update to v0.9.1

27a7ad86 · luopl · 731cf9b8 · 27a7ad86 · 27a7ad86 · 27a7ad86
Commit 27a7ad86 authored Oct 14, 2024 by luopl
20 changed files
--- a/.env.local
+++ b/.env.local
+# Note: actually we do not support .env, just for reference
+# api
+API_HOST=0.0.0.0
+API_PORT=8000
+API_KEY=
+API_MODEL_NAME=gpt-3.5-turbo
+FASTAPI_ROOT_PATH=
+# general
+DISABLE_VERSION_CHECK=
+FORCE_CHECK_IMPORTS=
+LLAMAFACTORY_VERBOSITY=
+USE_MODELSCOPE_HUB=
+RECORD_VRAM=
+# torchrun
+FORCE_TORCHRUN=
+MASTER_ADDR=
+MASTER_PORT=
+NNODES=
+RANK=
+NPROC_PER_NODE=
+# wandb
+WANDB_DISABLED=
+WANDB_PROJECT=huggingface
+WANDB_API_KEY=
+# gradio ui
+GRADIO_SHARE=False
+GRADIO_SERVER_NAME=0.0.0.0
+GRADIO_SERVER_PORT=
+GRADIO_ROOT_PATH=
+# setup
+ENABLE_SHORT_CONSOLE=1
+# reserved (do not use)
+LLAMABOARD_ENABLED=
+LLAMABOARD_WORKDIR=
--- a/Makefile
+++ b/Makefile
 .PHONY: quality style test
-check_dirs := scripts src tests
+check_dirs := scripts src tests setup.py
 quality:
 	ruff check $(check_dirs)

--- a/README.md
+++ b/README.md
--- a/README_zh.md
+++ b/README_zh.md
@@ -26,11 +26,14 @@ https://github.com/user-attachments/assets/e6ce34b0-52d5-4f3e-a830-592106c4c272
 选择你的打开方式：
 - **Colab**：https://colab.research.google.com/drive/1d5KQtbemerlSDSxZIfAaWXhKr30QypiK?usp=sharing
- **PAI-DSW**：https://gallery.pai-ml.com/#/preview/deepLearning/nlp/llama_factory
+- **PAI-DSW**：[Llama3 案例](https://gallery.pai-ml.com/#/preview/deepLearning/nlp/llama_factory) | [Qwen2-VL 案例](https://gallery.pai-ml.com/#/preview/deepLearning/nlp/llama_factory_qwen2vl)
 - **本地机器**：请见[如何使用](#如何使用)
 - **入门教程**：https://zhuanlan.zhihu.com/p/695287607
 - **框架文档**：https://llamafactory.readthedocs.io/zh-cn/latest/
+> [!NOTE]
+> 除上述链接以外的其他网站均为未经许可的第三方网站，请小心甄别。
 ## 目录
 - [项目特色](#项目特色)
@@ -48,11 +51,11 @@ https://github.com/user-attachments/assets/e6ce34b0-52d5-4f3e-a830-592106c4c272
 ## 项目特色
- **多种模型**：LLaMA、LLaVA、Mistral、Mixtral-MoE、Qwen、Yi、Gemma、Baichuan、ChatGLM、Phi 等等。
+- **多种模型**：LLaMA、LLaVA、Mistral、Mixtral-MoE、Qwen、Qwen2-VL、Yi、Gemma、Baichuan、ChatGLM、Phi 等等。
 - **集成方法**：（增量）预训练、（多模态）指令监督微调、奖励模型训练、PPO 训练、DPO 训练、KTO 训练、ORPO 训练等等。
 - **多种精度**：16 比特全参数微调、冻结微调、LoRA 微调和基于 AQLM/AWQ/GPTQ/LLM.int8/HQQ/EETQ 的 2/3/4/5/6/8 比特 QLoRA 微调。
- **先进算法**：GaLore、BAdam、Adam-mini、DoRA、LongLoRA、LLaMA Pro、Mixture-of-Depths、LoRA+、LoftQ、PiSSA 和 Agent 微调。
+- **先进算法**：[GaLore](https://github.com/jiaweizzhao/GaLore)、[BAdam](https://github.com/Ledzy/BAdam)、[Adam-mini](https://github.com/zyushun/Adam-mini)、DoRA、LongLoRA、LLaMA Pro、Mixture-of-Depths、LoRA+、LoftQ、PiSSA 和 Agent 微调。
- **实用技巧**：FlashAttention-2、Unsloth、RoPE scaling、NEFTune 和 rsLoRA。
+- **实用技巧**：[FlashAttention-2](https://github.com/Dao-AILab/flash-attention)、[Unsloth](https://github.com/unslothai/unsloth)、[Liger Kernel](https://github.com/linkedin/Liger-Kernel)、RoPE scaling、NEFTune 和 rsLoRA。
 - **实验监控**：LlamaBoard、TensorBoard、Wandb、MLflow 等等。
 - **极速推理**：基于 vLLM 的 OpenAI 风格 API、浏览器界面和命令行接口。
@@ -73,19 +76,25 @@ https://github.com/user-attachments/assets/e6ce34b0-52d5-4f3e-a830-592106c4c272
 ## 更新日志
-[24/08/09] 我们支持了 **[Adam-mini](https://arxiv.org/abs/2406.16793)** 优化器。详细用法请参照 [examples](examples/README_zh.md)。感谢 [@relic-yuexi](https://github.com/relic-yuexi) 的 PR。
+[24/09/19] 我们支持了 **[Qwen2.5](https://qwenlm.github.io/blog/qwen2.5/)** 模型的微调。
-[24/07/04] 我们支持了[无污染打包训练](https://github.com/MeetKai/functionary/tree/main/functionary/train/packing)。请使用 `neat_packing: true` 参数。感谢 [@chuan298](https://github.com/chuan298) 的 PR。
+[24/08/30] 我们支持了 **[Qwen2-VL](https://qwenlm.github.io/blog/qwen2-vl/)** 模型的微调。感谢 [@simonJJJ](https://github.com/simonJJJ) 的 PR。
-[24/06/16] 我们支持了 **[PiSSA](https://arxiv.org/abs/2404.02948)** 算法。详细用法请参照 [examples](examples/README_zh.md)。
+[24/08/27] 我们支持了 **[Liger Kernel](https://github.com/linkedin/Liger-Kernel)**。请使用 `enable_liger_kernel: true` 来加速训练。
+[24/08/09] 我们支持了 **[Adam-mini](https://github.com/zyushun/Adam-mini)** 优化器。详细用法请参照 [examples](examples/README_zh.md)。感谢 [@relic-yuexi](https://github.com/relic-yuexi) 的 PR。
 <details><summary>展开日志</summary>
+[24/07/04] 我们支持了[无污染打包训练](https://github.com/MeetKai/functionary/tree/main/functionary/train/packing)。请使用 `neat_packing: true` 参数。感谢 [@chuan298](https://github.com/chuan298) 的 PR。
+[24/06/16] 我们支持了 **[PiSSA](https://arxiv.org/abs/2404.02948)** 算法。详细用法请参照 [examples](examples/README_zh.md)。
 [24/06/07] 我们支持了 **[Qwen2](https://qwenlm.github.io/blog/qwen2/)** 和 **[GLM-4](https://github.com/THUDM/GLM-4)** 模型的微调。
 [24/05/26] 我们支持了 **[SimPO](https://arxiv.org/abs/2405.14734)** 偏好对齐算法。详细用法请参照 [examples](examples/README_zh.md)。
-[24/05/20] 我们支持了 **PaliGemma** 系列模型的微调。注意 PaliGemma 是预训练模型，你需要使用 `gemma` 模板进行微调使其获得对话能力。
+[24/05/20] 我们支持了 **PaliGemma** 系列模型的微调。注意 PaliGemma 是预训练模型，你需要使用 `paligemma` 模板进行微调使其获得对话能力。
 [24/05/18] 我们支持了 **[KTO](https://arxiv.org/abs/2402.01306)** 偏好对齐算法。详细用法请参照 [examples](examples/README_zh.md)。
@@ -157,33 +166,36 @@ https://github.com/user-attachments/assets/e6ce34b0-52d5-4f3e-a830-592106c4c272
 ## 模型
-| 模型名                                                            | 模型大小                          | Template  |
+| 模型名                                                            | 模型大小                          | Template         |
-| ----------------------------------------------------------------- | -------------------------------- | --------- |
+| ----------------------------------------------------------------- | -------------------------------- | ---------------- |
-| [Baichuan 2](https://huggingface.co/baichuan-inc)                 | 7B/13B                           | baichuan2 |
+| [Baichuan 2](https://huggingface.co/baichuan-inc)                 | 7B/13B                           | baichuan2        |
-| [BLOOM/BLOOMZ](https://huggingface.co/bigscience)                 | 560M/1.1B/1.7B/3B/7.1B/176B      | -         |
+| [BLOOM/BLOOMZ](https://huggingface.co/bigscience)                 | 560M/1.1B/1.7B/3B/7.1B/176B      | -                |
-| [ChatGLM3](https://huggingface.co/THUDM)                          | 6B                               | chatglm3  |
+| [ChatGLM3](https://huggingface.co/THUDM)                          | 6B                               | chatglm3         |
-| [Command R](https://huggingface.co/CohereForAI)                   | 35B/104B                         | cohere    |
+| [Command R](https://huggingface.co/CohereForAI)                   | 35B/104B                         | cohere           |
-| [DeepSeek (Code/MoE)](https://huggingface.co/deepseek-ai)         | 7B/16B/67B/236B                  | deepseek  |
+| [DeepSeek (Code/MoE)](https://huggingface.co/deepseek-ai)         | 7B/16B/67B/236B                  | deepseek         |
-| [Falcon](https://huggingface.co/tiiuae)                           | 7B/11B/40B/180B                  | falcon    |
+| [Falcon](https://huggingface.co/tiiuae)                           | 7B/11B/40B/180B                  | falcon           |
-| [Gemma/Gemma 2/CodeGemma](https://huggingface.co/google)          | 2B/7B/9B/27B                     | gemma     |
+| [Gemma/Gemma 2/CodeGemma](https://huggingface.co/google)          | 2B/7B/9B/27B                     | gemma            |
-| [GLM-4](https://huggingface.co/THUDM)                             | 9B                               | glm4      |
+| [GLM-4](https://huggingface.co/THUDM)                             | 9B                               | glm4             |
-| [InternLM2/InternLM2.5](https://huggingface.co/internlm)          | 7B/20B                           | intern2   |
+| [InternLM2/InternLM2.5](https://huggingface.co/internlm)          | 7B/20B                           | intern2          |
-| [Llama](https://github.com/facebookresearch/llama)                | 7B/13B/33B/65B                   | -         |
+| [Llama](https://github.com/facebookresearch/llama)                | 7B/13B/33B/65B                   | -                |
-| [Llama 2](https://huggingface.co/meta-llama)                      | 7B/13B/70B                       | llama2    |
+| [Llama 2](https://huggingface.co/meta-llama)                      | 7B/13B/70B                       | llama2           |
-| [Llama 3/Llama 3.1](https://huggingface.co/meta-llama)            | 8B/70B                           | llama3    |
+| [Llama 3-3.2](https://huggingface.co/meta-llama)                  | 1B/3B/8B/70B                     | llama3           |
-| [LLaVA-1.5](https://huggingface.co/llava-hf)                      | 7B/13B                           | vicuna    |
+| [LLaVA-1.5](https://huggingface.co/llava-hf)                      | 7B/13B                           | llava            |
-| [MiniCPM](https://huggingface.co/openbmb)                         | 1B/2B                            | cpm       |
+| [LLaVA-NeXT](https://huggingface.co/llava-hf)                     | 7B/8B/13B/34B/72B/110B           | llava_next       |
-| [Mistral/Mixtral](https://huggingface.co/mistralai)               | 7B/8x7B/8x22B                    | mistral   |
+| [LLaVA-NeXT-Video](https://huggingface.co/llava-hf)               | 7B/34B                           | llava_next_video |
-| [OLMo](https://huggingface.co/allenai)                            | 1B/7B                            | -         |
+| [MiniCPM](https://huggingface.co/openbmb)                         | 1B/2B/4B                         | cpm/cpm3         |
-| [PaliGemma](https://huggingface.co/google)                        | 3B                               | gemma     |
+| [Mistral/Mixtral](https://huggingface.co/mistralai)               | 7B/8x7B/8x22B                    | mistral          |
-| [Phi-1.5/Phi-2](https://huggingface.co/microsoft)                 | 1.3B/2.7B                        | -         |
+| [OLMo](https://huggingface.co/allenai)                            | 1B/7B                            | -                |
-| [Phi-3](https://huggingface.co/microsoft)                         | 4B/7B/14B                        | phi       |
+| [PaliGemma](https://huggingface.co/google)                        | 3B                               | paligemma        |
-| [Qwen/Qwen1.5/Qwen2 (Code/Math/MoE)](https://huggingface.co/Qwen) | 0.5B/1.5B/4B/7B/14B/32B/72B/110B | qwen      |
+| [Phi-1.5/Phi-2](https://huggingface.co/microsoft)                 | 1.3B/2.7B                        | -                |
-| [StarCoder 2](https://huggingface.co/bigcode)                     | 3B/7B/15B                        | -         |
+| [Phi-3](https://huggingface.co/microsoft)                         | 4B/7B/14B                        | phi              |
-| [XVERSE](https://huggingface.co/xverse)                           | 7B/13B/65B                       | xverse    |
+| [Qwen (1-2.5) (Code/Math/MoE)](https://huggingface.co/Qwen)       | 0.5B/1.5B/3B/7B/14B/32B/72B/110B | qwen             |
-| [Yi/Yi-1.5](https://huggingface.co/01-ai)                         | 6B/9B/34B                        | yi        |
+| [Qwen2-VL](https://huggingface.co/Qwen)                           | 2B/7B/72B                        | qwen2_vl         |
-| [Yi-VL](https://huggingface.co/01-ai)                             | 6B/34B                           | yi_vl     |
+| [StarCoder 2](https://huggingface.co/bigcode)                     | 3B/7B/15B                        | -                |
-| [Yuan 2](https://huggingface.co/IEITYuan)                         | 2B/51B/102B                      | yuan      |
+| [XVERSE](https://huggingface.co/xverse)                           | 7B/13B/65B                       | xverse           |
+| [Yi/Yi-1.5 (Code)](https://huggingface.co/01-ai)                  | 1.5B/6B/9B/34B                   | yi               |
+| [Yi-VL](https://huggingface.co/01-ai)                             | 6B/34B                           | yi_vl            |
+| [Yuan 2](https://huggingface.co/IEITYuan)                         | 2B/51B/102B                      | yuan             |
 > [!NOTE]
 > 对于所有“基座”（Base）模型，`template` 参数可以是 `default`, `alpaca`, `vicuna` 等任意值。但“对话”（Instruct/Chat）模型请务必使用**对应的模板**。
@@ -271,6 +283,7 @@ https://github.com/user-attachments/assets/e6ce34b0-52d5-4f3e-a830-592106c4c272
 - [Magpie-Pro-300K-Filtered (en)](https://huggingface.co/datasets/Magpie-Align/Magpie-Pro-300K-Filtered)
 - [Magpie-ultra-v0.1 (en)](https://huggingface.co/datasets/argilla/magpie-ultra-v0.1)
 - [LLaVA mixed (en&zh)](https://huggingface.co/datasets/BUAADreamer/llava-en-zh-300k)
+- [Pokemon-gpt4o-captions (en&zh)](https://huggingface.co/datasets/jugg1024/pokemon-gpt4o-captions)
 - [Open Assistant (de)](https://huggingface.co/datasets/mayflowergmbh/oasst_de)
 - [Dolly 15k (de)](https://huggingface.co/datasets/mayflowergmbh/dolly-15k_de)
 - [Alpaca GPT4 (de)](https://huggingface.co/datasets/mayflowergmbh/alpaca-gpt4_de)
@@ -287,6 +300,8 @@ https://github.com/user-attachments/assets/e6ce34b0-52d5-4f3e-a830-592106c4c272
 - [DPO mixed (en&zh)](https://huggingface.co/datasets/hiyouga/DPO-En-Zh-20k)
 - [UltraFeedback (en)](https://huggingface.co/datasets/HuggingFaceH4/ultrafeedback_binarized)
+- [RLHF-V (en)](https://huggingface.co/datasets/openbmb/RLHF-V-Dataset)
+- [VLFeedback (en)](https://huggingface.co/datasets/Zhihui/VLFeedback)
 - [Orca DPO Pairs (en)](https://huggingface.co/datasets/Intel/orca_dpo_pairs)
 - [HH-RLHF (en)](https://huggingface.co/datasets/Anthropic/hh-rlhf)
 - [Nectar (en)](https://huggingface.co/datasets/berkeley-nest/Nectar)
@@ -349,7 +364,7 @@ cd LLaMA-Factory
 pip install -e ".[torch,metrics]"
 ```
-可选的额外依赖项：torch、torch-npu、metrics、deepspeed、bitsandbytes、hqq、eetq、gptq、awq、aqlm、vllm、galore、badam、adam-mini、qwen、modelscope、quality
+可选的额外依赖项：torch、torch-npu、metrics、deepspeed、liger-kernel、bitsandbytes、hqq、eetq、gptq、awq、aqlm、vllm、galore、badam、adam-mini、qwen、modelscope、quality
 > [!TIP]
 > 遇到包冲突时，可使用 `pip install --no-deps -e .` 解决。

--- a/assets/wechat.jpg
+++ b/assets/wechat.jpg
--- a/assets/wechat_npu.jpg
+++ b/assets/wechat_npu.jpg
--- a/data/README.md
+++ b/data/README.md
@@ -23,6 +23,7 @@ Currently we support datasets in **alpaca** and **sharegpt** format.
    "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)",
+    "videos": "the column name in the dataset containing the videos 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)"
@@ -107,7 +108,7 @@ Regarding the above dataset, the *dataset description* in `dataset_info.json` sh
 ### Preference Dataset
-Preference datasets are used for reward modeling, DPO training and ORPO training.
+Preference datasets are used for reward modeling, DPO training, ORPO and SimPO training.
 It requires a better response in `chosen` column and a worse response in `rejected` column.
@@ -139,67 +140,15 @@ Regarding the above dataset, the *dataset description* in `dataset_info.json` sh
 ### KTO Dataset
- [Example dataset](kto_en_demo.json)
+An additional column `kto_tag` is required. Please refer to the [sharegpt](#sharegpt-format) format for details.
-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 Image Dataset
-Multimodal datasets require a `images` column containing the paths to the input images. Currently we only support one image.
+An additional column `images` is required. Please refer to the [sharegpt](#sharegpt-format) format for details.
-```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:
+### Multimodal Video Dataset
-```json
+An additional column `videos` is required. Please refer to the [sharegpt](#sharegpt-format) format for details.
-"dataset_name": {
-  "file_name": "data.json",
-  "columns": {
-    "prompt": "instruction",
-    "query": "input",
-    "response": "output",
-    "images": "images"
-  }
-}
-```
 ## Sharegpt Format
@@ -252,6 +201,10 @@ Regarding the above dataset, the *dataset description* in `dataset_info.json` sh
 }
 ```
+### Pre-training Dataset
+Not yet supported, please use the [alpaca](#alpaca-format) format.
 ### Preference Dataset
 - [Example dataset](dpo_en_demo.json)
@@ -302,6 +255,125 @@ Regarding the above dataset, the *dataset description* in `dataset_info.json` sh
 }
 ```
+### KTO Dataset
+- [Example dataset](kto_en_demo.json)
+KTO datasets require a extra `kto_tag` column containing the boolean human feedback.
+```json
+[
+  {
+    "conversations": [
+      {
+        "from": "human",
+        "value": "human instruction"
+      },
+      {
+        "from": "gpt",
+        "value": "model response"
+      }
+    ],
+    "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",
+  "formatting": "sharegpt",
+  "columns": {
+    "messages": "conversations",
+    "kto_tag": "kto_tag"
+  }
+}
+```
+### Multimodal Image Dataset
+- [Example dataset](mllm_demo.json)
+Multimodal image datasets require a `images` column containing the paths to the input images.
+The number of images should be identical to the `<image>` tokens in the conversations.
+```json
+[
+  {
+    "conversations": [
+      {
+        "from": "human",
+        "value": "<image>human instruction"
+      },
+      {
+        "from": "gpt",
+        "value": "model response"
+      }
+    ],
+    "images": [
+      "image path (required)"
+    ]
+  }
+]
+```
+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",
+    "images": "images"
+  }
+}
+```
+### Multimodal Video Dataset
+- [Example dataset](mllm_video_demo.json)
+Multimodal video datasets require a `videos` column containing the paths to the input videos.
+The number of videos should be identical to the `<video>` tokens in the conversations.
+```json
+[
+  {
+    "conversations": [
+      {
+        "from": "human",
+        "value": "<video>human instruction"
+      },
+      {
+        "from": "gpt",
+        "value": "model response"
+      }
+    ],
+    "videos": [
+      "video path (required)"
+    ]
+  }
+]
+```
+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",
+    "videos": "videos"
+  }
+}
+```
 ### OpenAI Format
 The openai format is simply a special case of the sharegpt format, where the first message may be a system prompt.
@@ -345,7 +417,3 @@ Regarding the above dataset, the *dataset description* in `dataset_info.json` sh
  }
 }
 ```
-The KTO datasets and multimodal datasets in sharegpt format are similar to the alpaca format.
-Pre-training datasets are **incompatible** with the sharegpt format.
--- a/data/README_zh.md
+++ b/data/README_zh.md
@@ -23,6 +23,7 @@
    "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）",
+    "videos": "数据集代表视频输入的表头名称（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）"
@@ -107,7 +108,7 @@
 ### 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。
+偏好数据集用于奖励模型训练、DPO 训练、ORPO 训练和 SimPO 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。
@@ -139,67 +140,15 @@
 ### KTO 数据集
- [样例数据集](kto_en_demo.json)
+KTO 数据集需要提供额外的 `kto_tag` 列。详情请参阅 [sharegpt](#sharegpt-格式)。
-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)
+### 多模态图像数据集
-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。
+多模态图像数据集需要提供额外的 `images` 列。详情请参阅 [sharegpt](#sharegpt-格式)。
-```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：
+### 多模态视频数据集
-```json
+多模态视频数据集需要提供额外的 `videos` 列。详情请参阅 [sharegpt](#sharegpt-格式)。
-"数据集名称": {
-  "file_name": "data.json",
-  "columns": {
-    "prompt": "instruction",
-    "query": "input",
-    "response": "output",
-    "images": "images"
-  }
-}
-```
 ## Sharegpt 格式
@@ -252,6 +201,10 @@ KTO 数据集需要额外添加一个 `kto_tag` 列，包含 bool 类型的人
 }
 ```
+### 预训练数据集
+尚不支持，请使用 [alpaca](#alpaca-格式) 格式。
 ### 偏好数据集
 - [样例数据集](dpo_zh_demo.json)
@@ -302,6 +255,125 @@ Sharegpt 格式的偏好数据集同样需要在 `chosen` 列中提供更优的
 }
 ```
+### 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
+[
+  {
+    "conversations": [
+      {
+        "from": "human",
+        "value": "人类指令"
+      },
+      {
+        "from": "gpt",
+        "value": "模型回答"
+      }
+    ],
+    "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",
+  "formatting": "sharegpt",
+  "columns": {
+    "messages": "conversations",
+    "kto_tag": "kto_tag"
+  }
+}
+```
+### 多模态图像数据集
+- [样例数据集](mllm_demo.json)
+多模态图像数据集需要额外添加一个 `images` 列，包含输入图像的路径。
+注意图片的数量必须与文本中所有 `<image>` 标记的数量严格一致。
+```json
+[
+  {
+    "conversations": [
+      {
+        "from": "human",
+        "value": "<image>人类指令"
+      },
+      {
+        "from": "gpt",
+        "value": "模型回答"
+      }
+    ],
+    "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",
+  "formatting": "sharegpt",
+  "columns": {
+    "messages": "conversations",
+    "images": "images"
+  }
+}
+```
+### 多模态视频数据集
+- [样例数据集](mllm_video_demo.json)
+多模态视频数据集需要额外添加一个 `videos` 列，包含输入视频的路径。
+注意视频的数量必须与文本中所有 `<video>` 标记的数量严格一致。
+```json
+[
+  {
+    "conversations": [
+      {
+        "from": "human",
+        "value": "<video>人类指令"
+      },
+      {
+        "from": "gpt",
+        "value": "模型回答"
+      }
+    ],
+    "videos": [
+      "视频路径（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",
+  "formatting": "sharegpt",
+  "columns": {
+    "messages": "conversations",
+    "videos": "videos"
+  }
+}
+```
 ### 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。
@@ -345,7 +417,3 @@ OpenAI 格式仅仅是 sharegpt 格式的一种特殊情况，其中第一条消
  }
 }
 ```
-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。
--- a/data/dataset_info.json
+++ b/data/dataset_info.json
@@ -38,6 +38,20 @@
      "assistant_tag": "assistant"
    }
  },
+  "mllm_video_demo": {
+    "file_name": "mllm_video_demo.json",
+    "formatting": "sharegpt",
+    "columns": {
+      "messages": "messages",
+      "videos": "videos"
+    },
+    "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"
@@ -340,6 +354,14 @@
      "assistant_tag": "assistant"
    }
  },
+  "pokemon_cap": {
+    "hf_hub_url": "llamafactory/pokemon-gpt4o-captions",
+    "formatting": "sharegpt",
+    "columns": {
+      "messages": "conversations",
+      "images": "images"
+    }
+  },
  "mllm_pt_demo": {
    "hf_hub_url": "BUAADreamer/mllm_pt_demo",
    "formatting": "sharegpt",
@@ -433,6 +455,28 @@
      "rejected": "rejected"
    }
  },
+  "rlhf_v": {
+    "hf_hub_url": "llamafactory/RLHF-V",
+    "ranking": true,
+    "formatting": "sharegpt",
+    "columns": {
+      "messages": "conversations",
+      "chosen": "chosen",
+      "rejected": "rejected",
+      "images": "images"
+    }
+  },
+  "vlfeedback": {
+    "hf_hub_url": "Zhihui/VLFeedback",
+    "ranking": true,
+    "formatting": "sharegpt",
+    "columns": {
+      "messages": "conversations",
+      "chosen": "chosen",
+      "rejected": "rejected",
+      "images": "images"
+    }
+  },
  "orca_pairs": {
    "hf_hub_url": "Intel/orca_dpo_pairs",
    "ranking": true,

--- a/data/mllm_demo.json
+++ b/data/mllm_demo.json
@@ -2,7 +2,7 @@
  {
    "messages": [
      {
-        "content": "Who are they?",
+        "content": "<image>Who are they?",
        "role": "user"
      },
      {
@@ -25,7 +25,7 @@
  {
    "messages": [
      {
-        "content": "Who is he?",
+        "content": "<image>Who is he?",
        "role": "user"
      },
      {
@@ -48,7 +48,7 @@
  {
    "messages": [
      {
-        "content": "Please describe this image",
+        "content": "<image>Please describe this image",
        "role": "user"
      },
      {
@@ -71,7 +71,7 @@
  {
    "messages": [
      {
-        "content": "他们是谁？",
+        "content": "<image>他们是谁？",
        "role": "user"
      },
      {
@@ -94,7 +94,7 @@
  {
    "messages": [
      {
-        "content": "他是谁？",
+        "content": "<image>他是谁？",
        "role": "user"
      },
      {
@@ -117,7 +117,7 @@
  {
    "messages": [
      {
-        "content": "请描述这张图片",
+        "content": "<image>请描述这张图片",
        "role": "user"
      },
      {

--- a/data/mllm_demo_data/1.mp4
+++ b/data/mllm_demo_data/1.mp4
--- a/data/mllm_demo_data/2.avi
+++ b/data/mllm_demo_data/2.avi
--- a/data/mllm_demo_data/3.mp4
+++ b/data/mllm_demo_data/3.mp4
--- a/data/mllm_video_demo.json
+++ b/data/mllm_video_demo.json
+[
+  {
+    "messages": [
+      {
+        "content": "<video>Why is this video funny?",
+        "role": "user"
+      },
+      {
+        "content": "Because a baby is reading, and he is so cute!",
+        "role": "assistant"
+      }
+    ],
+    "videos": [
+      "mllm_demo_data/1.mp4"
+    ]
+  },
+  {
+    "messages": [
+      {
+        "content": "<video>What is she doing?",
+        "role": "user"
+      },
+      {
+        "content": "She is cooking.",
+        "role": "assistant"
+      }
+    ],
+    "videos": [
+      "mllm_demo_data/2.avi"
+    ]
+  },
+  {
+    "messages": [
+      {
+        "content": "<video>What's in the video?",
+        "role": "user"
+      },
+      {
+        "content": "A baby is playing in the living room.",
+        "role": "assistant"
+      }
+    ],
+    "videos": [
+      "mllm_demo_data/3.mp4"
+    ]
+  }
+]
\ No newline at end of file
--- a/docker/docker-cuda/Dockerfile
+++ b/docker/docker-cuda/Dockerfile
+# Use the NVIDIA official image with PyTorch 2.3.0
+# https://docs.nvidia.com/deeplearning/frameworks/pytorch-release-notes/rel-24-02.html
+FROM nvcr.io/nvidia/pytorch:24.02-py3
+# Define environments
+ENV MAX_JOBS=4
+ENV FLASH_ATTENTION_FORCE_BUILD=TRUE
+ENV VLLM_WORKER_MULTIPROC_METHOD=spawn
+# Define installation arguments
+ARG INSTALL_BNB=false
+ARG INSTALL_VLLM=false
+ARG INSTALL_DEEPSPEED=false
+ARG INSTALL_FLASHATTN=false
+ARG INSTALL_LIGER_KERNEL=false
+ARG INSTALL_HQQ=false
+ARG INSTALL_EETQ=false
+ARG PIP_INDEX=https://pypi.org/simple
+# Set the working directory
+WORKDIR /app
+# Install the requirements
+COPY requirements.txt /app
+RUN pip config set global.index-url "$PIP_INDEX" && \
+    pip config set global.extra-index-url "$PIP_INDEX" && \
+    python -m pip install --upgrade pip && \
+    python -m pip install -r requirements.txt
+# Copy the rest of the application into the image
+COPY . /app
+# Install the LLaMA Factory
+RUN EXTRA_PACKAGES="metrics"; \
+    if [ "$INSTALL_BNB" == "true" ]; then \
+        EXTRA_PACKAGES="${EXTRA_PACKAGES},bitsandbytes"; \
+    fi; \
+    if [ "$INSTALL_VLLM" == "true" ]; then \
+        EXTRA_PACKAGES="${EXTRA_PACKAGES},vllm"; \
+    fi; \
+    if [ "$INSTALL_DEEPSPEED" == "true" ]; then \
+        EXTRA_PACKAGES="${EXTRA_PACKAGES},deepspeed"; \
+    fi; \
+    if [ "$INSTALL_LIGER_KERNEL" == "true" ]; then \
+        EXTRA_PACKAGES="${EXTRA_PACKAGES},liger-kernel"; \
+    fi; \
+    if [ "$INSTALL_HQQ" == "true" ]; then \
+        EXTRA_PACKAGES="${EXTRA_PACKAGES},hqq"; \
+    fi; \
+    if [ "$INSTALL_EETQ" == "true" ]; then \
+        EXTRA_PACKAGES="${EXTRA_PACKAGES},eetq"; \
+    fi; \
+    pip install -e ".[$EXTRA_PACKAGES]"
+# Rebuild flash attention
+RUN pip uninstall -y transformer-engine flash-attn && \
+    if [ "$INSTALL_FLASHATTN" == "true" ]; then \
+        pip uninstall -y ninja && pip install ninja && \
+        pip install --no-cache-dir flash-attn --no-build-isolation; \
+    fi
+# Set up volumes
+VOLUME [ "/root/.cache/huggingface", "/root/.cache/modelscope", "/app/data", "/app/output" ]
+# Expose port 7860 for the LLaMA Board
+ENV GRADIO_SERVER_PORT 7860
+EXPOSE 7860
+# Expose port 8000 for the API service
+ENV API_PORT 8000
+EXPOSE 8000
--- a/docker/docker-cuda/docker-compose.yml
+++ b/docker/docker-cuda/docker-compose.yml
+services:
+  llamafactory:
+    build:
+      dockerfile: ./docker/docker-cuda/Dockerfile
+      context: ../..
+      args:
+        INSTALL_BNB: false
+        INSTALL_VLLM: false
+        INSTALL_DEEPSPEED: false
+        INSTALL_FLASHATTN: false
+        INSTALL_LIGER_KERNEL: false
+        INSTALL_HQQ: false
+        INSTALL_EETQ: false
+        PIP_INDEX: https://pypi.org/simple
+    container_name: llamafactory
+    volumes:
+      - ../../hf_cache:/root/.cache/huggingface
+      - ../../ms_cache:/root/.cache/modelscope
+      - ../../data:/app/data
+      - ../../output:/app/output
+    ports:
+      - "7860:7860"
+      - "8000:8000"
+    ipc: host
+    tty: true
+    stdin_open: true
+    command: bash
+    deploy:
+      resources:
+        reservations:
+          devices:
+          - driver: nvidia
+            count: "all"
+            capabilities: [gpu]
+    restart: unless-stopped
--- a/docker/docker-npu/Dockerfile
+++ b/docker/docker-npu/Dockerfile
+# Use the Ubuntu 22.04 image with CANN 8.0.rc1
+# More versions can be found at https://hub.docker.com/r/ascendai/cann/tags
+# FROM ascendai/cann:8.0.rc1-910-ubuntu22.04-py3.8
+FROM ascendai/cann:8.0.rc1-910b-ubuntu22.04-py3.8
+# FROM ascendai/cann:8.0.rc1-910-openeuler22.03-py3.8
+# FROM ascendai/cann:8.0.rc1-910b-openeuler22.03-py3.8
+# Define environments
+ENV DEBIAN_FRONTEND=noninteractive
+# Define installation arguments
+ARG INSTALL_DEEPSPEED=false
+ARG PIP_INDEX=https://pypi.org/simple
+ARG TORCH_INDEX=https://download.pytorch.org/whl/cpu
+# Set the working directory
+WORKDIR /app
+# Install the requirements
+COPY requirements.txt /app
+RUN pip config set global.index-url "$PIP_INDEX" && \
+    pip config set global.extra-index-url "$TORCH_INDEX" && \
+    python -m pip install --upgrade pip && \
+    python -m pip install -r requirements.txt
+# Copy the rest of the application into the image
+COPY . /app
+# Install the LLaMA Factory
+RUN EXTRA_PACKAGES="torch-npu,metrics"; \
+    if [ "$INSTALL_DEEPSPEED" == "true" ]; then \
+        EXTRA_PACKAGES="${EXTRA_PACKAGES},deepspeed"; \
+    fi; \
+    pip install -e ".[$EXTRA_PACKAGES]"
+# Set up volumes
+VOLUME [ "/root/.cache/huggingface", "/root/.cache/modelscope", "/app/data", "/app/output" ]
+# Expose port 7860 for the LLaMA Board
+ENV GRADIO_SERVER_PORT 7860
+EXPOSE 7860
+# Expose port 8000 for the API service
+ENV API_PORT 8000
+EXPOSE 8000
--- a/docker/docker-npu/docker-compose.yml
+++ b/docker/docker-npu/docker-compose.yml
+services:
+  llamafactory:
+    build:
+      dockerfile: ./docker/docker-npu/Dockerfile
+      context: ../..
+      args:
+        INSTALL_DEEPSPEED: false
+        PIP_INDEX: https://pypi.org/simple
+    container_name: llamafactory
+    volumes:
+      - ../../hf_cache:/root/.cache/huggingface
+      - ../../ms_cache:/root/.cache/modelscope
+      - ../../data:/app/data
+      - ../../output:/app/output
+      - /usr/local/dcmi:/usr/local/dcmi
+      - /usr/local/bin/npu-smi:/usr/local/bin/npu-smi
+      - /usr/local/Ascend/driver:/usr/local/Ascend/driver
+      - /etc/ascend_install.info:/etc/ascend_install.info
+    ports:
+      - "7860:7860"
+      - "8000:8000"
+    ipc: host
+    tty: true
+    stdin_open: true
+    command: bash
+    devices:
+      - /dev/davinci0
+      - /dev/davinci_manager
+      - /dev/devmm_svm
+      - /dev/hisi_hdc
+    restart: unless-stopped
--- a/docker/docker-rocm/Dockerfile
+++ b/docker/docker-rocm/Dockerfile
+FROM hardandheavy/transformers-rocm:2.2.0
+# Define environments
+ENV MAX_JOBS=4
+ENV FLASH_ATTENTION_FORCE_BUILD=TRUE
+ENV VLLM_WORKER_MULTIPROC_METHOD=spawn
+# Define installation arguments
+ARG INSTALL_BNB=false
+ARG INSTALL_VLLM=false
+ARG INSTALL_DEEPSPEED=false
+ARG INSTALL_FLASHATTN=false
+ARG INSTALL_LIGER_KERNEL=false
+ARG INSTALL_HQQ=false
+ARG PIP_INDEX=https://pypi.org/simple
+# Set the working directory
+WORKDIR /app
+# Install the requirements
+COPY requirements.txt /app
+RUN pip config set global.index-url "$PIP_INDEX" && \
+    pip config set global.extra-index-url "$PIP_INDEX" && \
+    python -m pip install --upgrade pip && \
+    python -m pip install -r requirements.txt
+# Copy the rest of the application into the image
+COPY . /app
+# Install the LLaMA Factory
+RUN EXTRA_PACKAGES="metrics"; \
+    if [ "$INSTALL_BNB" == "true" ]; then \
+        EXTRA_PACKAGES="${EXTRA_PACKAGES},bitsandbytes"; \
+    fi; \
+    if [ "$INSTALL_VLLM" == "true" ]; then \
+        EXTRA_PACKAGES="${EXTRA_PACKAGES},vllm"; \
+    fi; \
+    if [ "$INSTALL_DEEPSPEED" == "true" ]; then \
+        EXTRA_PACKAGES="${EXTRA_PACKAGES},deepspeed"; \
+    fi; \
+    if [ "$INSTALL_LIGER_KERNEL" == "true" ]; then \
+        EXTRA_PACKAGES="${EXTRA_PACKAGES},liger-kernel"; \
+    fi; \
+    if [ "$INSTALL_HQQ" == "true" ]; then \
+        EXTRA_PACKAGES="${EXTRA_PACKAGES},hqq"; \
+    fi; \
+    pip install -e ".[$EXTRA_PACKAGES]"
+# Rebuild flash attention
+RUN pip uninstall -y transformer-engine flash-attn && \
+    if [ "$INSTALL_FLASHATTN" == "true" ]; then \
+        pip uninstall -y ninja && pip install ninja && \
+        pip install --no-cache-dir flash-attn --no-build-isolation; \
+    fi
+# Set up volumes
+VOLUME [ "/root/.cache/huggingface", "/root/.cache/modelscope", "/app/data", "/app/output" ]
+# Expose port 7860 for the LLaMA Board
+ENV GRADIO_SERVER_PORT 7860
+EXPOSE 7860
+# Expose port 8000 for the API service
+ENV API_PORT 8000
+EXPOSE 8000
--- a/docker/docker-rocm/docker-compose.yml
+++ b/docker/docker-rocm/docker-compose.yml
+services:
+  llamafactory:
+    build:
+      dockerfile: ./docker/docker-rocm/Dockerfile
+      context: ../..
+      args:
+        INSTALL_BNB: false
+        INSTALL_VLLM: false
+        INSTALL_DEEPSPEED: false
+        INSTALL_FLASHATTN: false
+        INSTALL_LIGER_KERNEL: false
+        INSTALL_HQQ: false
+        PIP_INDEX: https://pypi.org/simple
+    container_name: llamafactory
+    volumes:
+      - ../../hf_cache:/root/.cache/huggingface
+      - ../../ms_cache:/root/.cache/modelscope
+      - ../../data:/app/data
+      - ../../output:/app/output
+      - ../../saves:/app/saves
+    ports:
+      - "7860:7860"
+      - "8000:8000"
+    ipc: host
+    tty: true
+    stdin_open: true
+    command: bash
+    devices:
+      - /dev/kfd:/dev/kfd
+      - /dev/dri:/dev/dri
+    restart: unless-stopped