Modelscope

中文版本

新模型推荐
|  序号  |  模型名称&快捷链接  |
| --- | --- |
| 1  | [千问-7B](https://modelscope.cn/models/qwen/Qwen-7B/summary)  [千问-7B-chat](https://modelscope.cn/models/qwen/Qwen-7B-Chat/summary)  |
| 2 | [chatglm2-6b-32k](https://modelscope.cn/models/ZhipuAI/chatglm2-6b-32k/summary) |
| 3 | [MDQE视频实例分割](https://modelscope.cn/models/marquezx/cv_mdqe_video-instance-segmentation/summary) |
| 4 | [语音合成-越南语-通用领域-24k-发音人tien](https://modelscope.cn/models/damo/speech_sambert-hifigan_nsf_tts_tien_Vietnamese_24k/summary) |
| 5 | [语音合成-马来语-通用领域-24k-发音人farah](https://modelscope.cn/models/damo/speech_sambert-hifigan_nsf_tts_farah_Malay_24k/summary) |
| 6 | [stable-diffusion-xl-refiner-1.0](https://modelscope.cn/models/AI-ModelScope/stable-diffusion-xl-refiner-1.0/summary) |
| 7 | [stable-diffusion-xl-base-1.0](https://modelscope.cn/models/AI-ModelScope/stable-diffusion-xl-base-1.0/summary) |
| 8 | [PolyLM-智能服务-文本生成模型-多语言-13B](https://modelscope.cn/models/damo/nlp_polylm_assistant_13b_text_generation/summary) |
| 9 | [鹏城·盘古增强版-2.6B-CPU](https://modelscope.cn/models/cubeai/pangu2b6-cpu/summary) |
| 10 | [ERes2Net-Base语种识别-中英文识别-16k](https://modelscope.cn/models/damo/speech_eres2net_base_lre_en-cn_16k/summary) |
| 11 | [ERes2Net-Large语种识别-中英文识别-16k](https://modelscope.cn/models/damo/speech_eres2net_large_lre_en-cn_16k/summary) |
| 12 | [codegeex2-6b](https://modelscope.cn/models/ZhipuAI/codegeex2-6b/summary) |
| 13 | [openbuddy-llama2-13b-v8.1-fp16](https://modelscope.cn/models/OpenBuddy/openbuddy-llama2-13b-v8.1-fp16/summary) |
| 14 | [CT-Transformer标点-中英文-通用-large](https://modelscope.cn/models/damo/punc_ct-transformer_cn-en-common-vocab471067-large/summary) |
| 15 | [CAM++语种识别-中英文识别-16k](https://modelscope.cn/models/damo/speech_campplus_lre_en-cn_16k/summary) |
| 16 | [zeroscope_v2_xl高清文生视频](https://modelscope.cn/models/baiguan18/zeroscope_v2_xl/summary) |
| 17 | [FreeWilly2](https://modelscope.cn/models/AI-ModelScope/FreeWilly2/summary) |
| 18 | [Beautiful-Realistic-Asians-v5](https://modelscope.cn/models/buptwq/Beautiful-Realistic-Asians-v5/summary) |
| 19 | [ProST: 视频文本通用检索模型](https://modelscope.cn/models/damo/multi_modal_clip_vtretrieval_prost/summary) |
| 10 | [Realistic_Vision_V4.0](https://modelscope.cn/models/AI-ModelScope/Realistic_Vision_V4.0/summary) |
| 21 | [CAM++说话人确认-中文-3DSpeaker-16k](https://modelscope.cn/models/damo/speech_campplus_sv_zh-cn_3dspeaker_16k/summary) |
| 22 | [Llama-2-70b-ms](https://modelscope.cn/models/modelscope/Llama-2-70b-ms/summary) |
| 23 | [Llama-2-13b-chat-ms](https://modelscope.cn/models/modelscope/Llama-2-13b-chat-ms/summary) |
| 24 | [Llama-2-7b-ms](https://modelscope.cn/models/modelscope/Llama-2-7b-ms/summary) |
| 25 | [Llama-2-7b-chat-ms](https://modelscope.cn/models/modelscope/Llama-2-7b-chat-ms/summary) |
| 26 | [Llama-2-13b-ms](https://modelscope.cn/models/modelscope/Llama-2-13b-ms/summary) |
| 27 | [PolyLM-指令精调-文本生成模型-多语言-13B](https://modelscope.cn/models/damo/nlp_polylm_multialpaca_13b_text_generation/summary) |
| 28 | [LLaVA视觉问答模型](https://modelscope.cn/models/xingzi/llava_visual-question-answering/summary) |
| 29 | [Paraformer语音识别-英文-通用-16k-离线-large-pytorch](https://modelscope.cn/models/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/summary) |
| 30 | [speech_bert_semantic-spk-turn-detection-punc_speaker-diarization_chinese](https://modelscope.cn/models/damo/speech_bert_semantic-spk-turn-detection-punc_speaker-diarization_chinese/summary) |
| 31 | [生成扩散模型高效调优-Swift-LoRA](https://modelscope.cn/models/damo/multi-modal_efficient-diffusion-tuning-swift-lora/summary) |
| 32 | [生成扩散模型高效调优-Swift-Adapter](https://modelscope.cn/models/damo/multi-modal_efficient-diffusion-tuning-swift-adapter/summary) |
| 33 | [生成扩散模型高效调优-Swift-Prompt](https://modelscope.cn/models/damo/multi-modal_efficient-diffusion-tuning-swift-prompt/summary) |
| 34 | [MindChat-7B](https://modelscope.cn/models/X-D-Lab/MindChat-7B/summary) |
| 35 | [MindChat-6B](https://modelscope.cn/models/X-D-Lab/MindChat-6B/summary) |
| 36 | [MindChat-Baichuan-13B](https://modelscope.cn/models/X-D-Lab/MindChat-Baichuan-13B/summary) |
| 37 | [rwkv-4-music](https://modelscope.cn/models/AI-ModelScope/rwkv-4-music/summary) |
| 38 | [RWKV-4-Raven-7B](https://modelscope.cn/models/AI-ModelScope/RWKV-4-Raven-7B/summary) |
| 39 | [rwkv-4-world](https://modelscope.cn/models/AI-ModelScope/rwkv-4-world/summary) |
| 40 | [球面上的全景图单目深度估计](https://modelscope.cn/models/damo/cv_s2net_panorama-depth-estimation/summary) |
| 41 | [AquilaChat-7B](https://modelscope.cn/models/AI-ModelScope/AquilaChat-7B/summary) |
| 42 | [Sunsimiao-6B-05M](https://modelscope.cn/models/X-D-Lab/Sunsimiao-6B-05M/summary) |
| 43 | [Sunsimiao-InternLM-01M](https://modelscope.cn/models/X-D-Lab/Sunsimiao-InternLM-01M/summary) |
| 44 | [4K 超高清 NeRF 重建算法](https://modelscope.cn/models/DAMOXR/cv_nerf-3d-reconstruction-4k-nerf_damo/summary) |
| 45 | [基于扩散模型的文生图-360全景图生成模型](https://modelscope.cn/models/damo/cv_diffusion_text-to-360panorama-image_generation/summary) |
| 46 | [speech_bert_dialogue-detetction_speaker-diarization_chinese](https://modelscope.cn/models/damo/speech_bert_dialogue-detetction_speaker-diarization_chinese/summary) |
| 47 | [PolyLM-文本生成模型-多语言-13B](https://modelscope.cn/models/damo/nlp_polylm_13b_text_generation/summary) |
| 48 | [stable-diffusion-xl-base-0.9](https://modelscope.cn/models/AI-ModelScope/stable-diffusion-xl-base-0.9/summary) |
| 49 | [百川13B对话模型](https://modelscope.cn/models/baichuan-inc/Baichuan-13B-Chat/summary) |
| 50 | [百川13B模型](https://modelscope.cn/models/baichuan-inc/Baichuan-13B-Base/summary) |
| 51 | [书生·浦语大模型](https://modelscope.cn/models/AI-ModelScope/internlm-chat-7b-8k/summary) |
| 52 | [internlm-chat-7b](https://modelscope.cn/models/AI-ModelScope/internlm-chat-7b/summary) |
| 53 | [StableSR图像超分辨率](https://modelscope.cn/models/xhlin129/cv_stablesr_image-super-resolution/summary) |
| 54 | [ERes2Net-Large说话人确认-中文-3D-Speaker-16k](https://modelscope.cn/models/damo/speech_eres2net_large_sv_zh-cn_3dspeaker_16k/summary) |
| 55 | [ERes2Net-Base说话人确认-中文-3D-Speaker-16k](https://modelscope.cn/models/damo/speech_eres2net_base_sv_zh-cn_3dspeaker_16k/summary) |
| 56 | [基于向量量化的神经辐射场压缩](https://modelscope.cn/models/DAMOXR/cv_nerf_3d-reconstruction_vector-quantize-compression/summary) |
| 57 | [baichuan_agent](https://modelscope.cn/models/HOPE_FOR_FUTURE/baichuan_agent/summary) |
| 58 | [Regularized DINO说话人确认-中文-3D-Speaker-16k](https://modelscope.cn/models/damo/speech_rdino_ecapa_tdnn_sv_zh-cn_3dspeaker_16k/summary) |
| 59 | [CAAI-Hackathon](https://modelscope.cn/models/caai/caai-stable-diffusion-lora/summary) |
| 60 | [BAT语音识别-中文-aishell1-16k-离线](https://modelscope.cn/models/damo/speech_bat_asr-zh-cn-16k-aishell1-vocab4234-pytorch/summary) |

功能列表
- 训练时使用AutoModel情况下增加模型版本检查
- 支持safe tensors weight pipeline。
- 支持transformers类模型的流式输出。
- 优化类包装器。
- 支持huggingface transformers的AutoModel, AutoConfig and AutoTokenizer
- 在llm中添加了完整参数的sft。
- 添加了日语README。
- 在params和load函数中添加了download_mode参数。
- 使用Xformers 提高了attention计算时的内存/显存性能。


功能提升

- 将 stable diffusion 版本升级到更强大的版本2.1。
- 增加custom stable diffusion 微调。
- 添加了 stable diffusion swift tuner。
- 在不使用deepspeed的情况下支持llama和lora微调。
- 为lora  stable diffusion 添加了lora_rank参数。
- 优化了torch1.11和torch2.0.1镜像构建脚本。
- 在sbert文本分类中支持从数据集获取标签，并在chatglm-6b中构建文件数据集。
- 更新了speaker_verification_pipeline.py。
- 更新了默认测试级别。
- 更新了aliyuncs pip的默认值。
- 更新了语言识别任务名称。
- 为text-to-video添加了height和width参数。
- 自定义 diffusion pipeline。
- 添加了支持ASRDataset的download_mode参数。
- 更新了chatglm6b v2的新版本。
- 改进了加载meta-csv缓存路径的方式。
- 添加了一个example/llm模块。
- 优化了注释和格式。
- 设置download_mode的默认值。
- 使用num_inference_steps和guidance_scale参数更新pipeline。
- 在finetune_speech_recognition.py中添加了download_mode的支持，使用params.download_mode。
- 在finetune_speech_recognition.py中使用ASRDataset替换MsDataset。
- 更新了ASRDataset，为重新下载数据集（如数据集损坏或损坏）添加了download_mode。
- 更新了asr_dataset.py，支持使用download_mode重新下载数据。
- 将text_in设置为必需参数。
- 修改了text_generation_pipeline类的参数传递。
- 添加了baichuan/chatglm2+lora+agent示例。
- 添加了 stable diffusion 教程ipynb。


BugFix


- 忽略http错误，以防止模型检查时混淆。
- 解决了加载 checkpoint时出现的不同设备问题。
- 修复了缺少plugin模块文件的问题。
- 解决了镜像标签无cuda的问题。
- 解决了easycv CPU扩展构建问题。
- 解决了设备错误问题。
- 解决了amp和device_map问题。
- 通过配置pysptk >= 0.1.19解决了pip安装错误。
- 解决了ckpt输出目录忽略*.safetensors的问题。
- 修复了对baichuan的eval和sequence_length支持的问题。
- 解决了在文档分割pipeline中使用cuda设备的问题。
- 删除了清华相关的硬编码。
- 解决了与stable diffusion pipeline相关的错误，该pipeline无法识别“lora_scale”参数。
- 解决了与chatglm2模块相关的错误。
- 修复了mPLUG-Owl生成长度错误。
- 更正了speaker模型的详细信息。
- 修复了在加载本地stable diffusion数据集时出现的错误。
- 修复了chatglm管道中的错误。
- 修复了chatglm6b 2的错误。
- 修复了与empty hypothesis相关的chatglm2评估错误。


English Version

New Model List and Quick Access

| No | Model Name & Link |
| --- | --- |
|  1  | [Qwen-7B](https://modelscope.cn/models/qwen/Qwen-7B/summary)  [Qwen-7B-chat](https://modelscope.cn/models/qwen/Qwen-7B-Chat/summary)  |
| 2 | [chatglm2-6b-32k](https://modelscope.cn/models/ZhipuAI/chatglm2-6b-32k/summary) |
| 3 | [MDQE video-instance-segmentation](https://modelscope.cn/models/marquezx/cv_mdqe_video-instance-segmentation/summary) |
| 4 | [speech_sambert-hifigan_nsf_tts_tien_Vietnamese_24k](https://modelscope.cn/models/damo/speech_sambert-hifigan_nsf_tts_tien_Vietnamese_24k/summary) |
| 5 | [speech_sambert-hifigan_nsf_tts_farah_Malay_24k](https://modelscope.cn/models/damo/speech_sambert-hifigan_nsf_tts_farah_Malay_24k/summary) |
| 6 | [stable-diffusion-xl-refiner-1.0](https://modelscope.cn/models/AI-ModelScope/stable-diffusion-xl-refiner-1.0/summary) |
| 7 | [stable-diffusion-xl-base-1.0](https://modelscope.cn/models/AI-ModelScope/stable-diffusion-xl-base-1.0/summary) |
| 8 | [PolyLM-assistant_13b_text_generation](https://modelscope.cn/models/damo/nlp_polylm_assistant_13b_text_generation/summary) |
| 9 | [pangu-plus-2.6B-CPU](https://modelscope.cn/models/cubeai/pangu2b6-cpu/summary) |
| 10 | [ERes2Net-Base-language identification-en-cn-16k](https://modelscope.cn/models/damo/speech_eres2net_base_lre_en-cn_16k/summary) |
| 11 | [ERes2Net-Large-language identification-en-cn-16k](https://modelscope.cn/models/damo/speech_eres2net_large_lre_en-cn_16k/summary) |
| 12 | [codegeex2-6b](https://modelscope.cn/models/ZhipuAI/codegeex2-6b/summary) |
| 13 | [openbuddy-llama2-13b-v8.1-fp16](https://modelscope.cn/models/OpenBuddy/openbuddy-llama2-13b-v8.1-fp16/summary) |
| 14 | [CT-Transformer-punc-cn-en-common-large](https://modelscope.cn/models/damo/punc_ct-transformer_cn-en-common-vocab471067-large/summary) |
| 15 | [CAM++-language identification-en-cn-16k](https://modelscope.cn/models/damo/speech_campplus_lre_en-cn_16k/summary) |
| 16 | [zeroscope_v2_xl high-definition text-to-video generation](https://modelscope.cn/models/baiguan18/zeroscope_v2_xl/summary) |
| 17 | [FreeWilly2](https://modelscope.cn/models/AI-ModelScope/FreeWilly2/summary) |
| 18 | [Beautiful-Realistic-Asians-v5](https://modelscope.cn/models/buptwq/Beautiful-Realistic-Asians-v5/summary) |
| 19 | [ProST: retrieval model for video-text](https://modelscope.cn/models/damo/multi_modal_clip_vtretrieval_prost/summary) |
| 20 | [Realistic_Vision_V4.0](https://modelscope.cn/models/AI-ModelScope/Realistic_Vision_V4.0/summary) |
| 21 | [CAM++-zh-cn-3DSpeaker-16k](https://modelscope.cn/models/damo/speech_campplus_sv_zh-cn_3dspeaker_16k/summary) |
| 22 | [Llama-2-70b-ms](https://modelscope.cn/models/modelscope/Llama-2-70b-ms/summary) |
| 23 | [Llama-2-13b-chat-ms](https://modelscope.cn/models/modelscope/Llama-2-13b-chat-ms/summary) |
| 24 | [Llama-2-7b-ms](https://modelscope.cn/models/modelscope/Llama-2-7b-ms/summary) |
| 25 | [Llama-2-7b-chat-ms](https://modelscope.cn/models/modelscope/Llama-2-7b-chat-ms/summary) |
| 26 | [Llama-2-13b-ms](https://modelscope.cn/models/modelscope/Llama-2-13b-ms/summary) |
| 27 | [PolyLM-multialpaca-text_generation-13B](https://modelscope.cn/models/damo/nlp_polylm_multialpaca_13b_text_generation/summary) |
| 28 | [LLaVA visual-question-answering](https://modelscope.cn/models/xingzi/llava_visual-question-answering/summary) |
| 29 | [Paraformer-asr_nat-zh-cn-16k-large-pytorch](https://modelscope.cn/models/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/summary) |
| 30 | [speech_bert_semantic-spk-turn-detection-punc_speaker-diarization_chinese](https://modelscope.cn/models/damo/speech_bert_semantic-spk-turn-detection-punc_speaker-diarization_chinese/summary) |
| 31 | [multi-modal_efficient-diffusion-tuning-Swift-LoRA](https://modelscope.cn/models/damo/multi-modal_efficient-diffusion-tuning-swift-lora/summary) |
| 32 | [multi-modal_efficient-diffusion-tuning-Swift-Adapter](https://modelscope.cn/models/damo/multi-modal_efficient-diffusion-tuning-swift-adapter/summary) |
| 33 | [multi-modal_efficient-diffusion-tuning-Swift-Prompt](https://modelscope.cn/models/damo/multi-modal_efficient-diffusion-tuning-swift-prompt/summary) |
| 34 | [MindChat-7B](https://modelscope.cn/models/X-D-Lab/MindChat-7B/summary) |
| 35 | [MindChat-6B](https://modelscope.cn/models/X-D-Lab/MindChat-6B/summary) |
| 36 | [MindChat-Baichuan-13B](https://modelscope.cn/models/X-D-Lab/MindChat-Baichuan-13B/summary) |
| 37 | [rwkv-4-music](https://modelscope.cn/models/AI-ModelScope/rwkv-4-music/summary) |
| 38 | [RWKV-4-Raven-7B](https://modelscope.cn/models/AI-ModelScope/RWKV-4-Raven-7B/summary) |
| 39 | [rwkv-4-world](https://modelscope.cn/models/AI-ModelScope/rwkv-4-world/summary) |
| 40 | [monocular depth estimation for panoramic images on a sphere](https://modelscope.cn/models/damo/cv_s2net_panorama-depth-estimation/summary) |
| 41 | [AquilaChat-7B](https://modelscope.cn/models/AI-ModelScope/AquilaChat-7B/summary) |
| 42 | [Sunsimiao-6B-05M](https://modelscope.cn/models/X-D-Lab/Sunsimiao-6B-05M/summary) |
| 43 | [Sunsimiao-InternLM-01M](https://modelscope.cn/models/X-D-Lab/Sunsimiao-InternLM-01M/summary) |
| 44 | [4K Ultra high definition NeRF 3d-reconstruction](https://modelscope.cn/models/DAMOXR/cv_nerf-3d-reconstruction-4k-nerf_damo/summary) |
| 45 | [diffusion_text-to-360panorama-image_generation](https://modelscope.cn/models/damo/cv_diffusion_text-to-360panorama-image_generation/summary) |
| 46 | [speech_bert_dialogue-detetction_speaker-diarization_chinese](https://modelscope.cn/models/damo/speech_bert_dialogue-detetction_speaker-diarization_chinese/summary) |
| 47 | [PolyLM-text_generation-13B](https://modelscope.cn/models/damo/nlp_polylm_13b_text_generation/summary) |
| 48 | [stable-diffusion-xl-base-0.9](https://modelscope.cn/models/AI-ModelScope/stable-diffusion-xl-base-0.9/summary) |
| 49 | [Baichuan-13B-Chat](https://modelscope.cn/models/baichuan-inc/Baichuan-13B-Chat/summary) |
| 50 | [Baichuan-13B-Base](https://modelscope.cn/models/baichuan-inc/Baichuan-13B-Base/summary) |
| 51 | [internlm-chat-7b-8k](https://modelscope.cn/models/AI-ModelScope/internlm-chat-7b-8k/summary) |
| 52 | [internlm-chat-7b](https://modelscope.cn/models/AI-ModelScope/internlm-chat-7b/summary) |
| 53 | [StableSR image-super-resolution](https://modelscope.cn/models/xhlin129/cv_stablesr_image-super-resolution/summary) |
| 54 | [ERes2Net-Large large_sv_zh-cn_3dspeaker_16k](https://modelscope.cn/models/damo/speech_eres2net_large_sv_zh-cn_3dspeaker_16k/summary) |
| 55 | [ERes2Net-Base base_sv_zh-cn_3dspeaker_16k](https://modelscope.cn/models/damo/speech_eres2net_base_sv_zh-cn_3dspeaker_16k/summary) |
| 56 | [3d-reconstruction_vector-quantize-compression](https://modelscope.cn/models/DAMOXR/cv_nerf_3d-reconstruction_vector-quantize-compression/summary) |
| 57 | [baichuan_agent](https://modelscope.cn/models/HOPE_FOR_FUTURE/baichuan_agent/summary) |
| 58 | [Regularized DINO ecapa_tdnn -3D-Speaker-16k](https://modelscope.cn/models/damo/speech_rdino_ecapa_tdnn_sv_zh-cn_3dspeaker_16k/summary) |
| 59 | [CAAI-Hackathon](https://modelscope.cn/models/caai/caai-stable-diffusion-lora/summary) |
| 60 | [BAT-asr-zh-cn-aishell1-16k](https://modelscope.cn/models/damo/speech_bat_asr-zh-cn-16k-aishell1-vocab4234-pytorch/summary) |

Feature

- Added check model for training and model_dir for automodel.
- Added support for safetensors weight pipeline.
- Support for stream output on transformers model
- Refined class wrapper
- Added Support for AutoModel, AutoConfig and AutoTokenizer
- Added full parameter sft to llm
- Added Japanese README
- Added download_mode param to params and load function.
- Accelerated memory efficient attention with Xformers.

Improvements

- Upgraded stable diffusion version to more powerful version 2.1.
- Custom method for finetuning stable diffusion
- Added stable diffusion swift tuner
- Support for llama & lora finetune without deepspeed
- Added lora_rank parameter for lora stable diffusion
- Refactored torch1.11 and torch2.0.1 build script
- Support getting labels from dataset in sbert text classification and building dataset from file in chatglm-6b
- Updated speaker_verification_pipeline.py
- Changed tests level
- Set default aliyuncs pip
- Added height and width parameters for text-to-video.
- Customized the diffusion pipeline.
- Added support for ASRDataset for download_mode parameters.
- Updated the Fea/chatglm6b v2 new version.
- Improved the load meta-csv cathe paths.
- Added an example/llm module.
- Optimized comments and formatting.
- Set the download_mode default value.
- Updated the pipeline with num_inference_steps and guidance_scale parameters.
- Added support for download_mode in finetune_speech_recognition.py with params.download_mode.
- Replaced MsDataset with ASRDataset in finetune_speech_recognition.py.
- Updated ASRDataset with download_mode for re-downloading the dataset if it is broken or corrupted.
- Updated asr_dataset.py to support download_mode for re-downloading data.
- Made text_in a required parameter.
- Modified the parameter passing of the text_generation_pipeline class.
- Added baichuan/chatglm2 +lora+agent examples.
- Added stable diffusion tutorial ipynb.

BugFix

- Ignored http error to prevent confusion during model check.
- Fixed checkpoint issue related to same device.
- Fixed missing plugin python module files.
- Fixed build tag no cuda issue.
- Fixed easycv CPU extension build issue.
- Fixed device error.
- Fixed issue with amp and device_map
- Fixed pip install error with pysptk>=0.1.19
- Fixed issue with ckpt output directory ignoring *.safetensors
- Fixed eval and sequence_length support for baichuan
- Fixed issue with using cuda device in document segmentation pipeline inference
- Removed hard code tsinghua
- Fixed amp + device_map (386)
- Fixed bugs related to the Chinese stable diffusion pipeline not recognizing the 'lora_scale' argument.
- Fixed bugs related to the chatglm2 module.
- Fixed mPLUG-Owl generating length bug.
- Fixed details of speaker models.
- Fixed bugs related to loading local sd dataset.
- Fixed bugs in the chatglm pipeline.
- Fixed chatglm6b 2.
- Fixed chatglm2 evaluation error related to empty hypothesis.

Fix some bugs

中文版本

新特性
- 增加baichuan模型lora inference
- 增加baichuan和chatglm2 lora agent示例

BugFix

- 修复历史问题
- 修复sd加载本地数据集的问题
- 修复chatglm推理问题
- 修改text_generation_pipeline传参
- 修复chatglm6b和chatglm6b 2
- 修复评估报错：hypothesis emtpy


English Version

Features
- Add lora_inference for baichuan
- Add baichuan/chatglm2+lora+agent examples


BugFix

- fix history problem
- Fix a bug of loading local stable diffusion dataset
- Fix/chatglm pipeline
- Modify the parameter passing of the text_generation_pipeline class
- Fix/chatglm6b 2
- Fix/chatglm6b
- fix evaluation error: hypothesis emtpy

中文版本

新模型推荐
| 序号 | 模型名称&快捷链接 |
| --- | --- |
| 1 | [读光-文字识别-轻量化端侧识别模型-中英-通用领域](https://modelscope.cn/models/damo/cv_LightweightEdge_ocr-recognitoin-general_damo/summary) |
| 2 | [读光-文字检测-轻量化端侧DBNet行检测模型-中英-通用领域](https://modelscope.cn/models/damo/cv_proxylessnas_ocr-detection-db-line-level_damo/summary) |
| 3 | [CAM++说话人转换点定位-两人-中文](https://modelscope.cn/models/damo/speech_campplus-transformer_scl_zh-cn_16k-common/summary) |



高亮功能

- 新增轻量化端侧识别模型LightweightEdge
- 新增轻量化端侧DBNet行检测模型
- 新增CAM++说话人转换点定位
- llama模型支持finetune和deepseed
- llama模型支持lora
- 对于transformers模型支持device_map
- 数据集支持jsonl格式
- 对于大型模型文件支持并行下载（dsw或eais环境）
- 提升youku超大型数据集下载体验

功能列表
- 新增轻量化端侧识别模型LightweightEdge
- 新增轻量化端侧DBNet行检测模型
- 新增flextrain ner样例
- 新增在文本分类finetune的training args中增加模型版本
- 新增StreamingMixin
- 支持torch extension
- 支持llama模型微调和deepspeed
- pipeline中支持第三方的key
- 支持说话人分离pipeline
- 新增eres2net_aug v2模型
- 支持transformers model device_map
- 支持模型权重diff
- 数据集支持jsonl格式
- 新增Lora/Adapter/Prompt/Chatglm6b
- 部分tests增加teardown
- 解除datasets包版本限制
- 支持从model id加载
- llama模型支持lora
- 对于大型模型文件支持并行下载


功能提升

- 提升mPLUG-youku大型数据集的下载体验


BugFix
- 修复DeepspeedHook.register_processor
- dockerfile的兼容性修改（py37和py38）
- 修复 extra_args
- 修复ngpu bug和移除easyasr
- 修复mplug-youku超大数据集下载相关问题
- 修复gpt3 finetune nan的问题
- 修复torch extension ci hang住的问题
- 修复easycv lr hook 错误
- 修复torch2.x 兼容性问题
- 修复diffusers版本冲突问题
- 修复eval RecursionError
- 对于DiffusionForTextToImageSynthesis修复device_map问题
- 修复stable diffusion pipeline cpu推理问题
- 修复llama lora问题

English Version

New Model List and Quick Access

| No | Model Name & Link |
| --- | --- |
| 1 | [cv_LightweightEdge_ocr-recognitoin-general_damo](https://modelscope.cn/models/damo/cv_LightweightEdge_ocr-recognitoin-general_damo/summary) |
| 2 | [cv_proxylessnas_ocr-detection-db-line-level_damo](https://modelscope.cn/models/damo/cv_proxylessnas_ocr-detection-db-line-level_damo/summary) |
| 3 | [speech_campplus-transformer_scl_zh-cn_16k-common](https://modelscope.cn/models/damo/speech_campplus-transformer_scl_zh-cn_16k-common/summary) |


Highlight
- Add new OCR recognition model (LightweightEdge) and some functions
- Add ocr detection new model db-nas
- Add CAM++ model
- Support llama model finetune and deepspeed
- Support lora for llama model
- Support device_map for transformers
- Support jsonl format in datasets
- Support parallel download large model file
- Improve mPLUG-YOUKU dataset downloading experience

Breaking changes


Feature
- Add new OCR recognition model (LightweightEdge) and some functions
- Add ocr detection new model db-nas
- Add ner example for flextrain
- Add model revision in training_args and modify dataset loading in finetune text classification
- Add StreamingMixin
- Support pre build torch extension build image, first extension megatron_util
- Add llama finetune + deepspeed
- Support third_party key in pipeline
- Add speaker diarization pipeline and improve some speaker pipelines
- Add eres2net_aug v2
- Support device_map for transformers model
- Add make diff & recover for model weights
- Support jsonl format in meta data
- Add Lora/Adapter/Prompt/Chatglm6b
- Add teardown for tests
- Unfreeze datasets version setting
- Support load from model id
- Support lora for llama
- Support parallel download large model file

Improvements

- llama tuned model -> pipeline
- improve youku dataset downloading experience

BugFix

- Fix bug for DeepspeedHook.register_processor
- Docker file py38 and py37 compatible merge
- Fix extra_args
- ngpu bug and rm easyasr
- Fix issues for downloading mplug-youku dataset
- Fix gpt3 finetune nan
- Fix ci hang when build torch extension
- Fix easycv lr hook error
- Fix torch 2.x compatible issue
- Fix diffuser version conflict cv and multi-modal
- Fix eval RecursionError
- Fix device_map for DiffusionForTextToImageSynthesis
- Fix cpu inference for stable diffusion pipeline
- Fix llama lora bug

中文版本


功能列表

- 支持跳过easycv三方依赖引入
- 支持Flextrain training args和push_to_hub
- 支持domain_specific_object_detection 的onnx格式导出


BugFix

- 修复test_cli CI报错
- 修复merge hook
- 修复NER tokenizer不能接收kwargs的问题
- 修复lineless_table_recognition功能遇到空白图片崩溃的bug
- 修复某些情况下private数据集鉴权失败的问题

English Version



Feature
- Add pattern to skip easycv.thirdparty
- Support flex train feature (training args and push_to_hub adaptions)
- Support onnx export for domain_specific_object_detection



BugFix

- Fix CI: test merge dataset failed
- Fix merge_hook
- Fix NER tokenizer which won't accept kwargs
- Fix lineless_table_recognition crashed when input blank images
- fix private dataset auth issue

中文版本

该版本共新增上架5个模型。


新模型列表及快捷访问

| **贡献组织** | **模型名称** | **是否支持Finetune** |
| --- | --- | --- |
| **达摩院** | [ERes2Net说话人确认-英文-VoxCeleb-16k-离线-pytorch](https://modelscope.cn/models/damo/speech_eres2net_sv_en_voxceleb_16k/summary) | 否 |
| **达摩院** | [mPLUG-Owl-多模态对话-英文-7B](https://modelscope.cn/models/damo/multi-modal_mplug_owl_multimodal-dialogue_7b/summary) | 否 |
| **达摩院** | [FastInst快速实例分割](https://modelscope.cn/models/damo/cv_resnet50_fast-instance-segmentation_coco/summary) | 否 |
| **达摩院** | [TransFace人脸识别模型](https://modelscope.cn/models/damo/cv_vit_face-recognition/summary) | 否 |
| **达摩院** | [Regularized DINO说话人确认-英文-VoxCeleb-16k-离线-pytorch](https://modelscope.cn/models/damo/speech_rdino_ecapa_tdnn_sv_en_voxceleb_16k/summary) | 否 |



非兼容性修改
* 支持Python3.8版本
* 移除demo check



English Version
Highlight
- Support Python3.8
- Add mPLUG-Owl model
- Add cvpr23 Fastinst model


Breaking changes
- Support Python3.8
- Remove demo check


Feature
- Add ERes2Net for speaker verification
- Add mPLUG-Owl model
- Support FlexTrain and update the structure of trainer
- Add cvpr23 fastinst model
- Support Virgo MaxCompute datasource for Ali-cloud inner applications
- Add clip_interrogator
- Add gpt3 example
- Add convert megatron ckpt script
- Add trainer for UniTE
- Add transface model
- Add verified if whl installed
- Support python3.8
- Add ONNX exporter for ans dfsmn
- Add rdino model



Improvements

- Update multi_modal_embedding example
- Refine easrasr
- Pipeline input, output and parameter normalization.
- Display hub error message
- Remove easycv codes, plugin access



BugFix

- Fix bug in **kwargs duplicated for audio module
- Fix distributed hook to lazyimport and an import bug
- Fix transformer examples
- Add pop for base class parameters
- Fix func update_local_model; change funasr version
- Remove pai-easycv requirement
- Fix hypotheses did't init in cpu device, make fid_dialogue_test available