately for any production-level application. 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_5", torch_dtype="auto")
+tokenizer = AutoTokenizer.from_pretrained("microsoft/phi-1_5")
+
+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-1.5
+
+* Generate Inaccurate Code and Facts: The model often produces incorrect code snippets and statements. Users should treat these outputs as suggestions or starting points, not as definitive or accurate solutions.
+
+* Limited Scope for code: If the model generates Python scripts that utilize uncommon packages or scripts in other languages, we strongly recommend users manually verify all API uses.
+
+* Unreliable Responses to Instruction: The model has not undergone instruction fine-tuning. As a result, it may struggle or fail to adhere to intricate or nuanced instructions provided by users.
+
+* Language Limitations: The model is primarily designed to understand standard English.  Informal English, slang, or any other language outside of English might pose challenges to its comprehension, leading to potential misinterpretations or errors in response.
+
+* Potential Societal Biases: Regardless of the safe data used for its training, the model is not entirely free from societal biases. There's a possibility it may generate content that mirrors these societal biases, particularly if prompted or instructed to do so. We urge users to be aware of this and to exercise caution and critical thinking when interpreting model outputs.
+
+* Toxicity: Despite that the model is trained with carefully selected data, the model can still produce harmful content if explicitly prompted or instructed to do so. We chose to release the model for research purposes only -- We hope to help the open-source community develop the most effective ways to reduce the toxicity of a model directly after pretraining.
+
+## Training
+
+### Model
+
+* Architecture: a Transformer-based model with next-word prediction objective
+* Dataset size: 30B tokens
+* Training tokens: 150B tokens
+* Precision: fp16
+* GPUs: 32xA100-40G
+* Training time: 8 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_5/resolve/main/LICENSE).
+
+### Citation
+
+You can find the paper at https://arxiv.org/abs/2309.05463. Please cite as:
+
+```bib
+@article{textbooks2,
+  title={Textbooks Are All You Need II: \textbf{phi-1.5} technical report},
+  author={Li, Yuanzhi and Bubeck, S{\'e}bastien and Eldan, Ronen and Del Giorno, Allie and Gunasekar, Suriya and Lee, Yin Tat},
+  journal={arXiv preprint arXiv:2309.05463},
+  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.

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_5",
+  "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": "float16",
+  "transformers_version": "4.37.0",
+  "use_cache": true,
+  "vocab_size": 51200
+}

config.pbtxt

@@ -1,131 +0,0 @@
-# Triton Backend for TransformerLLM.
-backend: "python"
-max_batch_size: 0
-
-# Triton should expect as input a single string
-# input of variable length named 'text_input'
-input [
-
-  {
-    name: "text_input"
-    data_type: TYPE_STRING
-    dims: [ 1 ]
-
-
-  },
-  {
-    name: "max_length"
-    data_type: TYPE_INT32
-    dims: [ 1 ]
-
-    optional: true
-
-
-  },
-  {
-    name: "max_new_tokens"
-    data_type: TYPE_INT32
-    dims: [ 1 ]
-
-    optional: true
-
-
-  },
-  {
-    name: "do_sample"
-    data_type: TYPE_BOOL
-    dims: [ 1 ]
-
-    optional: true
-
-
-  },
-  {
-    name: "top_k"
-    data_type: TYPE_INT32
-    dims: [ 1 ]
-
-    optional: true
-
-
-  },
-  {
-    name: "top_p"
-    data_type: TYPE_FP32
-    dims: [ 1 ]
-
-    optional: true
-
-
-  },
-  {
-    name: "temperature"
-    data_type: TYPE_FP32
-    dims: [ 1 ]
-
-    optional: true
-
-
-  },
-  {
-    name: "repetition_penalty"
-    data_type: TYPE_FP32
-    dims: [ 1 ]
-
-    optional: true
-
-
-  },
-  {
-    name: "stream"
-    data_type: TYPE_BOOL
-    dims: [ 1 ]
-
-    optional: true
-
-
-  }
-
-]
-
-
-# Triton should expect to respond with a single string
-# output of variable length named 'text_output'
-output [
-
-  {
-    name: "text_output"
-    data_type: TYPE_STRING
-    dims: [ 1 ]
-
-  }
-
-]
-
-parameters: [
-  {
-    key: "base_model_path",
-    value: {string_value: "/cheetah/input/model/groupuser/phi-1_5"}
-  },
-  {
-    key: "is_adapter_model",
-    value: {string_value: "false"}
-  },
-  {
-    key: "adapter_model_path",
-    value: {string_value: ""}
-  },
-  
-  {
-    key: "quantization",
-    value: {string_value: "none"}
-  }
-]
-
-instance_group [
-  {
-    kind: KIND_AUTO
-    count: 1
-  }
-]
-

generation_config.json

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

special_tokens_map.json

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

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|>"
+}