add attribute file

app.py

@@ -0,0 +1,88 @@
+import os
+import streamlit as st
+from llama_index.core import VectorStoreIndex, SimpleDirectoryReader, Settings
+from llama_index.embeddings.huggingface import HuggingFaceEmbedding
+from llama_index.legacy.callbacks import CallbackManager
+from llama_index.llms.openai_like import OpenAILike
+
+
+# Get API_KEY in Env
+api_key = os.getenv('INTERNLM_API_KEY')
+
+# Create an instance of CallbackManager
+callback_manager = CallbackManager()
+
+api_base_url =  "https://internlm-chat.intern-ai.org.cn/puyu/api/v1/"
+model = "internlm2.5-latest"
+# api_key = " your api_key"
+
+# api_base_url =  "https://api.siliconflow.cn/v1"
+# model = "internlm/internlm2_5-7b-chat"
+# api_key = "请填写 API Key"
+
+llm =OpenAILike(model=model, api_base=api_base_url, api_key=api_key, is_chat_model=True,callback_manager=callback_manager)
+
+
+
+st.set_page_config(page_title="llama_index_demo", page_icon="🦜🔗")
+st.title("llama_index_demo")
+
+# 初始化模型
+@st.cache_resource
+def init_models():
+    embed_model = HuggingFaceEmbedding(
+        model_name="./model/sentence-transformer"
+    )
+    Settings.embed_model = embed_model
+
+    #用初始化llm
+    Settings.llm = llm
+
+    documents = SimpleDirectoryReader("./data").load_data()
+    index = VectorStoreIndex.from_documents(documents)
+    query_engine = index.as_query_engine()
+
+    return query_engine
+
+# 检查是否需要初始化模型
+if 'query_engine' not in st.session_state:
+    st.session_state['query_engine'] = init_models()
+
+def greet2(question):
+    response = st.session_state['query_engine'].query(question)
+    return response
+
+      
+# Store LLM generated responses
+if "messages" not in st.session_state.keys():
+    st.session_state.messages = [{"role": "assistant", "content": "你好，我是你的助手，有什么我可以帮助你的吗？"}]    
+
+    # Display or clear chat messages
+for message in st.session_state.messages:
+    with st.chat_message(message["role"]):
+        st.write(message["content"])
+
+def clear_chat_history():
+    st.session_state.messages = [{"role": "assistant", "content": "你好，我是你的助手，有什么我可以帮助你的吗？"}]
+
+st.sidebar.button('Clear Chat History', on_click=clear_chat_history)
+
+# Function for generating LLaMA2 response
+def generate_llama_index_response(prompt_input):
+    return greet2(prompt_input)
+
+# User-provided prompt
+if prompt := st.chat_input():
+    st.session_state.messages.append({"role": "user", "content": prompt})
+    with st.chat_message("user"):
+        st.write(prompt)
+
+# Gegenerate_llama_index_response last message is not from assistant
+if st.session_state.messages[-1]["role"] != "assistant":
+    with st.chat_message("assistant"):
+        with st.spinner("Thinking..."):
+            response = generate_llama_index_response(prompt)
+            placeholder = st.empty()
+            placeholder.markdown(response)
+    message = {"role": "assistant", "content": response}
+    st.session_state.messages.append(message)

data/README_zh-CN.md

@@ -0,0 +1,304 @@
+<div align="center">
+  <img src="https://github.com/InternLM/lmdeploy/assets/36994684/0cf8d00f-e86b-40ba-9b54-dc8f1bc6c8d8" width="600"/>
+  <br /><br />
+
+[![GitHub Repo stars](https://img.shields.io/github/stars/InternLM/xtuner?style=social)](https://github.com/InternLM/xtuner/stargazers)
+[![license](https://img.shields.io/github/license/InternLM/xtuner.svg)](https://github.com/InternLM/xtuner/blob/main/LICENSE)
+[![PyPI](https://img.shields.io/pypi/v/xtuner)](https://pypi.org/project/xtuner/)
+[![Downloads](https://static.pepy.tech/badge/xtuner)](https://pypi.org/project/xtuner/)
+[![issue resolution](https://img.shields.io/github/issues-closed-raw/InternLM/xtuner)](https://github.com/InternLM/xtuner/issues)
+[![open issues](https://img.shields.io/github/issues-raw/InternLM/xtuner)](https://github.com/InternLM/xtuner/issues)
+
+👋 加入我们：[![Static Badge](https://img.shields.io/badge/-grey?style=social&logo=wechat&label=微信)](https://cdn.vansin.top/internlm/xtuner.jpg)
+[![Static Badge](https://img.shields.io/badge/-grey?style=social&logo=twitter&label=推特)](https://twitter.com/intern_lm)
+[![Static Badge](https://img.shields.io/badge/-grey?style=social&logo=discord&label=Discord)](https://discord.gg/xa29JuW87d)
+
+🔍 探索我们的模型：
+[![Static Badge](https://img.shields.io/badge/-gery?style=social&label=🤗%20Huggingface)](https://huggingface.co/xtuner)
+[![Static Badge](https://img.shields.io/badge/-gery?style=social&label=🤖%20ModelScope)](https://www.modelscope.cn/organization/xtuner)
+[![Static Badge](https://img.shields.io/badge/-gery?style=social&label=🧰%20OpenXLab)](https://openxlab.org.cn/usercenter/xtuner)
+[![Static Badge](https://img.shields.io/badge/-gery?style=social&label=🧠%20WiseModel)](https://www.wisemodel.cn/organization/xtuner)
+
+[English](README.md) | 简体中文
+
+</div>
+
+## 🚀 Speed Benchmark
+
+- XTuner 与 LLaMA-Factory 在 Llama2-7B 模型上的训练效率对比
+
+<div align=center>
+  <img src="https://github.com/InternLM/xtuner/assets/41630003/9c9dfdf4-1efb-4daf-84bf-7c379ae40b8b" style="width:80%">
+</div>
+
+- XTuner 与 LLaMA-Factory 在 Llama2-70B 模型上的训练效率对比
+
+<div align=center>
+  <img src="https://github.com/InternLM/xtuner/assets/41630003/5ba973b8-8885-4b72-b51b-c69fa1583bdd" style="width:80%">
+</div>
+
+## 🎉 更新
+- **\[2024/07\]** 支持 [MiniCPM](xtuner/configs/minicpm/) 模型!
+- **\[2024/07\]** 支持训练 [DPO](https://github.com/InternLM/xtuner/tree/main/xtuner/configs/dpo)， [ORPO](https://github.com/InternLM/xtuner/tree/main/xtuner/configs/orpo) 还有 [Reward Model](https://github.com/InternLM/xtuner/tree/main/xtuner/configs/reward_model) ! 并且能够支持打包数据以及序列并行功能！ 请参考 [文档](https://xtuner.readthedocs.io/zh-cn/latest/dpo/overview.html) 了解更多信息。
+- **\[2024/07\]** 支持 [InternLM 2.5](xtuner/configs/internlm/internlm2_5_chat_7b/) 模型!
+- **\[2024/06\]** 支持 [DeepSeek V2](xtuner/configs/deepseek/deepseek_v2_chat/) models! **训练速度提升一倍！**
+- **\[2024/04\]** 多模态大模型 [LLaVA-Phi-3-mini](https://huggingface.co/xtuner/llava-phi-3-mini-hf) 发布！快速开始请查阅此[文档](xtuner/configs/llava/phi3_mini_4k_instruct_clip_vit_large_p14_336)！
+- **\[2024/04\]** 多模态大模型 [LLaVA-Llama-3-8B](https://huggingface.co/xtuner/llava-llama-3-8b) 和 [LLaVA-Llama-3-8B-v1.1](https://huggingface.co/xtuner/llava-llama-3-8b-v1_1) 发布！快速开始请查阅此[文档](xtuner/configs/llava/llama3_8b_instruct_clip_vit_large_p14_336)！
+- **\[2024/04\]** 支持 [Llama 3](xtuner/configs/llama) 模型！
+- **\[2024/04\]** 支持序列并行训练策略以实现语言模型超长上下文训练！\[[文档](https://github.com/InternLM/xtuner/blob/docs/docs/zh_cn/acceleration/train_extreme_long_sequence.rst)\] \[[速度基准](https://github.com/InternLM/xtuner/blob/docs/docs/zh_cn/acceleration/benchmark.rst)\]
+- **\[2024/02\]** 支持 [Gemma](xtuner/configs/gemma) 模型！
+- **\[2024/02\]** 支持 [Qwen1.5](xtuner/configs/qwen/qwen1_5) 模型！
+- **\[2024/01\]** 支持 [InternLM2](xtuner/configs/internlm) 模型！同时，最新版的多模态大模型 [LLaVA-Internlm2-7B](https://huggingface.co/xtuner/llava-internlm2-7b) / [20B](https://huggingface.co/xtuner/llava-internlm2-20b) 发布，其表现出强大的性能！
+- **\[2024/01\]** 支持 [DeepSeek-MoE](https://huggingface.co/deepseek-ai/deepseek-moe-16b-chat) 模型！20GB 显存即可实现 QLoRA 微调，4x80GB 即可实现全参数微调。快速开始请查阅相关[配置文件](xtuner/configs/deepseek/)！
+- **\[2023/12\]** 🔥 支持多模态模型 VLM（[LLaVA-v1.5](https://github.com/haotian-liu/LLaVA)）预训练和指令微调！快速开始请查阅此[文档](xtuner/configs/llava/README_zh-CN.md)！
+- **\[2023/12\]** 🔥 支持 [Mixtral 8x7B](https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1) 模型！快速开始请查阅此[文档](xtuner/configs/mixtral/README.md)！
+- **\[2023/11\]** 支持 [ChatGLM3-6B](xtuner/configs/chatglm) 模型！
+- **\[2023/10\]** 支持 [MSAgent-Bench](https://modelscope.cn/datasets/damo/MSAgent-Bench) 数据集，并且微调所得大语言模型可应用至 [Lagent](https://github.com/InternLM/lagent) 框架！
+- **\[2023/10\]** 优化数据处理逻辑以兼容 `system` 字段，相关细节请查阅[文档](docs/zh_cn/user_guides/dataset_format.md)！
+- **\[2023/09\]** 支持 [InternLM-20B](xtuner/configs/internlm) 系列模型！
+- **\[2023/09\]** 支持 [Baichuan2](xtuner/configs/baichuan) 系列模型！
+- **\[2023/08\]** XTuner 正式发布！众多微调模型已上传至 [HuggingFace](https://huggingface.co/xtuner)！
+
+## 📖 介绍
+
+XTuner 是一个高效、灵活、全能的轻量化大模型微调工具库。
+
+**高效**
+
+- 支持大语言模型 LLM、多模态图文模型 VLM 的预训练及轻量级微调。XTuner 支持在 8GB 显存下微调 7B 模型，同时也支持多节点跨设备微调更大尺度模型（70B+）。
+- 自动分发高性能算子（如 FlashAttention、Triton kernels 等）以加速训练吞吐。
+- 兼容 [DeepSpeed](https://github.com/microsoft/DeepSpeed) 🚀，轻松应用各种 ZeRO 训练优化策略。
+
+**灵活**
+
+- 支持多种大语言模型，包括但不限于 [InternLM](https://huggingface.co/internlm)、[Mixtral-8x7B](https://huggingface.co/mistralai)、[Llama 2](https://huggingface.co/meta-llama)、[ChatGLM](https://huggingface.co/THUDM)、[Qwen](https://huggingface.co/Qwen)、[Baichuan](https://huggingface.co/baichuan-inc)。
+- 支持多模态图文模型 LLaVA 的预训练与微调。利用 XTuner 训得模型 [LLaVA-InternLM2-20B](https://huggingface.co/xtuner/llava-internlm2-20b) 表现优异。
+- 精心设计的数据管道，兼容任意数据格式，开源数据或自定义数据皆可快速上手。
+- 支持 [QLoRA](http://arxiv.org/abs/2305.14314)、[LoRA](http://arxiv.org/abs/2106.09685)、全量参数微调等多种微调算法，支撑用户根据具体需求作出最优选择。
+
+**全能**
+
+- 支持增量预训练、指令微调与 Agent 微调。
+- 预定义众多开源对话模版，支持与开源或训练所得模型进行对话。
+- 训练所得模型可无缝接入部署工具库 [LMDeploy](https://github.com/InternLM/lmdeploy)、大规模评测工具库 [OpenCompass](https://github.com/open-compass/opencompass) 及 [VLMEvalKit](https://github.com/open-compass/VLMEvalKit)。
+
+## 🔥 支持列表
+
+<table>
+<tbody>
+<tr align="center" valign="middle">
+<td>
+  <b>模型</b>
+</td>
+<td>
+  <b>数据集</b>
+</td>
+<td>
+  <b>数据格式</b>
+</td>
+ <td>
+  <b>微调算法</b>
+</td>
+</tr>
+<tr valign="top">
+<td align="left" valign="top">
+<ul>
+  <li><a href="https://huggingface.co/internlm">InternLM 2 / 2.5</a></li>
+  <li><a href="https://huggingface.co/meta-llama">Llama 2 / 3</a></li>
+  <li><a href="https://huggingface.co/collections/microsoft/phi-3-6626e15e9585a200d2d761e3">Phi-3</a></li>
+  <li><a href="https://huggingface.co/THUDM/chatglm2-6b">ChatGLM2</a></li>
+  <li><a href="https://huggingface.co/THUDM/chatglm3-6b">ChatGLM3</a></li>
+  <li><a href="https://huggingface.co/Qwen/Qwen-7B">Qwen</a></li>
+  <li><a href="https://huggingface.co/baichuan-inc/Baichuan2-7B-Base">Baichuan2</a></li>
+  <li><a href="https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1">Mixtral</a></li>
+  <li><a href="https://huggingface.co/deepseek-ai/DeepSeek-V2-Chat">DeepSeek V2</a></li>
+  <li><a href="https://huggingface.co/google">Gemma</a></li>
+  <li><a href="https://huggingface.co/openbmb">MiniCPM</a></li>
+  <li>...</li>
+</ul>
+</td>
+<td>
+<ul>
+  <li><a href="https://modelscope.cn/datasets/damo/MSAgent-Bench">MSAgent-Bench</a></li>
+  <li><a href="https://huggingface.co/datasets/fnlp/moss-003-sft-data">MOSS-003-SFT</a> 🔧</li>
+  <li><a href="https://huggingface.co/datasets/tatsu-lab/alpaca">Alpaca en</a> / <a href="https://huggingface.co/datasets/silk-road/alpaca-data-gpt4-chinese">zh</a></li>
+  <li><a href="https://huggingface.co/datasets/WizardLM/WizardLM_evol_instruct_V2_196k">WizardLM</a></li>
+  <li><a href="https://huggingface.co/datasets/timdettmers/openassistant-guanaco">oasst1</a></li>
+  <li><a href="https://huggingface.co/datasets/garage-bAInd/Open-Platypus">Open-Platypus</a></li>
+  <li><a href="https://huggingface.co/datasets/HuggingFaceH4/CodeAlpaca_20K">Code Alpaca</a></li>
+  <li><a href="https://huggingface.co/datasets/burkelibbey/colors">Colorist</a> 🎨</li>
+  <li><a href="https://github.com/WangRongsheng/ChatGenTitle">Arxiv GenTitle</a></li>
+  <li><a href="https://github.com/LiuHC0428/LAW-GPT">Chinese Law</a></li>
+  <li><a href="https://huggingface.co/datasets/Open-Orca/OpenOrca">OpenOrca</a></li>
+  <li><a href="https://huggingface.co/datasets/shibing624/medical">Medical Dialogue</a></li>
+  <li>...</li>
+</ul>
+</td>
+<td>
+<ul>
+  <li><a href="docs/zh_cn/user_guides/incremental_pretraining.md">Incremental Pre-training</a> </li>
+  <li><a href="docs/zh_cn/user_guides/single_turn_conversation.md">Single-turn Conversation SFT</a> </li>
+  <li><a href="docs/zh_cn/user_guides/multi_turn_conversation.md">Multi-turn Conversation SFT</a> </li>
+</ul>
+</td>
+<td>
+<ul>
+  <li><a href="http://arxiv.org/abs/2305.14314">QLoRA</a></li>
+  <li><a href="http://arxiv.org/abs/2106.09685">LoRA</a></li>
+  <li>全量参数微调</li>
+  <li><a href="https://arxiv.org/abs/2305.18290">DPO</a></li>
+  <li><a href="https://arxiv.org/abs/2403.07691">ORPO</a></li>
+  <li>Reward Model</a></li>
+</ul>
+</td>
+</tr>
+</tbody>
+</table>
+
+## 🛠️ 快速上手
+
+### 安装
+
+- 推荐使用 conda 先构建一个 Python-3.10 的虚拟环境
+
+  ```bash
+  conda create --name xtuner-env python=3.10 -y
+  conda activate xtuner-env
+  ```
+
+- 通过 pip 安装 XTuner：
+
+  ```shell
+  pip install -U xtuner
+  ```
+
+  亦可集成 DeepSpeed 安装：
+
+  ```shell
+  pip install -U 'xtuner[deepspeed]'
+  ```
+
+- 从源码安装 XTuner：
+
+  ```shell
+  git clone https://github.com/InternLM/xtuner.git
+  cd xtuner
+  pip install -e '.[all]'
+  ```
+
+### 微调
+
+XTuner 支持微调大语言模型。数据集预处理指南请查阅[文档](./docs/zh_cn/user_guides/dataset_prepare.md)。
+
+- **步骤 0**，准备配置文件。XTuner 提供多个开箱即用的配置文件，用户可以通过下列命令查看：
+
+  ```shell
+  xtuner list-cfg
+  ```
+
+  或者，如果所提供的配置文件不能满足使用需求，请导出所提供的配置文件并进行相应更改：
+
+  ```shell
+  xtuner copy-cfg ${CONFIG_NAME} ${SAVE_PATH}
+  vi ${SAVE_PATH}/${CONFIG_NAME}_copy.py
+  ```
+
+- **步骤 1**，开始微调。
+
+  ```shell
+  xtuner train ${CONFIG_NAME_OR_PATH}
+  ```
+
+  例如，我们可以利用 QLoRA 算法在 oasst1 数据集上微调 InternLM2.5-Chat-7B：
+
+  ```shell
+  # 单卡
+  xtuner train internlm2_5_chat_7b_qlora_oasst1_e3 --deepspeed deepspeed_zero2
+  # 多卡
+  (DIST) NPROC_PER_NODE=${GPU_NUM} xtuner train internlm2_5_chat_7b_qlora_oasst1_e3 --deepspeed deepspeed_zero2
+  (SLURM) srun ${SRUN_ARGS} xtuner train internlm2_5_chat_7b_qlora_oasst1_e3 --launcher slurm --deepspeed deepspeed_zero2
+  ```
+
+  - `--deepspeed` 表示使用 [DeepSpeed](https://github.com/microsoft/DeepSpeed) 🚀 来优化训练过程。XTuner 内置了多种策略，包括 ZeRO-1、ZeRO-2、ZeRO-3 等。如果用户期望关闭此功能，请直接移除此参数。
+
+  - 更多示例，请查阅[文档](./docs/zh_cn/user_guides/finetune.md)。
+
+- **步骤 2**，将保存的 PTH 模型（如果使用的DeepSpeed，则将会是一个文件夹）转换为 HuggingFace 模型：
+
+  ```shell
+  xtuner convert pth_to_hf ${CONFIG_NAME_OR_PATH} ${PTH} ${SAVE_PATH}
+  ```
+
+### 对话
+
+XTuner 提供与大语言模型对话的工具。
+
+```shell
+xtuner chat ${NAME_OR_PATH_TO_LLM} --adapter {NAME_OR_PATH_TO_ADAPTER} [optional arguments]
+```
+
+例如：
+
+与 InternLM2.5-Chat-7B 对话：
+
+```shell
+xtuner chat internlm/internlm2-chat-7b --prompt-template internlm2_chat
+```
+
+更多示例，请查阅[文档](./docs/zh_cn/user_guides/chat.md)。
+
+### 部署
+
+- **步骤 0**，将 HuggingFace adapter 合并到大语言模型：
+
+  ```shell
+  xtuner convert merge \
+      ${NAME_OR_PATH_TO_LLM} \
+      ${NAME_OR_PATH_TO_ADAPTER} \
+      ${SAVE_PATH} \
+      --max-shard-size 2GB
+  ```
+
+- **步骤 1**，使用任意推理框架部署微调后的大语言模型，例如 [LMDeploy](https://github.com/InternLM/lmdeploy) 🚀：
+
+  ```shell
+  pip install lmdeploy
+  python -m lmdeploy.pytorch.chat ${NAME_OR_PATH_TO_LLM} \
+      --max_new_tokens 256 \
+      --temperture 0.8 \
+      --top_p 0.95 \
+      --seed 0
+  ```
+
+  🔥 追求速度更快、显存占用更低的推理？欢迎体验 [LMDeploy](https://github.com/InternLM/lmdeploy) 提供的 4-bit 量化！使用指南请见[文档](https://github.com/InternLM/lmdeploy/tree/main#quantization)。
+
+### 评测
+
+- 推荐使用一站式平台 [OpenCompass](https://github.com/InternLM/opencompass) 来评测大语言模型，其目前已涵盖 50+ 数据集的约 30 万条题目。
+
+## 🤝 贡献指南
+
+我们感谢所有的贡献者为改进和提升 XTuner 所作出的努力。请参考[贡献指南](.github/CONTRIBUTING.md)来了解参与项目贡献的相关指引。
+
+## 🎖️ 致谢
+
+- [Llama 2](https://github.com/facebookresearch/llama)
+- [DeepSpeed](https://github.com/microsoft/DeepSpeed)
+- [QLoRA](https://github.com/artidoro/qlora)
+- [LMDeploy](https://github.com/InternLM/lmdeploy)
+- [LLaVA](https://github.com/haotian-liu/LLaVA)
+
+## 🖊️ 引用
+
+```bibtex
+@misc{2023xtuner,
+    title={XTuner: A Toolkit for Efficiently Fine-tuning LLM},
+    author={XTuner Contributors},
+    howpublished = {\url{https://github.com/InternLM/xtuner}},
+    year={2023}
+}
+```
+
+## 开源许可证
+
+该项目采用 [Apache License 2.0 开源许可证](LICENSE)。同时，请遵守所使用的模型与数据集的许可证。

download_hf.py

@@ -0,0 +1,7 @@
+import os
+
+# 设置环境变量
+os.environ['HF_ENDPOINT'] = 'https://hf-mirror.com'
+
+# 下载模型
+os.system('huggingface-cli download --resume-download sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2 --local-dir ./model/sentence-transformer')

model/sentence-transformer/.gitattributes

@@ -0,0 +1,21 @@
+*.bin.* filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tar.gz filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack 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
+pytorch_model.bin filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text
+unigram.json filter=lfs diff=lfs merge=lfs -text
+.git/lfs/objects/8a/01/8a016203ad4fe42aaad6e9329f70e4ea2ea19d4e14e43f1a36ec140233e604ef filter=lfs diff=lfs merge=lfs -text
+model.safetensors filter=lfs diff=lfs merge=lfs -text

model/sentence-transformer/1_Pooling/config.json

@@ -0,0 +1,7 @@
+{
+  "word_embedding_dimension": 384,
+  "pooling_mode_cls_token": false,
+  "pooling_mode_mean_tokens": true,
+  "pooling_mode_max_tokens": false,
+  "pooling_mode_mean_sqrt_len_tokens": false
+}

model/sentence-transformer/README.md

@@ -0,0 +1,164 @@
+---
+language:
+- multilingual
+- ar
+- bg
+- ca
+- cs
+- da
+- de
+- el
+- en
+- es
+- et
+- fa
+- fi
+- fr
+- gl
+- gu
+- he
+- hi
+- hr
+- hu
+- hy
+- id
+- it
+- ja
+- ka
+- ko
+- ku
+- lt
+- lv
+- mk
+- mn
+- mr
+- ms
+- my
+- nb
+- nl
+- pl
+- pt
+- ro
+- ru
+- sk
+- sl
+- sq
+- sr
+- sv
+- th
+- tr
+- uk
+- ur
+- vi
+license: apache-2.0
+library_name: sentence-transformers
+tags:
+- sentence-transformers
+- feature-extraction
+- sentence-similarity
+- transformers
+language_bcp47:
+- fr-ca
+- pt-br
+- zh-cn
+- zh-tw
+pipeline_tag: sentence-similarity
+---
+
+# sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2
+
+This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 384 dimensional dense vector space and can be used for tasks like clustering or semantic search.
+
+
+
+## Usage (Sentence-Transformers)
+
+Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
+
+```
+pip install -U sentence-transformers
+```
+
+Then you can use the model like this:
+
+```python
+from sentence_transformers import SentenceTransformer
+sentences = ["This is an example sentence", "Each sentence is converted"]
+
+model = SentenceTransformer('sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2')
+embeddings = model.encode(sentences)
+print(embeddings)
+```
+
+
+
+## Usage (HuggingFace Transformers)
+Without [sentence-transformers](https://www.SBERT.net), you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings.
+
+```python
+from transformers import AutoTokenizer, AutoModel
+import torch
+
+
+# Mean Pooling - Take attention mask into account for correct averaging
+def mean_pooling(model_output, attention_mask):
+    token_embeddings = model_output[0] #First element of model_output contains all token embeddings
+    input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
+    return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9)
+
+
+# Sentences we want sentence embeddings for
+sentences = ['This is an example sentence', 'Each sentence is converted']
+
+# Load model from HuggingFace Hub
+tokenizer = AutoTokenizer.from_pretrained('sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2')
+model = AutoModel.from_pretrained('sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2')
+
+# Tokenize sentences
+encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')
+
+# Compute token embeddings
+with torch.no_grad():
+    model_output = model(**encoded_input)
+
+# Perform pooling. In this case, max pooling.
+sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask'])
+
+print("Sentence embeddings:")
+print(sentence_embeddings)
+```
+
+
+
+## Evaluation Results
+
+
+
+For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name=sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2)
+
+
+
+## Full Model Architecture
+```
+SentenceTransformer(
+  (0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: BertModel 
+  (1): Pooling({'word_embedding_dimension': 384, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False})
+)
+```
+
+## Citing & Authors
+
+This model was trained by [sentence-transformers](https://www.sbert.net/). 
+        
+If you find this model helpful, feel free to cite our publication [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://arxiv.org/abs/1908.10084):
+```bibtex 
+@inproceedings{reimers-2019-sentence-bert,
+    title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
+    author = "Reimers, Nils and Gurevych, Iryna",
+    booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
+    month = "11",
+    year = "2019",
+    publisher = "Association for Computational Linguistics",
+    url = "http://arxiv.org/abs/1908.10084",
+}
+```

model/sentence-transformer/config.json

@@ -0,0 +1,24 @@
+{
+  "_name_or_path": "old_models/paraphrase-multilingual-MiniLM-L12-v2/0_Transformer",
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 384,
+  "initializer_range": 0.02,
+  "intermediate_size": 1536,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.7.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 250037
+}

model/sentence-transformer/config_sentence_transformers.json

@@ -0,0 +1,7 @@
+{
+  "__version__": {
+    "sentence_transformers": "2.0.0",
+    "transformers": "4.7.0",
+    "pytorch": "1.9.0+cu102"
+  }
+}

model/sentence-transformer/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eaa086f0ffee582aeb45b36e34cdd1fe2d6de2bef61f8a559a1bbc9bd955917b
+size 470641600

model/sentence-transformer/modules.json

@@ -0,0 +1,14 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  }
+]

model/sentence-transformer/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16cc9e54df6e083272378abec2d75dc34d7a48b5276db3ccc050d18de672ac59
+size 470693617

model/sentence-transformer/sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 128,
+  "do_lower_case": false
+}

model/sentence-transformer/sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
+size 5069051

model/sentence-transformer/special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}

model/sentence-transformer/tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22150b6ba00e477c7f816f1988d028fff924e2b52e14540889690c72c5add40e
+size 470899176

model/sentence-transformer/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c3387be76557bd40970cec13153b3bbf80407865484b209e655e5e4729076b8
+size 9081518

model/sentence-transformer/tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": true, "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "tokenize_chinese_chars": true, "strip_accents": null, "bos_token": "<s>", "eos_token": "</s>", "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "old_models/paraphrase-multilingual-MiniLM-L12-v2/0_Transformer"}

model/sentence-transformer/unigram.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71b44701d7efd054205115acfa6ef126c5d2f84bd3affe0c59e48163674d19a6
+size 14763234

requirements.txt

@@ -0,0 +1,132 @@
+aiohappyeyeballs==2.4.3
+aiohttp==3.11.4
+aiosignal==1.3.1
+altair==5.4.1
+annotated-types==0.7.0
+anyio==4.6.2.post1
+async-timeout==5.0.1
+attrs==24.2.0
+beautifulsoup4==4.12.3
+blinker==1.9.0
+cachetools==5.5.0
+certifi==2024.8.30
+charset-normalizer==3.4.0
+click==8.1.7
+dataclasses-json==0.6.7
+Deprecated==1.2.15
+dirtyjson==1.0.8
+distro==1.9.0
+einops==0.7.0
+exceptiongroup==1.2.2
+filelock==3.16.1
+filetype==1.2.0
+frozenlist==1.5.0
+fsspec==2024.10.0
+gitdb==4.0.11
+GitPython==3.1.43
+greenlet==3.1.1
+h11==0.14.0
+httpcore==1.0.7
+httpx==0.27.2
+huggingface-hub==0.26.2
+idna==3.10
+InstructorEmbedding==1.0.1
+Jinja2==3.1.4
+jiter==0.7.1
+joblib==1.4.2
+jsonschema==4.23.0
+jsonschema-specifications==2024.10.1
+llama-cloud==0.1.5
+llama-index==0.11.20
+llama-index-agent-openai==0.3.4
+llama-index-cli==0.3.1
+llama-index-core==0.11.23
+llama-index-embeddings-huggingface==0.3.1
+llama-index-embeddings-instructor==0.2.1
+llama-index-embeddings-openai==0.2.5
+llama-index-indices-managed-llama-cloud==0.6.0
+llama-index-legacy==0.9.48.post4
+llama-index-llms-openai==0.2.16
+llama-index-llms-openai-like==0.2.0
+llama-index-llms-replicate==0.3.0
+llama-index-multi-modal-llms-openai==0.2.3
+llama-index-program-openai==0.2.0
+llama-index-question-gen-openai==0.2.0
+llama-index-readers-file==0.2.2
+llama-index-readers-llama-parse==0.3.0
+llama-parse==0.5.14
+markdown-it-py==3.0.0
+MarkupSafe==3.0.2
+marshmallow==3.23.1
+mdurl==0.1.2
+mpmath==1.3.0
+multidict==6.1.0
+mypy-extensions==1.0.0
+narwhals==1.14.1
+nest-asyncio==1.6.0
+networkx==3.4.2
+nltk==3.9.1
+numpy==1.26.4
+nvidia-cublas-cu12==12.1.3.1
+nvidia-cuda-cupti-cu12==12.1.105
+nvidia-cuda-nvrtc-cu12==12.1.105
+nvidia-cuda-runtime-cu12==12.1.105
+nvidia-cudnn-cu12==9.1.0.70
+nvidia-cufft-cu12==11.0.2.54
+nvidia-curand-cu12==10.3.2.106
+nvidia-cusolver-cu12==11.4.5.107
+nvidia-cusparse-cu12==12.1.0.106
+nvidia-nccl-cu12==2.21.5
+nvidia-nvjitlink-cu12==12.4.127
+nvidia-nvtx-cu12==12.1.105
+openai==1.54.4
+packaging==24.2
+pandas==2.2.3
+pillow==10.4.0
+propcache==0.2.0
+protobuf==5.26.1
+pyarrow==18.0.0
+pydantic==2.9.2
+pydantic_core==2.23.4
+pydeck==0.9.1
+Pygments==2.18.0
+pypdf==4.3.1
+python-dateutil==2.9.0.post0
+pytz==2024.2
+PyYAML==6.0.2
+referencing==0.35.1
+regex==2024.11.6
+requests==2.32.3
+rich==13.9.4
+rpds-py==0.21.0
+safetensors==0.4.5
+scikit-learn==1.5.2
+scipy==1.14.1
+sentence-transformers==2.7.0
+six==1.16.0
+smmap==5.0.1
+sniffio==1.3.1
+soupsieve==2.6
+SQLAlchemy==2.0.36
+streamlit==1.39.0
+striprtf==0.0.26
+sympy==1.13.1
+tenacity==8.5.0
+threadpoolctl==3.5.0
+tiktoken==0.8.0
+tokenizers==0.20.3
+toml==0.10.2
+torch==2.5.0+cu121
+torchaudio==2.5.0+cu121
+torchvision==0.20.0+cu121
+tornado==6.4.1
+tqdm==4.67.0
+transformers==4.46.3
+triton==3.1.0
+typing-inspect==0.9.0
+typing_extensions==4.12.2
+tzdata==2024.2
+urllib3==2.2.3
+watchdog==5.0.3
+wrapt==1.16.0
+yarl==1.17.2