Update model.properties, Dockerfile, requirements.txt, LICENSE.txt, README.md,...

Update model.properties, Dockerfile, requirements.txt, LICENSE.txt, README.md, whl.zip, doc/training_loss.png, doc/result.png, doc/internlm2_math.pdf, finetune/single_node.sh, finetune/multi_node.sh, finetune/data/README.md, finetune/data/identity.json, finetune/data/mllm_demo.json, finetune/data/dataset_info.json, finetune/data/alpaca_zh_demo.json, finetune/data/alpaca_en_demo.json, finetune/data/glaive_toolcall_zh_demo.json, finetune/data/dpo_zh_demo.json, finetune/data/c4_demo.json, finetune/data/glaive_toolcall_en_demo.json, finetune/data/kto_en_demo.json, finetune/data/dpo_en_demo.json, finetune/data/README_zh.md, finetune/data/wiki_demo.txt, finetune/scripts/cal_flops.py, finetune/scripts/length_cdf.py, finetune/scripts/cal_ppl.py, finetune/scripts/llamafy_qwen.py, finetune/scripts/cal_lr.py, finetune/scripts/llamafy_baichuan2.py, finetune/scripts/llama_pro.py, finetune/scripts/loftq_init.py, finetune/src/api.py, finetune/src/train.py, finetune/src/webui.py, finetune/src/llmfactory/__init__.py, finetune/src/llmfactory/cli.py, finetune/src/llmfactory/api/__init__.py, finetune/src/llmfactory/api/common.py, finetune/src/llmfactory/api/chat.py, finetune/src/llmfactory/api/app.py, finetune/src/llmfactory/api/protocol.py, finetune/src/llmfactory/chat/__init__.py, finetune/src/llmfactory/chat/base_engine.py, finetune/src/llmfactory/chat/vllm_engine.py, finetune/src/llmfactory/chat/chat_model.py, finetune/src/llmfactory/chat/hf_engine.py, finetune/src/llmfactory/data/__init__.py, finetune/src/llmfactory/data/loader.py, finetune/src/llmfactory/data/utils.py, finetune/src/llmfactory/data/collator.py, finetune/src/llmfactory/data/formatter.py, finetune/src/llmfactory/data/aligner.py, finetune/src/llmfactory/data/template.py, finetune/src/llmfactory/data/parser.py, finetune/src/llmfactory/data/preprocess.py, finetune/src/llmfactory/eval/__init__.py, finetune/src/llmfactory/eval/template.py, finetune/src/llmfactory/eval/evaluator.py, finetune/src/llmfactory/extras/__init__.py, finetune/src/llmfactory/extras/logging.py, finetune/src/llmfactory/extras/constants.py, finetune/src/llmfactory/extras/misc.py, finetune/src/llmfactory/extras/packages.py, finetune/src/llmfactory/extras/ploting.py, finetune/src/llmfactory/extras/callbacks.py, finetune/src/llmfactory/hparams/__init__.py, finetune/src/llmfactory/hparams/data_args.py, finetune/src/llmfactory/hparams/finetuning_args.py, finetune/src/llmfactory/hparams/generating_args.py, finetune/src/llmfactory/hparams/evaluation_args.py, finetune/src/llmfactory/hparams/model_args.py, finetune/src/llmfactory/hparams/parser.py, finetune/src/llmfactory/model/__init__.py, finetune/src/llmfactory/model/patcher.py, finetune/src/llmfactory/model/adapter.py, finetune/src/llmfactory/model/loader.py, finetune/src/llmfactory/model/utils/__init__.py, finetune/src/llmfactory/model/utils/misc.py, finetune/src/llmfactory/model/utils/checkpointing.py, finetune/src/llmfactory/model/utils/embedding.py, finetune/src/llmfactory/model/utils/attention.py, finetune/src/llmfactory/model/utils/longlora.py, finetune/src/llmfactory/model/utils/visual.py, finetune/src/llmfactory/model/utils/moe.py, finetune/src/llmfactory/model/utils/valuehead.py, finetune/src/llmfactory/model/utils/rope.py, finetune/src/llmfactory/model/utils/quantization.py, finetune/src/llmfactory/model/utils/mod.py, finetune/src/llmfactory/model/utils/unsloth.py, finetune/src/llmfactory/train/__init__.py, finetune/src/llmfactory/train/utils.py, finetune/src/llmfactory/train/tuner.py, finetune/src/llmfactory/train/dpo/__init__.py, finetune/src/llmfactory/train/dpo/trainer.py, finetune/src/llmfactory/train/dpo/workflow.py, finetune/src/llmfactory/train/kto/__init__.py, finetune/src/llmfactory/train/kto/trainer.py, finetune/src/llmfactory/train/kto/workflow.py, finetune/src/llmfactory/train/orpo/trainer.py, finetune/src/llmfactory/train/orpo/__init__.py, finetune/src/llmfactory/train/orpo/workflow.py, finetune/src/llmfactory/train/ppo/__init__.py, finetune/src/llmfactory/train/ppo/workflow.py, finetune/src/llmfactory/train/ppo/utils.py, finetune/src/llmfactory/train/ppo/trainer.py, finetune/src/llmfactory/train/pt/__init__.py, finetune/src/llmfactory/train/pt/workflow.py, finetune/src/llmfactory/train/pt/trainer.py, finetune/src/llmfactory/train/rm/__init__.py, finetune/src/llmfactory/train/rm/metric.py, finetune/src/llmfactory/train/rm/workflow.py, finetune/src/llmfactory/train/rm/trainer.py, finetune/src/llmfactory/train/sft/__init__.py, finetune/src/llmfactory/train/sft/metric.py, finetune/src/llmfactory/train/sft/trainer.py, finetune/src/llmfactory/train/sft/workflow.py, finetune/src/llmfactory/webui/__init__.py, finetune/src/llmfactory/webui/chatter.py, finetune/src/llmfactory/webui/common.py, finetune/src/llmfactory/webui/css.py, finetune/src/llmfactory/webui/manager.py, finetune/src/llmfactory/webui/engine.py, finetune/src/llmfactory/webui/runner.py, finetune/src/llmfactory/webui/interface.py, finetune/src/llmfactory/webui/utils.py, finetune/src/llmfactory/webui/locales.py, finetune/src/llmfactory/webui/components/__init__.py, finetune/src/llmfactory/webui/components/chatbot.py, finetune/src/llmfactory/webui/components/data.py, finetune/src/llmfactory/webui/components/eval.py, finetune/src/llmfactory/webui/components/export.py, finetune/src/llmfactory/webui/components/infer.py, finetune/src/llmfactory/webui/components/top.py, finetune/src/llmfactory/webui/components/train.py, inference/single_dcu.py files

Dockerfile

+FROM docker pull image.sourcefind.cn:5000/dcu/admin/base/pytorch:2.1.0-centos7.6-dtk24.04-py310
+COPY requirement.txt requirement.txt
+RUN source /opt/dtk-24.04/env.sh
+ENV LANG C.UTF-8
+RUN pip install -r requirement.txt -i http://mirrors.aliyun.com/pypi/simple/ --trusted-host mirrors.aliyun.com
+

LICENSE.txt

+                                 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 2023 01.AI
+
+   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

+# InternLM-Math
+
+## 论文
+
+`InternLM-Math: Open Math Large Language Models Toward Verifiable Reasoning`
+
+- [https://arxiv.org/abs/2402.06332]
+## 算法原理
+
+InternLM-Math是基于InternLM2-Base模型进行数学预训练得到的大型语言模型。融合了链式推理、奖励建模、数据增强和形式推理等多种能力，不仅可以解决数学问题，还可以验证推理过程的正确性。
+
+
+## 环境配置
+
+### Docker（方法一）
+
+此处提供[光源](https://www.sourcefind.cn/#/service-details)拉取 docker 镜像的地址与使用步骤
+
+```
+docker pull xxx
+docker run -it --shm-size=1024G -v /parastor/home/internlm-math-pytorch:/home/internlm-math-pytorch -v /opt/hyhal:/opt/hyhal --privileged=true --device=/dev/kfd --device=/dev/dri/ --group-add video --name internlm-math  <your IMAGE ID> bash  # <your IMAGE ID>为以上拉取的docker的镜像ID替换，本镜像为：c85ed27005f2
+cd /home/internlm-math-pytorch
+pip install -r requirement.txt -i https://mirrors.aliyun.com/pypi/simple/  --trusted-host mirrors.aliyun.com
+# deepspeed、bitsandbytes可从whl.zip文件里获取安装：
+pip install deepspeed-0.12.3+das1.0+gita724046.abi0.dtk2404.torch2.1.0-cp310-cp310-manylinux2014_x86_64.whl
+pip install bitsandbytes-0.42.0-py3-none-any.whl
+
+```
+
+### Dockerfile（方法二）
+
+此处提供 dockerfile 的使用方法
+
+```
+docker build  -t internlm-math-df:latest .
+docker run -it --shm-size=1024G -v /parastor/home/internlm-math-pytorch:/home/internlm-math-pytorch -v /opt/hyhal:/opt/hyhal --privileged=true --device=/dev/kfd --device=/dev/dri/ --group-add video --name internlm-math  internlm-math-df  bash
+pip install -r requirement.txt -i https://mirrors.aliyun.com/pypi/simple/  --trusted-host mirrors.aliyun.com
+# deepspeed、bitsandbytes可从whl.zip文件里获取安装：
+pip install deepspeed-0.12.3+das1.0+gita724046.abi0.dtk2404.torch2.1.0-cp310-cp310-manylinux2014_x86_64.whl
+pip install bitsandbytes-0.42.0-py3-none-any.whl
+
+```
+
+### Anaconda（方法三）
+
+此处提供本地配置、编译的详细步骤，例如：
+
+关于本项目 DCU 显卡所需的特殊深度学习库可从[光合](https://developer.hpccube.com/tool/)开发者社区下载安装。
+
+```
+DTK驱动：dtk23.04
+python：python3.10
+torch: 2.1.0
+torchvision: 0.16.0
+deepspeed:0.12.3
+bitsandbytes: 0.42.0
+triton:2.1.0
+```
+
+`Tips：以上dtk驱动、python、paddle等DCU相关工具版本需要严格一一对应`
+
+其它非深度学习库参照 requirements.txt 安装：
+
+```
+pip install -r requirements.txt
+```
+
+## 数据集
+使用alpaca_en.json数据集，已经包含在data目录中，具体文件为alpaca_en_demo.json
+项目中已提供用于试验训练的迷你数据集，训练数据目录结构如下，用于正常训练的完整数据集请按此目录结构进行制备：
+
+```
+ ── data
+    ├── alpaca_en_demo.json.json
+    └── alpaca_zh_demo.json.json
+```
+
+## 训练
+
+一般情况下，ModelZoo 上的项目提供单机训练的启动方法即可，单机单卡、单机多卡至少提供其一训练方法。
+
+### 单机单卡
+
+```
+cd fintune
+sh single_dcu_finetune_lora.sh
+```
+### 单机多卡
+
+```
+sh multi_node.sh
+```
+
+
+## 推理
+
+```
+cd examples/inference
+sh single_node.sh
+```
+
+## result
+
+使用的加速卡:2张 DCU-K100-64G
+
+<div align=center>
+    <img src="./doc/training_loss.png"/>
+</div>
+
+### 精度
+测试数据：[alpaca_en_demo.json]，使用的加速卡:K100-64G,2卡训练。
+
+根据测试结果情况填写表格：
+| device | train_loss | 
+| :------: | :------: | 
+| DCU-K100 | 1.0941 | 
+| GPU-A800 | 1.0944 | 
+
+使用opencompass(https://github.com/open-compass/opencompass)得到的测试结果对比
+<div align=center>
+    <img src="./doc/result.png"/>
+</div>
+## 应用场景
+
+### 算法类别
+
+数学推理
+
+### 热点应用行业
+
+`科研,教育,金融`
+
+
+## 源码仓库及问题反馈
+
+- https://github.com/InternLM/InternLM-Math
+
+## 参考资料
+
+- https://github.com/hiyouga/LLaMA-Factory/tree/main
+- https://github.com/InternLM/InternLM-Math
+- https://hf-mirror.com/internlm/internlm2-math-7b
+

finetune/data/README.md

+The [dataset_info.json](dataset_info.json) contains all available datasets. If you are using a custom dataset, please **make sure** to add a *dataset description* in `dataset_info.json` and specify `dataset: dataset_name` before training to use it.
+
+Currently we support datasets in **alpaca** and **sharegpt** format.
+
+```json
+"dataset_name": {
+  "hf_hub_url": "the name of the dataset repository on the Hugging Face hub. (if specified, ignore script_url and file_name)",
+  "ms_hub_url": "the name of the dataset repository on the Model Scope hub. (if specified, ignore script_url and file_name)",
+  "script_url": "the name of the directory containing a dataset loading script. (if specified, ignore file_name)",
+  "file_name": "the name of the dataset folder or dataset file in this directory. (required if above are not specified)",
+  "formatting": "the format of the dataset. (optional, default: alpaca, can be chosen from {alpaca, sharegpt})",
+  "ranking": "whether the dataset is a preference dataset or not. (default: False)",
+  "subset": "the name of the subset. (optional, default: None)",
+  "folder": "the name of the folder of the dataset repository on the Hugging Face hub. (optional, default: None)",
+  "columns (optional)": {
+    "prompt": "the column name in the dataset containing the prompts. (default: instruction)",
+    "query": "the column name in the dataset containing the queries. (default: input)",
+    "response": "the column name in the dataset containing the responses. (default: output)",
+    "history": "the column name in the dataset containing the histories. (default: None)",
+    "messages": "the column name in the dataset containing the messages. (default: conversations)",
+    "system": "the column name in the dataset containing the system prompts. (default: None)",
+    "tools": "the column name in the dataset containing the tool description. (default: None)",
+    "images": "the column name in the dataset containing the image inputs. (default: None)",
+    "chosen": "the column name in the dataset containing the chosen answers. (default: None)",
+    "rejected": "the column name in the dataset containing the rejected answers. (default: None)",
+    "kto_tag": "the column name in the dataset containing the kto tags. (default: None)"
+  },
+  "tags (optional, used for the sharegpt format)": {
+    "role_tag": "the key in the message represents the identity. (default: from)",
+    "content_tag": "the key in the message represents the content. (default: value)",
+    "user_tag": "the value of the role_tag represents the user. (default: human)",
+    "assistant_tag": "the value of the role_tag represents the assistant. (default: gpt)",
+    "observation_tag": "the value of the role_tag represents the tool results. (default: observation)",
+    "function_tag": "the value of the role_tag represents the function call. (default: function_call)",
+    "system_tag": "the value of the role_tag represents the system prompt. (default: system, can override system column)"
+  }
+}
+```
+
+## Alpaca Format
+
+### Supervised Fine-Tuning Dataset
+
+* [Example dataset](alpaca_en_demo.json)
+
+In supervised fine-tuning, the `instruction` column will be concatenated with the `input` column and used as the human prompt, then the human prompt would be `instruction\ninput`. The `output` column represents the model response.
+
+The `system` column will be used as the system prompt if specified.
+
+The `history` column is a list consisting of string tuples representing prompt-response pairs in the history messages. Note that the responses in the history **will also be learned by the model** in supervised fine-tuning.
+
+```json
+[
+  {
+    "instruction": "human instruction (required)",
+    "input": "human input (optional)",
+    "output": "model response (required)",
+    "system": "system prompt (optional)",
+    "history": [
+      ["human instruction in the first round (optional)", "model response in the first round (optional)"],
+      ["human instruction in the second round (optional)", "model response in the second round (optional)"]
+    ]
+  }
+]
+```
+
+Regarding the above dataset, the *dataset description* in `dataset_info.json` should be:
+
+```json
+"dataset_name": {
+  "file_name": "data.json",
+  "columns": {
+    "prompt": "instruction",
+    "query": "input",
+    "response": "output",
+    "system": "system",
+    "history": "history"
+  }
+}
+```
+
+### Pre-training Dataset
+
+- [Example dataset](c4_demo.json)
+
+In pre-training, only the `text` column will be used for model learning.
+
+```json
+[
+  {"text": "document"},
+  {"text": "document"}
+]
+```
+
+Regarding the above dataset, the *dataset description* in `dataset_info.json` should be:
+
+```json
+"dataset_name": {
+  "file_name": "data.json",
+  "columns": {
+    "prompt": "text"
+  }
+}
+```
+
+### Preference Dataset
+
+Preference datasets are used for reward modeling, DPO training and ORPO training.
+
+It requires a better response in `chosen` column and a worse response in `rejected` column.
+
+```json
+[
+  {
+    "instruction": "human instruction (required)",
+    "input": "human input (optional)",
+    "chosen": "chosen answer (required)",
+    "rejected": "rejected answer (required)"
+  }
+]
+```
+
+Regarding the above dataset, the *dataset description* in `dataset_info.json` should be:
+
+```json
+"dataset_name": {
+  "file_name": "data.json",
+  "ranking": true,
+  "columns": {
+    "prompt": "instruction",
+    "query": "input",
+    "chosen": "chosen",
+    "rejected": "rejected"
+  }
+}
+```
+
+### KTO Dataset
+
+- [Example dataset](kto_en_demo.json)
+
+KTO datasets require a extra `kto_tag` column containing the boolean human feedback.
+
+```json
+[
+  {
+    "instruction": "human instruction (required)",
+    "input": "human input (optional)",
+    "output": "model response (required)",
+    "kto_tag": "human feedback [true/false] (required)"
+  }
+]
+```
+
+Regarding the above dataset, the *dataset description* in `dataset_info.json` should be:
+
+```json
+"dataset_name": {
+  "file_name": "data.json",
+  "columns": {
+    "prompt": "instruction",
+    "query": "input",
+    "response": "output",
+    "kto_tag": "kto_tag"
+  }
+}
+```
+
+### Multimodal Dataset
+
+- [Example dataset](mllm_demo.json)
+
+Multimodal datasets require a `images` column containing the paths to the input images. Currently we only support one image.
+
+```json
+[
+  {
+    "instruction": "human instruction (required)",
+    "input": "human input (optional)",
+    "output": "model response (required)",
+    "images": [
+      "image path (required)"
+    ]
+  }
+]
+```
+
+Regarding the above dataset, the *dataset description* in `dataset_info.json` should be:
+
+```json
+"dataset_name": {
+  "file_name": "data.json",
+  "columns": {
+    "prompt": "instruction",
+    "query": "input",
+    "response": "output",
+    "images": "images"
+  }
+}
+```
+
+## Sharegpt Format
+
+### Supervised Fine-Tuning Dataset
+
+- [Example dataset](glaive_toolcall_en_demo.json)
+
+Compared to the alpaca format, the sharegpt format allows the datasets have **more roles**, such as human, gpt, observation and function. They are presented in a list of objects in the `conversations` column.
+
+Note that the human and observation should appear in odd positions, while gpt and function should appear in even positions.
+
+```json
+[
+  {
+    "conversations": [
+      {
+        "from": "human",
+        "value": "human instruction"
+      },
+      {
+        "from": "function_call",
+        "value": "tool arguments"
+      },
+      {
+        "from": "observation",
+        "value": "tool result"
+      },
+      {
+        "from": "gpt",
+        "value": "model response"
+      }
+    ],
+    "system": "system prompt (optional)",
+    "tools": "tool description (optional)"
+  }
+]
+```
+
+Regarding the above dataset, the *dataset description* in `dataset_info.json` should be:
+
+```json
+"dataset_name": {
+  "file_name": "data.json",
+  "formatting": "sharegpt",
+  "columns": {
+    "messages": "conversations",
+    "system": "system",
+    "tools": "tools"
+  }
+}
+```
+
+### Preference Dataset
+
+- [Example dataset](dpo_en_demo.json)
+
+Preference datasets in sharegpt format also require a better message in `chosen` column and a worse message in `rejected` column.
+
+```json
+[
+  {
+    "conversations": [
+      {
+        "from": "human",
+        "value": "human instruction"
+      },
+      {
+        "from": "gpt",
+        "value": "model response"
+      },
+      {
+        "from": "human",
+        "value": "human instruction"
+      }
+    ],
+    "chosen": {
+      "from": "gpt",
+      "value": "chosen answer (required)"
+    },
+    "rejected": {
+      "from": "gpt",
+      "value": "rejected answer (required)"
+    }
+  }
+]
+```
+
+Regarding the above dataset, the *dataset description* in `dataset_info.json` should be:
+
+```json
+"dataset_name": {
+  "file_name": "data.json",
+  "formatting": "sharegpt",
+  "ranking": true,
+  "columns": {
+    "messages": "conversations",
+    "chosen": "chosen",
+    "rejected": "rejected"
+  }
+}
+```
+
+### OpenAI Format
+
+The openai format is simply a special case of the sharegpt format, where the first message may be a system prompt.
+
+```json
+[
+  {
+    "messages": [
+      {
+        "role": "system",
+        "content": "system prompt (optional)"
+      },
+      {
+        "role": "user",
+        "content": "human instruction"
+      },
+      {
+        "role": "assistant",
+        "content": "model response"
+      }
+    ]
+  }
+]
+```
+
+Regarding the above dataset, the *dataset description* in `dataset_info.json` should be:
+
+```json
+"dataset_name": {
+  "file_name": "data.json",
+  "formatting": "sharegpt",
+  "columns": {
+    "messages": "messages"
+  },
+  "tags": {
+    "role_tag": "role",
+    "content_tag": "content",
+    "user_tag": "user",
+    "assistant_tag": "assistant",
+    "system_tag": "system"
+  }
+}
+```
+
+The KTO datasets and multimodal datasets in sharegpt format are similar to the alpaca format.
+
+Pre-training datasets are **incompatible** with the sharegpt format.

finetune/data/README_zh.md

+[dataset_info.json](dataset_info.json) 包含了所有可用的数据集。如果您希望使用自定义数据集，请**务必**在 `dataset_info.json` 文件中添加*数据集描述*，并通过修改 `dataset: 数据集名称` 配置来使用数据集。
+
+目前我们支持 **alpaca** 格式和 **sharegpt** 格式的数据集。
+
+```json
+"数据集名称": {
+  "hf_hub_url": "Hugging Face 的数据集仓库地址（若指定，则忽略 script_url 和 file_name）",
+  "ms_hub_url": "ModelScope 的数据集仓库地址（若指定，则忽略 script_url 和 file_name）",
+  "script_url": "包含数据加载脚本的本地文件夹名称（若指定，则忽略 file_name）",
+  "file_name": "该目录下数据集文件的名称（若上述参数未指定，则此项必需）",
+  "formatting": "数据集格式（可选，默认：alpaca，可以为 alpaca 或 sharegpt）",
+  "ranking": "是否为偏好数据集（可选，默认：False）",
+  "subset": "数据集子集的名称（可选，默认：None）",
+  "folder": "Hugging Face 仓库的文件夹名称（可选，默认：None）",
+  "columns（可选）": {
+    "prompt": "数据集代表提示词的表头名称（默认：instruction）",
+    "query": "数据集代表请求的表头名称（默认：input）",
+    "response": "数据集代表回答的表头名称（默认：output）",
+    "history": "数据集代表历史对话的表头名称（默认：None）",
+    "messages": "数据集代表消息列表的表头名称（默认：conversations）",
+    "system": "数据集代表系统提示的表头名称（默认：None）",
+    "tools": "数据集代表工具描述的表头名称（默认：None）",
+    "images": "数据集代表图像输入的表头名称（默认：None）",
+    "chosen": "数据集代表更优回答的表头名称（默认：None）",
+    "rejected": "数据集代表更差回答的表头名称（默认：None）",
+    "kto_tag": "数据集代表 KTO 标签的表头名称（默认：None）"
+  },
+  "tags（可选，用于 sharegpt 格式）": {
+    "role_tag": "消息中代表发送者身份的键名（默认：from）",
+    "content_tag": "消息中代表文本内容的键名（默认：value）",
+    "user_tag": "消息中代表用户的 role_tag（默认：human）",
+    "assistant_tag": "消息中代表助手的 role_tag（默认：gpt）",
+    "observation_tag": "消息中代表工具返回结果的 role_tag（默认：observation）",
+    "function_tag": "消息中代表工具调用的 role_tag（默认：function_call）",
+    "system_tag": "消息中代表系统提示的 role_tag（默认：system，会覆盖 system column）"
+  }
+}
+```
+
+## Alpaca 格式
+
+### 指令监督微调数据集
+
+- [样例数据集](alpaca_zh_demo.json)
+
+在指令监督微调时，`instruction` 列对应的内容会与 `input` 列对应的内容拼接后作为人类指令，即人类指令为 `instruction\ninput`。而 `output` 列对应的内容为模型回答。
+
+如果指定，`system` 列对应的内容将被作为系统提示词。
+
+`history` 列是由多个字符串二元组构成的列表，分别代表历史消息中每轮对话的指令和回答。注意在指令监督微调时，历史消息中的回答内容**也会被用于模型学习**。
+
+```json
+[
+  {
+    "instruction": "人类指令（必填）",
+    "input": "人类输入（选填）",
+    "output": "模型回答（必填）",
+    "system": "系统提示词（选填）",
+    "history": [
+      ["第一轮指令（选填）", "第一轮回答（选填）"],
+      ["第二轮指令（选填）", "第二轮回答（选填）"]
+    ]
+  }
+]
+```
+
+对于上述格式的数据，`dataset_info.json` 中的*数据集描述*应为：
+
+```json
+"数据集名称": {
+  "file_name": "data.json",
+  "columns": {
+    "prompt": "instruction",
+    "query": "input",
+    "response": "output",
+    "system": "system",
+    "history": "history"
+  }
+}
+```
+
+### 预训练数据集
+
+- [样例数据集](c4_demo.json)
+
+在预训练时，只有 `text` 列中的内容会用于模型学习。
+
+```json
+[
+  {"text": "document"},
+  {"text": "document"}
+]
+```
+
+对于上述格式的数据，`dataset_info.json` 中的*数据集描述*应为：
+
+```json
+"数据集名称": {
+  "file_name": "data.json",
+  "columns": {
+    "prompt": "text"
+  }
+}
+```
+
+### 偏好数据集
+
+偏好数据集用于奖励模型训练、DPO 训练和 ORPO 训练。
+
+它需要在 `chosen` 列中提供更优的回答，并在 `rejected` 列中提供更差的回答。
+
+```json
+[
+  {
+    "instruction": "人类指令（必填）",
+    "input": "人类输入（选填）",
+    "chosen": "优质回答（必填）",
+    "rejected": "劣质回答（必填）"
+  }
+]
+```
+
+对于上述格式的数据，`dataset_info.json` 中的*数据集描述*应为：
+
+```json
+"数据集名称": {
+  "file_name": "data.json",
+  "ranking": true,
+  "columns": {
+    "prompt": "instruction",
+    "query": "input",
+    "chosen": "chosen",
+    "rejected": "rejected"
+  }
+}
+```
+
+### KTO 数据集
+
+- [样例数据集](kto_en_demo.json)
+
+KTO 数据集需要额外添加一个 `kto_tag` 列，包含 bool 类型的人类反馈。
+
+```json
+[
+  {
+    "instruction": "人类指令（必填）",
+    "input": "人类输入（选填）",
+    "output": "模型回答（必填）",
+    "kto_tag": "人类反馈 [true/false]（必填）"
+  }
+]
+```
+
+对于上述格式的数据，`dataset_info.json` 中的*数据集描述*应为：
+
+```json
+"数据集名称": {
+  "file_name": "data.json",
+  "columns": {
+    "prompt": "instruction",
+    "query": "input",
+    "response": "output",
+    "kto_tag": "kto_tag"
+  }
+}
+```
+
+### 多模态数据集
+
+- [样例数据集](mllm_demo.json)
+
+多模态数据集需要额外添加一个 `images` 列，包含输入图像的路径。目前我们仅支持单张图像输入。
+
+```json
+[
+  {
+    "instruction": "人类指令（必填）",
+    "input": "人类输入（选填）",
+    "output": "模型回答（必填）",
+    "images": [
+      "图像路径（必填）"
+    ]
+  }
+]
+```
+
+对于上述格式的数据，`dataset_info.json` 中的*数据集描述*应为：
+
+```json
+"数据集名称": {
+  "file_name": "data.json",
+  "columns": {
+    "prompt": "instruction",
+    "query": "input",
+    "response": "output",
+    "images": "images"
+  }
+}
+```
+
+## Sharegpt 格式
+
+### 指令监督微调数据集
+
+- [样例数据集](glaive_toolcall_zh_demo.json)
+
+相比 alpaca 格式的数据集，sharegpt 格式支持**更多的角色种类**，例如 human、gpt、observation、function 等等。它们构成一个对象列表呈现在 `conversations` 列中。
+
+注意其中 human 和 observation 必须出现在奇数位置，gpt 和 function 必须出现在偶数位置。
+
+```json
+[
+  {
+    "conversations": [
+      {
+        "from": "human",
+        "value": "人类指令"
+      },
+      {
+        "from": "function_call",
+        "value": "工具参数"
+      },
+      {
+        "from": "observation",
+        "value": "工具结果"
+      },
+      {
+        "from": "gpt",
+        "value": "模型回答"
+      }
+    ],
+    "system": "系统提示词（选填）",
+    "tools": "工具描述（选填）"
+  }
+]
+```
+
+对于上述格式的数据，`dataset_info.json` 中的*数据集描述*应为：
+
+```json
+"数据集名称": {
+  "file_name": "data.json",
+  "formatting": "sharegpt",
+  "columns": {
+    "messages": "conversations",
+    "system": "system",
+    "tools": "tools"
+  }
+}
+```
+
+### 偏好数据集
+
+- [样例数据集](dpo_zh_demo.json)
+
+Sharegpt 格式的偏好数据集同样需要在 `chosen` 列中提供更优的消息，并在 `rejected` 列中提供更差的消息。
+
+```json
+[
+  {
+    "conversations": [
+      {
+        "from": "human",
+        "value": "人类指令"
+      },
+      {
+        "from": "gpt",
+        "value": "模型回答"
+      },
+      {
+        "from": "human",
+        "value": "人类指令"
+      }
+    ],
+    "chosen": {
+      "from": "gpt",
+      "value": "优质回答"
+    },
+    "rejected": {
+      "from": "gpt",
+      "value": "劣质回答"
+    }
+  }
+]
+```
+
+对于上述格式的数据，`dataset_info.json` 中的*数据集描述*应为：
+
+```json
+"数据集名称": {
+  "file_name": "data.json",
+  "formatting": "sharegpt",
+  "ranking": true,
+  "columns": {
+    "messages": "conversations",
+    "chosen": "chosen",
+    "rejected": "rejected"
+  }
+}
+```
+
+### OpenAI 格式
+
+OpenAI 格式仅仅是 sharegpt 格式的一种特殊情况，其中第一条消息可能是系统提示词。
+
+```json
+[
+  {
+    "messages": [
+      {
+        "role": "system",
+        "content": "系统提示词（选填）"
+      },
+      {
+        "role": "user",
+        "content": "人类指令"
+      },
+      {
+        "role": "assistant",
+        "content": "模型回答"
+      }
+    ]
+  }
+]
+```
+
+对于上述格式的数据，`dataset_info.json` 中的*数据集描述*应为：
+
+```json
+"数据集名称": {
+  "file_name": "data.json",
+  "formatting": "sharegpt",
+  "columns": {
+    "messages": "messages"
+  },
+  "tags": {
+    "role_tag": "role",
+    "content_tag": "content",
+    "user_tag": "user",
+    "assistant_tag": "assistant",
+    "system_tag": "system"
+  }
+}
+```
+
+Sharegpt 格式中的 KTO 数据集和多模态数据集与 alpaca 格式的类似。
+
+预训练数据集**不支持** sharegpt 格式。

finetune/data/dataset_info.json

+{
+  "identity": {
+    "file_name": "identity.json"
+  },
+  "alpaca_en_demo": {
+    "file_name": "alpaca_en_demo.json"
+  },
+  "alpaca_zh_demo": {
+    "file_name": "alpaca_zh_demo.json"
+  },
+  "glaive_toolcall_en_demo": {
+    "file_name": "glaive_toolcall_en_demo.json",
+    "formatting": "sharegpt",
+    "columns": {
+      "messages": "conversations",
+      "tools": "tools"
+    }
+  },
+  "glaive_toolcall_zh_demo": {
+    "file_name": "glaive_toolcall_zh_demo.json",
+    "formatting": "sharegpt",
+    "columns": {
+      "messages": "conversations",
+      "tools": "tools"
+    }
+  },
+  "mllm_demo": {
+    "file_name": "mllm_demo.json",
+    "formatting": "sharegpt",
+    "columns": {
+      "messages": "messages",
+      "images": "images"
+    },
+    "tags": {
+      "role_tag": "role",
+      "content_tag": "content",
+      "user_tag": "user",
+      "assistant_tag": "assistant"
+    }
+  },
+  "alpaca_en": {
+    "hf_hub_url": "llamafactory/alpaca_en",
+    "ms_hub_url": "llamafactory/alpaca_en"
+  },
+  "alpaca_zh": {
+    "hf_hub_url": "llamafactory/alpaca_zh",
+    "ms_hub_url": "llamafactory/alpaca_zh"
+  },
+  "alpaca_gpt4_en": {
+    "hf_hub_url": "llamafactory/alpaca_gpt4_en",
+    "ms_hub_url": "llamafactory/alpaca_gpt4_en"
+  },
+  "alpaca_gpt4_zh": {
+    "hf_hub_url": "llamafactory/alpaca_gpt4_zh",
+    "ms_hub_url": "llamafactory/alpaca_gpt4_zh"
+  },
+  "glaive_toolcall_en": {
+    "hf_hub_url": "llamafactory/glaive_toolcall_en",
+    "formatting": "sharegpt",
+    "columns": {
+      "messages": "conversations",
+      "tools": "tools"
+    }
+  },
+  "glaive_toolcall_zh": {
+    "hf_hub_url": "llamafactory/glaive_toolcall_zh",
+    "formatting": "sharegpt",
+    "columns": {
+      "messages": "conversations",
+      "tools": "tools"
+    }
+  },
+  "lima": {
+    "hf_hub_url": "llamafactory/lima",
+    "formatting": "sharegpt"
+  },
+  "guanaco": {
+    "hf_hub_url": "JosephusCheung/GuanacoDataset",
+    "ms_hub_url": "AI-ModelScope/GuanacoDataset"
+  },
+  "belle_2m": {
+    "hf_hub_url": "BelleGroup/train_2M_CN",
+    "ms_hub_url": "AI-ModelScope/train_2M_CN"
+  },
+  "belle_1m": {
+    "hf_hub_url": "BelleGroup/train_1M_CN",
+    "ms_hub_url": "AI-ModelScope/train_1M_CN"
+  },
+  "belle_0.5m": {
+    "hf_hub_url": "BelleGroup/train_0.5M_CN",
+    "ms_hub_url": "AI-ModelScope/train_0.5M_CN"
+  },
+  "belle_dialog": {
+    "hf_hub_url": "BelleGroup/generated_chat_0.4M",
+    "ms_hub_url": "AI-ModelScope/generated_chat_0.4M"
+  },
+  "belle_math": {
+    "hf_hub_url": "BelleGroup/school_math_0.25M",
+    "ms_hub_url": "AI-ModelScope/school_math_0.25M"
+  },
+  "belle_multiturn": {
+    "script_url": "belle_multiturn",
+    "formatting": "sharegpt"
+  },
+  "ultra_chat": {
+    "script_url": "ultra_chat",
+    "formatting": "sharegpt"
+  },
+  "open_platypus": {
+    "hf_hub_url": "garage-bAInd/Open-Platypus",
+    "ms_hub_url": "AI-ModelScope/Open-Platypus"
+  },
+  "codealpaca": {
+    "hf_hub_url": "sahil2801/CodeAlpaca-20k",
+    "ms_hub_url": "AI-ModelScope/CodeAlpaca-20k"
+  },
+  "alpaca_cot": {
+    "hf_hub_url": "QingyiSi/Alpaca-CoT",
+    "ms_hub_url": "AI-ModelScope/Alpaca-CoT"
+  },
+  "openorca": {
+    "hf_hub_url": "Open-Orca/OpenOrca",
+    "ms_hub_url": "AI-ModelScope/OpenOrca",
+    "columns": {
+      "prompt": "question",
+      "response": "response",
+      "system": "system_prompt"
+    }
+  },
+  "slimorca": {
+    "hf_hub_url": "Open-Orca/SlimOrca",
+    "formatting": "sharegpt"
+  },
+  "mathinstruct": {
+    "hf_hub_url": "TIGER-Lab/MathInstruct",
+    "ms_hub_url": "AI-ModelScope/MathInstruct",
+    "columns": {
+      "prompt": "instruction",
+      "response": "output"
+    }
+  },
+  "firefly": {
+    "hf_hub_url": "YeungNLP/firefly-train-1.1M",
+    "columns": {
+      "prompt": "input",
+      "response": "target"
+    }
+  },
+  "wikiqa": {
+    "hf_hub_url": "wiki_qa",
+    "columns": {
+      "prompt": "question",
+      "response": "answer"
+    }
+  },
+  "webqa": {
+    "hf_hub_url": "suolyer/webqa",
+    "ms_hub_url": "AI-ModelScope/webqa",
+    "columns": {
+      "prompt": "input",
+      "response": "output"
+    }
+  },
+  "webnovel": {
+    "hf_hub_url": "zxbsmk/webnovel_cn",
+    "ms_hub_url": "AI-ModelScope/webnovel_cn"
+  },
+  "nectar_sft": {
+    "hf_hub_url": "AstraMindAI/SFT-Nectar",
+    "ms_hub_url": "AI-ModelScope/SFT-Nectar"
+  },
+  "deepctrl": {
+    "ms_hub_url": "deepctrl/deepctrl-sft-data"
+  },
+  "adgen": {
+    "hf_hub_url": "HasturOfficial/adgen",
+    "ms_hub_url": "AI-ModelScope/adgen",
+    "columns": {
+      "prompt": "content",
+      "response": "summary"
+    }
+  },
+  "sharegpt_hyper": {
+    "hf_hub_url": "totally-not-an-llm/sharegpt-hyperfiltered-3k",
+    "formatting": "sharegpt"
+  },
+  "sharegpt4": {
+    "hf_hub_url": "shibing624/sharegpt_gpt4",
+    "ms_hub_url": "AI-ModelScope/sharegpt_gpt4",
+    "formatting": "sharegpt"
+  },
+  "ultrachat_200k": {
+    "hf_hub_url": "HuggingFaceH4/ultrachat_200k",
+    "ms_hub_url": "AI-ModelScope/ultrachat_200k",
+    "formatting": "sharegpt",
+    "columns": {
+      "messages": "messages"
+    },
+    "tags": {
+      "role_tag": "role",
+      "content_tag": "content",
+      "user_tag": "user",
+      "assistant_tag": "assistant"
+    }
+  },
+  "agent_instruct": {
+    "hf_hub_url": "THUDM/AgentInstruct",
+    "ms_hub_url": "ZhipuAI/AgentInstruct",
+    "formatting": "sharegpt"
+  },
+  "lmsys_chat": {
+    "hf_hub_url": "lmsys/lmsys-chat-1m",
+    "ms_hub_url": "AI-ModelScope/lmsys-chat-1m",
+    "formatting": "sharegpt",
+    "columns": {
+      "messages": "conversation"
+    },
+    "tags": {
+      "role_tag": "role",
+      "content_tag": "content",
+      "user_tag": "human",
+      "assistant_tag": "assistant"
+    }
+  },
+  "evol_instruct": {
+    "hf_hub_url": "WizardLM/WizardLM_evol_instruct_V2_196k",
+    "ms_hub_url": "AI-ModelScope/WizardLM_evol_instruct_V2_196k",
+    "formatting": "sharegpt"
+  },
+  "glaive_toolcall_100k": {
+    "hf_hub_url": "hiyouga/glaive-function-calling-v2-sharegpt",
+    "formatting": "sharegpt",
+    "columns": {
+      "messages": "conversations",
+      "tools": "tools"
+    }
+  },
+  "cosmopedia": {
+    "hf_hub_url": "HuggingFaceTB/cosmopedia",
+    "columns": {
+      "prompt": "prompt",
+      "response": "text"
+    }
+  },
+  "stem_zh": {
+    "hf_hub_url": "hfl/stem_zh_instruction"
+  },
+  "ruozhiba_gpt4": {
+    "hf_hub_url": "hfl/ruozhiba_gpt4_turbo"
+  },
+  "llava_150k_en": {
+    "hf_hub_url": "BUAADreamer/llava-en-zh-300k",
+    "subset": "en",
+    "formatting": "sharegpt",
+    "columns": {
+      "messages": "messages",
+      "images": "images"
+    },
+    "tags": {
+      "role_tag": "role",
+      "content_tag": "content",
+      "user_tag": "user",
+      "assistant_tag": "assistant"
+    }
+  },
+  "llava_150k_zh": {
+    "hf_hub_url": "BUAADreamer/llava-en-zh-300k",
+    "subset": "zh",
+    "formatting": "sharegpt",
+    "columns": {
+      "messages": "messages",
+      "images": "images"
+    },
+    "tags": {
+      "role_tag": "role",
+      "content_tag": "content",
+      "user_tag": "user",
+      "assistant_tag": "assistant"
+    }
+  },
+  "oasst_de": {
+    "hf_hub_url": "mayflowergmbh/oasst_de"
+  },
+  "dolly_15k_de": {
+    "hf_hub_url": "mayflowergmbh/dolly-15k_de"
+  },
+  "alpaca-gpt4_de": {
+    "hf_hub_url": "mayflowergmbh/alpaca-gpt4_de"
+  },
+  "openschnabeltier_de": {
+    "hf_hub_url": "mayflowergmbh/openschnabeltier_de"
+  },
+  "evol_instruct_de": {
+    "hf_hub_url": "mayflowergmbh/evol-instruct_de"
+  },
+  "dolphin_de": {
+    "hf_hub_url": "mayflowergmbh/dolphin_de"
+  },
+  "booksum_de": {
+    "hf_hub_url": "mayflowergmbh/booksum_de"
+  },
+  "airoboros_de": {
+    "hf_hub_url": "mayflowergmbh/airoboros-3.0_de"
+  },
+  "ultrachat_de": {
+    "hf_hub_url": "mayflowergmbh/ultra-chat_de"
+  },
+  "dpo_en_demo": {
+    "file_name": "dpo_en_demo.json",
+    "ranking": true,
+    "formatting": "sharegpt",
+    "columns": {
+      "messages": "conversations",
+      "chosen": "chosen",
+      "rejected": "rejected"
+    }
+  },
+  "dpo_zh_demo": {
+    "file_name": "dpo_zh_demo.json",
+    "ranking": true,
+    "formatting": "sharegpt",
+    "columns": {
+      "messages": "conversations",
+      "chosen": "chosen",
+      "rejected": "rejected"
+    }
+  },
+  "dpo_mix_en": {
+    "hf_hub_url": "hiyouga/DPO-En-Zh-20k",
+    "subset": "en",
+    "ranking": true,
+    "formatting": "sharegpt",
+    "columns": {
+      "messages": "conversations",
+      "chosen": "chosen",
+      "rejected": "rejected"
+    }
+  },
+  "dpo_mix_zh": {
+    "hf_hub_url": "hiyouga/DPO-En-Zh-20k",
+    "subset": "zh",
+    "ranking": true,
+    "formatting": "sharegpt",
+    "columns": {
+      "messages": "conversations",
+      "chosen": "chosen",
+      "rejected": "rejected"
+    }
+  },
+  "orca_pairs": {
+    "hf_hub_url": "Intel/orca_dpo_pairs",
+    "ranking": true,
+    "columns": {
+      "prompt": "question",
+      "chosen": "chosen",
+      "rejected": "rejected",
+      "system": "system"
+    }
+  },
+  "hh_rlhf_en": {
+    "script_url": "hh_rlhf_en",
+    "ranking": true,
+    "columns": {
+      "prompt": "instruction",
+      "chosen": "chosen",
+      "rejected": "rejected",
+      "history": "history"
+    }
+  },
+  "nectar_rm": {
+    "hf_hub_url": "AstraMindAI/RLAIF-Nectar",
+    "ms_hub_url": "AI-ModelScope/RLAIF-Nectar",
+    "ranking": true
+  },
+  "orca_dpo_de": {
+    "hf_hub_url": "mayflowergmbh/intel_orca_dpo_pairs_de",
+    "ranking": true
+  },
+  "kto_en_demo": {
+    "file_name": "kto_en_demo.json",
+    "formatting": "sharegpt",
+    "columns": {
+      "messages": "messages",
+      "kto_tag": "label"
+    },
+    "tags": {
+      "role_tag": "role",
+      "content_tag": "content",
+      "user_tag": "user",
+      "assistant_tag": "assistant"
+    }
+  },
+  "kto_mix_en": {
+    "hf_hub_url": "argilla/kto-mix-15k",
+    "formatting": "sharegpt",
+    "columns": {
+      "messages": "completion",
+      "kto_tag": "label"
+    },
+    "tags": {
+      "role_tag": "role",
+      "content_tag": "content",
+      "user_tag": "user",
+      "assistant_tag": "assistant"
+    }
+  },
+  "wiki_demo": {
+    "file_name": "wiki_demo.txt",
+    "columns": {
+      "prompt": "text"
+    }
+  },
+  "c4_demo": {
+    "file_name": "c4_demo.json",
+    "columns": {
+      "prompt": "text"
+    }
+  },
+  "refinedweb": {
+    "hf_hub_url": "tiiuae/falcon-refinedweb",
+    "columns": {
+      "prompt": "content"
+    }
+  },
+  "redpajama_v2": {
+    "hf_hub_url": "togethercomputer/RedPajama-Data-V2",
+    "columns": {
+      "prompt": "raw_content"
+    },
+    "subset": "default"
+  },
+  "wikipedia_en": {
+    "hf_hub_url": "olm/olm-wikipedia-20221220",
+    "ms_hub_url": "AI-ModelScope/olm-wikipedia-20221220",
+    "columns": {
+      "prompt": "text"
+    }
+  },
+  "wikipedia_zh": {
+    "hf_hub_url": "pleisto/wikipedia-cn-20230720-filtered",
+    "ms_hub_url": "AI-ModelScope/wikipedia-cn-20230720-filtered",
+    "columns": {
+      "prompt": "completion"
+    }
+  },
+  "pile": {
+    "hf_hub_url": "monology/pile-uncopyrighted",
+    "ms_hub_url": "AI-ModelScope/pile",
+    "columns": {
+      "prompt": "text"
+    }
+  },
+  "skypile": {
+    "hf_hub_url": "Skywork/SkyPile-150B",
+    "ms_hub_url": "AI-ModelScope/SkyPile-150B",
+    "columns": {
+      "prompt": "text"
+    }
+  },
+  "the_stack": {
+    "hf_hub_url": "bigcode/the-stack",
+    "ms_hub_url": "AI-ModelScope/the-stack",
+    "columns": {
+      "prompt": "content"
+    }
+  },
+  "starcoder_python": {
+    "hf_hub_url": "bigcode/starcoderdata",
+    "ms_hub_url": "AI-ModelScope/starcoderdata",
+    "columns": {
+      "prompt": "content"
+    },
+    "folder": "python"
+  }
+}
\ No newline at end of file

finetune/data/mllm_demo.json

+[
+  {
+    "messages": [
+      {
+        "content": "Who are they?",
+        "role": "user"
+      },
+      {
+        "content": "They're Kane and Gretzka from Bayern Munich.",
+        "role": "assistant"
+      },
+      {
+        "content": "What are they doing?",
+        "role": "user"
+      },
+      {
+        "content": "They are celebrating on the soccer field.",
+        "role": "assistant"
+      }
+    ],
+    "images": [
+      "mllm_demo_data/1.jpg"
+    ]
+  },
+  {
+    "messages": [
+      {
+        "content": "Who is he?",
+        "role": "user"
+      },
+      {
+        "content": "He's Thomas Muller from Bayern Munich.",
+        "role": "assistant"
+      },
+      {
+        "content": "Why is he on the ground?",
+        "role": "user"
+      },
+      {
+        "content": "Because he's sliding on his knees to celebrate.",
+        "role": "assistant"
+      }
+    ],
+    "images": [
+      "mllm_demo_data/2.jpg"
+    ]
+  },
+  {
+    "messages": [
+      {
+        "content": "Please describe this image",
+        "role": "user"
+      },
+      {
+        "content": "Chinese astronaut Gui Haichao is giving a speech.",
+        "role": "assistant"
+      },
+      {
+        "content": "What has he accomplished?",
+        "role": "user"
+      },
+      {
+        "content": "He was appointed to be a payload specialist on Shenzhou 16 mission in June 2022, thus becoming the first Chinese civilian of Group 3 in space on 30 May 2023. He is responsible for the on-orbit operation of space science experimental payloads.",
+        "role": "assistant"
+      }
+    ],
+    "images": [
+      "mllm_demo_data/3.jpg"
+    ]
+  },
+  {
+    "messages": [
+      {
+        "content": "他们是谁？",
+        "role": "user"
+      },
+      {
+        "content": "他们是拜仁慕尼黑的凯恩和格雷茨卡。",
+        "role": "assistant"
+      },
+      {
+        "content": "他们在做什么？",
+        "role": "user"
+      },
+      {
+        "content": "他们在足球场上庆祝。",
+        "role": "assistant"
+      }
+    ],
+    "images": [
+      "mllm_demo_data/1.jpg"
+    ]
+  },
+  {
+    "messages": [
+      {
+        "content": "他是谁？",
+        "role": "user"
+      },
+      {
+        "content": "他是来自拜仁慕尼黑的托马斯·穆勒。",
+        "role": "assistant"
+      },
+      {
+        "content": "他为什么在地上？",
+        "role": "user"
+      },
+      {
+        "content": "因为他正在双膝跪地滑行庆祝。",
+        "role": "assistant"
+      }
+    ],
+    "images": [
+      "mllm_demo_data/2.jpg"
+    ]
+  },
+  {
+    "messages": [
+      {
+        "content": "请描述这张图片",
+        "role": "user"
+      },
+      {
+        "content": "中国宇航员桂海潮正在讲话。",
+        "role": "assistant"
+      },
+      {
+        "content": "他取得过哪些成就？",
+        "role": "user"
+      },
+      {
+        "content": "他于2022年6月被任命为神舟十六号任务的有效载荷专家，从而成为2023年5月30日进入太空的首位平民宇航员。他负责在轨操作空间科学实验有效载荷。",
+        "role": "assistant"
+      }
+    ],
+    "images": [
+      "mllm_demo_data/3.jpg"
+    ]
+  }
+]
\ No newline at end of file