Merge commit 'ca4d2f6ecef44df77289a02d3927b014a25bacac' into fix/packing

* commit 'ca4d2f6ecef44df77289a02d3927b014a25bacac': (29 commits)
  update wechat (modelscope#1071)
  Support glm4 (modelscope#1069)
  fix argument (modelscope#1066)
  ✏️ fix typo (modelscope#1064)
  Fix citest test_run.py (modelscope#1059)
  fix deepseek-vl template (modelscope#1057)
  fix vllm==0.4.3 (modelscope#1055)
  Fix mini-internvl-4b  (modelscope#1054)
  fix mini-internvl-4b (modelscope#1053)
  support sharegpt dataset format (modelscope#1052)
  fix deepseek-vl (modelscope#1046)
  update arguments (modelscope#1044)
  update arguments (modelscope#1043)
  fix phi3-vision bug
  fix phi3-vision bug (modelscope#1039)
  bump version
  Support SimPO Algorithm (modelscope#1037)
  support multimodal deploy (modelscope#1029)
  support mini-internvl (modelscope#1032)
  fix bugs (modelscope#1038)
  ...

# Conflicts:
#	swift/llm/sft.py

Author: tastelikefeet

README.md

@@ -47,6 +47,10 @@ SWIFT has rich documentations for users, please check [here](https://github.com/
 SWIFT web-ui is available both on [Huggingface space](https://huggingface.co/spaces/tastelikefeet/swift) and [ModelScope studio](https://www.modelscope.cn/studios/iic/Scalable-lightWeight-Infrastructure-for-Fine-Tuning/summary), please feel free to try!
 
 ## 🎉 News
+- 🔥2024.06.05: Support for **glm4** series LLM and glm4v-9b-chat MLLM. You can refer to [glm4v best practice](docs/source/Multi-Modal/glm4v最佳实践.md).
+- 🔥2024.06.01: Supoprts **SimPO** training! See [document](https://github.com/modelscope/swift/blob/main/docs/source_en/LLM/SimPO.md) to start training!
+- 🔥2024.06.01: Support for deploying large multimodal models, please refer to the [Multimodal Deployment Documentation](docs/source_en/Multi-Modal/mutlimodal-deployment.md) for more information.
+- 2024.05.31: Supports Mini-Internvl model, Use model_type `mini-internvl-chat-2b-v1_5` and `mini-internvl-chat-4b-v1_5`to train.
 - 2024.05.24: Supports Phi3-vision model, Use model_type `phi3-vision-128k-instruct` to train.
 - 2024.05.22: Supports DeepSeek-V2-Lite series models, model_type are `deepseek-v2-lite` and `deepseek-v2-lite-chat`
 - 2024.05.22: Supports TeleChat-12B-v2 model with quantized version, model_type are `telechat-12b-v2` and `telechat-12b-v2-gptq-int4`
@@ -233,7 +237,7 @@ You can refer to the following scripts to customize your own training script.
 |------------------|-------------------------------------------------------------------------------|
 | Pretraining      | Text Generation                                                               |
 | Fine-tuning      | Single-turn/Multi-turn<br>Agent Training/Self-cognition<br>Multi-modal Vision/Multi-modal Speech|
-| Human Alignment  | DPO<br>ORPO                                                                   |
+| Human Alignment  | DPO<br>ORPO<br>SimPO                                                          |
 | Text-to-Image    | DreamBooth, etc.                                                              |
 | Text-to-Video    | -                                                                             |
 
@@ -533,9 +537,10 @@ The complete list of supported models and datasets can be found at [Supported Mo
 | Llava              | [Llava series models](https://github.com/haotian-liu/LLaVA)                  | English            | 7B-34B                             | chat model |
 | Llava-Next              | [Llava-Next series models](https://github.com/LLaVA-VL/LLaVA-NeXT)                  | Chinese<br>English | 8B-110B                             | chat model |
 | mPLUG-Owl          | [mPLUG-Owl series models](https://github.com/X-PLUG/mPLUG-Owl)               | English            | 11B                                | chat model |
-| InternVL           | [InternVL](https://github.com/OpenGVLab/InternVL)                            | Chinese<br>English | 25.5B<br>including quantized version                              | chat model |
+| InternVL           | [InternVL](https://github.com/OpenGVLab/InternVL)                            | Chinese<br>English | 2B-25.5B<br>including quantized version                              | chat model |
 | Llava-llama3       | [xtuner](https://huggingface.co/xtuner/llava-llama-3-8b-v1_1-transformers)   | English            | 8B                                 | chat model |
-| Phi3                                      | Microsoft                                                                  | English            | 4B              | chat model |
+| Phi3-Vision                                      | Microsoft                        | English            | 4B              | chat model |
+| PaliGemma                                  | Google              | English | 3B              | chat model |
 
 #### Diffusion Models
 
@@ -612,8 +617,6 @@ make docs
 | [LLM Evaluation](docs/source_en/LLM/LLM-eval.md)     |
 | [LLM Quantization](docs/source_en/LLM/LLM-quantization.md)   |
 | [LLM Deployment](docs/source_en/LLM/VLLM-inference-acceleration-and-deployment.md) |
-| [DPO Human Alignment Training](docs/source_en/LLM/DPO.md)   |
-| [ORPO Human Alignment Training](docs/source_en/LLM/ORPO.md)   |
 | [AnimateDiff Training](docs/source_en/AIGC/AnimateDiff-train-infer.md) |
 
 ### Reference Documentation
@@ -634,6 +637,9 @@ make docs
 |  [Qwen1.5 Best Practice](docs/source_en/LLM/Qwen1.5-best-practice.md) |
 |  [Multi-Modal Model Training Best Practice](docs/source_en/Multi-Modal/index.md) |
 |  [NPU Best Practice](docs/source_en/LLM/NPU-best-practice.md) |
+| [DPO Human Alignment Training](docs/source_en/LLM/DPO.md)   |
+| [ORPO Human Alignment Training](docs/source_en/LLM/ORPO.md)   |
+| [SimPO Human Alignment Training](docs/source_en/LLM/SimPO.md)   |
 
 
 ### Deep Learning Tutorials

README_CN.md

@@ -48,6 +48,10 @@ SWIFT具有丰富的文档体系，如有使用问题请请查看[这里](https:
 可以在[Huggingface space](https://huggingface.co/spaces/tastelikefeet/swift) 和 [ModelScope创空间](https://www.modelscope.cn/studios/iic/Scalable-lightWeight-Infrastructure-for-Fine-Tuning/summary) 中体验SWIFT web-ui功能了。
 
 ## 🎉 新闻
+- 🔥2024.06.05: 支持glm4系列大模型和glm4v-9b-chat多模态大模型, 可以查看[glm4v最佳实践](docs/source/Multi-Modal/glm4v最佳实践.md).
+- 🔥2024.06.01: 支持**SimPO**训练，使用`swift simpo`来开始训练，最佳实践可以查看[这里](https://github.com/modelscope/swift/tree/main/docs/source/LLM/SimPO算法最佳实践.md)
+- 🔥2024.06.01: 支持多模态大模型部署, 可以查看[多模态部署文档](docs/source/Multi-Modal/MLLM部署文档.md).
+- 2024.05.31: 支持Mini-Internvl多模态模型, 使用model_type `mini-internvl-chat-2b-v1_5`和`mini-internvl-chat-4b-v1_5`来训练.
 - 2024.05.24: 支持Phi3多模态模型, 使用model_type `phi3-vision-128k-instruct`来训练.
 - 2024.05.22: 支持DeepSeek-V2-lite系列模型, model_type为 `deepseek-v2-lite`和`deekseek-v2-lite-chat`
 - 2024.05.22: 支持TeleChat-12b-v2模型和量化版本, model_type为 `telechat-12b-v2`和`telechat-12b-v2-gptq-int4`
@@ -59,7 +63,7 @@ SWIFT具有丰富的文档体系，如有使用问题请请查看[这里](https:
 - 2024.05.11: 支持使用[hqq](https://github.com/mobiusml/hqq)和[eetq](https://github.com/NetEase-FuXi/EETQ)进行qlora训练和量化推理，可以查看[LLM量化文档](https://github.com/modelscope/swift/tree/main/docs/source/LLM/LLM量化文档.md)
 - 2024.05.10: 支持序列并行. 先安装`pip install .[seq_parallel]`, 之后在DDP环境中添加`--sequence_parallel_size n`即可使用!
 - 2024.05.08: 支持DeepSeek-V2-Chat模型, 训练参考[这个脚本](https://github.com/modelscope/swift/blob/main/examples/pytorch/llm/scripts/deepseek-v2-chat/lora_ddp_ds3/sft.sh)。支持InternVL-Chat-V1.5-Int8模型，最佳实践参考[这里](https://github.com/modelscope/swift/tree/main/docs/source/Multi-Modal/internvl最佳实践.md).
-- 🔥2024.05.07: 支持**ORPO**训练，使用`swift orpo`来开始使用， 最佳实践可以查看[这里](https://github.com/modelscope/swift/tree/main/docs/source/LLM/ORPO算法最佳实践.md)
+- 🔥2024.05.07: 支持**ORPO**训练，使用`swift orpo`来开始训练， 最佳实践可以查看[这里](https://github.com/modelscope/swift/tree/main/docs/source/LLM/ORPO算法最佳实践.md)
 - 2024.05.07: 支持来自xtuner的Llava-Llama3模型，model_type为`llava-llama-3-8b-v1_1`.
 - 2024.04.29: 支持InternVL-Chat-V1.5的推理与微调, 最佳实践可以查看[这里](https://github.com/modelscope/swift/tree/main/docs/source/Multi-Modal/internvl最佳实践.md).
 - 🔥2024.04.26: 支持**LISA** 和 **unsloth**训练！指定 `--lisa_activated_layers=2` 来开启LISA（显存使用降低至全参训练的30%），指定 `--tuner_backend unsloth` 来使用unsloth，用更少的显存（30%或更少）更快的速度（5x）训练一个超大模型！
@@ -233,7 +237,7 @@ swift web-ui
 | -------- |------------------------------------|
 | 预训练   | 文本生成                               |
 | 微调     | 单轮/多轮<br>Agent训练/自我认知<br>多模态视觉/多模态语音 |
-| 人类对齐 | DPO<br>ORPO                                |
+| 人类对齐 | DPO<br>ORPO<br>SimPO                |
 | 文生图   | DreamBooth等                        |
 | 文生视频 | -                                  |
 
@@ -530,9 +534,10 @@ CUDA_VISIBLE_DEVICES=0 swift deploy \
 | Llava                                     | [Llava系列模型](https://github.com/haotian-liu/LLaVA)                          | 英文 | 7B-34B          | chat模型 |
 | Llava-Next                                | [Llava-Next系列模型](https://github.com/LLaVA-VL/LLaVA-NeXT)                   | 中文<br>英文 | 8B-110B         | chat模型 |
 | mPLUG-Owl                                 | [mPLUG-Owl系列模型](https://github.com/X-PLUG/mPLUG-Owl)                       | 英文 | 11B             | chat模型 |
-| InternVL                                  | [InternVL](https://github.com/OpenGVLab/InternVL)                          | 中文<br>英文 | 25.5B<br>包含量化版本 | chat模型 |
+| InternVL                                  | [InternVL](https://github.com/OpenGVLab/InternVL)                          | 中文<br>英文 | 2B-25.5B<br>包含量化版本 | chat模型 |
 | Llava-llama3                              | [xtuner](https://huggingface.co/xtuner/llava-llama-3-8b-v1_1-transformers) | 英文 | 8B              | chat model |
-| Phi3                                      | Microsoft                                                                  | 英文 | 4B              | chat model |
+| Phi3-Vision                                | 微软              | 英文 | 4B              | chat model |
+| PaliGemma                                  | Google              | 英文 | 3B              | chat model |
 
 #### 扩散模型
 
@@ -610,7 +615,6 @@ make docs
 | [LLM评测](https://github.com/modelscope/swift/blob/main/docs/source/LLM/LLM%E8%AF%84%E6%B5%8B%E6%96%87%E6%A1%A3.md) |
 | [LLM量化](https://github.com/modelscope/swift/blob/main/docs/source/LLM/LLM%E9%87%8F%E5%8C%96%E6%96%87%E6%A1%A3.md) |
 | [LLM部署](https://github.com/modelscope/swift/blob/main/docs/source/LLM/VLLM%E6%8E%A8%E7%90%86%E5%8A%A0%E9%80%9F%E4%B8%8E%E9%83%A8%E7%BD%B2.md) |
-| [DPO人类对齐训练](https://github.com/modelscope/swift/blob/main/docs/source/LLM/DPO%E8%AE%AD%E7%BB%83%E6%96%87%E6%A1%A3.md) |
 | [AnimateDiff训练](https://github.com/modelscope/swift/blob/main/docs/source/AIGC/AnimateDiff%E5%BE%AE%E8%B0%83%E6%8E%A8%E7%90%86%E6%96%87%E6%A1%A3.md) |
 
 
@@ -632,6 +636,9 @@ make docs
 |  [Qwen1.5最佳实践](https://github.com/modelscope/swift/blob/main/docs/source/LLM/Qwen1.5%E5%85%A8%E6%B5%81%E7%A8%8B%E6%9C%80%E4%BD%B3%E5%AE%9E%E8%B7%B5.md) |
 | [多模态模型训练最佳实践](https://github.com/modelscope/swift/blob/main/docs/source/Multi-Modal/index.md) |
 | [NPU推理与微调最佳实践](https://github.com/modelscope/swift/blob/main/docs/source/LLM/NPU%E6%8E%A8%E7%90%86%E4%B8%8E%E5%BE%AE%E8%B0%83%E6%9C%80%E4%BD%B3%E5%AE%9E%E8%B7%B5.md) |
+| [DPO人类对齐训练](https://github.com/modelscope/swift/blob/main/docs/source/LLM/DPO%E8%AE%AD%E7%BB%83%E6%96%87%E6%A1%A3.md) |
+| [ORPO人类对齐训练](https://github.com/modelscope/swift/blob/main/docs/source/LLM/ORPO%E7%AE%97%E6%B3%95%E6%9C%80%E4%BD%B3%E5%AE%9E%E8%B7%B5.md) |
+| [SimPO人类对齐训练](https://github.com/modelscope/swift/blob/main/docs/source/LLM/SimPO%E7%AE%97%E6%B3%95%E6%9C%80%E4%BD%B3%E5%AE%9E%E8%B7%B5.md) |
 
 
 ### 深度学习教程

asset/wechat.png

@@ -83,6 +83,7 @@ CUDA_VISIBLE_DEVICES=0 swift sft \
     --output_dir output \
 
 # 使用自己的数据集
+# 自定义数据集格式查看: https://github.com/modelscope/swift/blob/main/docs/source/LLM/%E8%87%AA%E5%AE%9A%E4%B9%89%E4%B8%8E%E6%8B%93%E5%B1%95.md#%E8%87%AA%E5%AE%9A%E4%B9%89%E6%95%B0%E6%8D%AE%E9%9B%86
 CUDA_VISIBLE_DEVICES=0 swift sft \
     --model_id_or_path qwen/Qwen-7B-Chat \
     --dataset chatml.jsonl \

docs/resources/simpo1.png

@@ -183,26 +183,47 @@ model, tokenizer = get_model_tokenizer(model_type, model_kwargs={'device_map': '
 
 template = get_template(template_type, tokenizer)
 seed_everything(42)
+
 query = '浙江的省会在哪里？'
 gen = inference_stream(model, template, query)
 print(f'query: {query}')
 for response, history in gen:
-    print(f'response: {response}')
+    pass
+print(f'response: {response}')
+
+# 方式1
 query = '这有什么好吃的？'
-gen = inference_stream(model, template, query, history)
+old_history = history
+gen = inference_stream(model, template, query, old_history)
 print(f'query: {query}')
 for response, history in gen:
     print(f'response: {response}')
 print(f'history: {history}')
 
+# 方式2
+query = '这有什么好吃的？'
+gen = inference_stream(model, template, query, old_history)
+print_idx = 0
+print(f'query: {query}\nresponse: ', end='')
+for response, history in gen:
+    delta = response[print_idx:]
+    print(delta, end='', flush=True)
+    print_idx = len(response)
+print(f'\nhistory: {history}')
+
 """Out[0]
 query: 浙江的省会在哪里？
-...
 response: 浙江省的省会是杭州。
 query: 这有什么好吃的？
+response: 杭
+response: 杭州
+response: 杭州市有
 ...
-response: 杭州市有很多著名的美食，例如西湖醋鱼、龙井虾仁、糖醋排骨、毛血旺等。此外，还有杭州特色的点心，如桂花糕、荷花酥、艾窝窝等。
-history: [('浙江的省会在哪里？', '浙江省的省会是杭州。'), ('这有什么好吃的？', '杭州市有很多著名的美食，例如西湖醋鱼、龙井虾仁、糖醋排骨、毛血旺等。此外，还有杭州特色的点心，如桂花糕、荷花酥、艾窝窝等。')]
+response: 杭州市有很多著名的美食，例如西湖醋鱼、龙井虾仁、糖醋排骨、毛血旺等。此外，还有杭州特色的点心，如桂花酥饼、抹茶糕点等。
+history: [['浙江的省会在哪里？', '浙江省的省会是杭州。'], ['这有什么好吃的？', '杭州市有很多著名的美食，例如西湖醋鱼、龙井虾仁、糖醋排骨、毛血旺等。此外，还有杭州特色的点心，如桂花酥饼、抹茶糕点等。']]
+query: 这有什么好吃的？
+response: 杭州有许多美食，比如西湖醋鱼、龙井虾仁、酱鸭等。此外，还有许多小吃，如烧麦、春卷、油条等，都是浙江特色美食。
+history: [['浙江的省会在哪里？', '浙江省的省会是杭州。'], ['这有什么好吃的？', '杭州有许多美食，比如西湖醋鱼、龙井虾仁、酱鸭等。此外，还有许多小吃，如烧麦、春卷、油条等，都是浙江特色美食。']]
 """
 ```