Modelscope

中文版本

高亮功能

- 优化ci
- 兼容transformers 4.34.0
- Support int4 model for llm_pipeline

BugFix

- fix merge error (582)
- move venv import from file level to class level to avoid import error… (575)

English Version


Highlight

- optimize ci
- compatible with transformers 4.34.0
- Support int4 model for llm_pipeline


BugFix

- fix merge error (582)
- move venv import from file level to class level to avoid import error… (575)

中文版本

新模型推荐


高亮功能

- 增加image_control_3d_portrait模型
- 增加3dhuman render and animation 模型
- 增加LLMPipeline支持大模型推理

功能列表

- 支持swift trainer和pipeline
- 增加image_control_3d_portrait模型
- 增加3dhuman render and animation 模型
- 新增 model for card correction
- 新增 head_reconstruction and text_to_head model
- 增加LLMpipeline支持大模型推理
- 增加 onnx exporter for ocr recognition model
- 增加 onnx exporter for ocr_detection db model
-
功能提升

BugFix

- 修复onnxruntime 新版本兼容性问题
- 修复huggingface兼容性问题
- asr支持本地模型
- 修复ci问题

English Version

New Model List and Quick Access

Highlight

- Add 3dhuman render and animation models
- Add image_control_3d_portrait
- Add LLMpipeline support LLM inference

Breaking changes

Feature
- support swift trainer and pipeline (547)
- add image_control_3d_portrait
- add 3dhuman render and animation models
- add model for card correction
- add head_reconstruction and text_to_head model
- add LLMpipeline support LLM inference
- add onnx exporter for ocr recognition model
- add onnx exporter for ocr_detection db model

Improvements

BugFix

- Fix onnxruntime providers parameter compatible issue
- Fix hf bug (569)
- Fix support local asr models (556)
- Fix fix ci issue
-

中文版本

新模型推荐


高亮功能

- 模型下载增加失败重试功能


功能列表

-

功能提升

- 支持模型下载失败重试

BugFix

- 解决新版本transformers position_ids兼容性问题


English Version

New Model List and Quick Access


Highlight

- Retry download model when failed.

Breaking changes

Feature
- Retry download model when failed.


Improvements



BugFix

- Fix latest transformers position_ids compatible issue.

中文版本

新模型推荐
| 序号 | 模型名称&快捷链接 |
| --- | --- |
| 1 | [通义千问-VL-Chat-Int4](https://modelscope.cn/models/qwen/Qwen-VL-Chat-Int4/summary) |
| 2 | [t5-base](https://modelscope.cn/models/AI-ModelScope/t5-base/summary) |
| 3 | [WizardMath-7B-V1.0](https://modelscope.cn/models/AI-ModelScope/WizardMath-7B-V1.0/summary) |
| 4 | [WizardCoder-3B-V1.0](https://www.modelscope.cn/models/AI-ModelScope/WizardCoder-3B-V1.0/summary) |
| 5 | [WizardCoder-Python-13B-V1.0](https://www.modelscope.cn/models/AI-ModelScope/WizardCoder-Python-13B-V1.0/summary) |
| 6 | [WizardCoder-Python-34B-V1.0](https://www.modelscope.cn/models/AI-ModelScope/WizardCoder-Python-34B-V1.0/summary) |
| 7 | [WizardMath-13B-V1.0](https://www.modelscope.cn/models/AI-ModelScope/WizardMath-13B-V1.0/summary) |
| 8 | [WizardLM-30B-V1.0](https://modelscope.cn/models/AI-ModelScope/WizardLM-30B-V1.0/summary/summary) |
| 9 | [WizardLM-7B-V1.0](https://modelscope.cn/models/AI-ModelScope/WizardLM-7B-V1.0/summary) |
| 10 | [CodeLlama-34b-Instruct-hf](https://modelscope.cn/models/AI-ModelScope/CodeLlama-34b-Instruct-hf/summary) |
| 11 | [CodeLlama-34b-Python-hf](https://modelscope.cn/models/AI-ModelScope/CodeLlama-34b-Python-hf/summary) |
| 12 | [CodeLlama-13b-Instruct-hf](https://modelscope.cn/models/AI-ModelScope/CodeLlama-13b-Instruct-hf/summary) |
| 13 | [CodeLlama-7b-hf](https://modelscope.cn/models/AI-ModelScope/CodeLlama-7b-hf/summary) |
| 14 | [CodeLlama-7b-Python-hf](https://modelscope.cn/models/AI-ModelScope/CodeLlama-7b-Python-hf/summary) |
| 15 | [CodeLlama-34b-hf](https://modelscope.cn/models/AI-ModelScope/CodeLlama-34b-hf/summary) |
| 16 | [CodeLlama-13b-hf](https://modelscope.cn/models/AI-ModelScope/CodeLlama-13b-hf/summary) |
| 17 | [CodeLlama-13b-Python-hf](https://modelscope.cn/models/AI-ModelScope/CodeLlama-13b-Python-hf/summary) |
| 18 | [CodeLlama-7b-Instruct-hf](https://modelscope.cn/models/AI-ModelScope/CodeLlama-7b-Instruct-hf/summary) |
| 19 | [WizardCoder-15B-V1.0](https://modelscope.cn/models/AI-ModelScope/WizardCoder-15B-V1.0/summary) |
| 20 | [WizardCoder-1B-V1.0](https://modelscope.cn/models/AI-ModelScope/WizardCoder-1B-V1.0/summary) |
| 21 | [WizardMath-7B-V1.0](https://modelscope.cn/models/AI-ModelScope/WizardMath-7B-V1.0/summary) |
| 22 | [WizardLM-13B-V1.2](https://modelscope.cn/models/AI-ModelScope/WizardLM-13B-V1.2/summary) |
| 23 | [ERes2Net-Base语种识别-中英粤日韩识别-8k](https://modelscope.cn/models/damo/speech_eres2net_base_five_lre_8k/summary) |
| 24 | [ERes2Net-large语种识别-中英粤日韩识别-8k](https://modelscope.cn/models/damo/speech_eres2net_large_five_lre_8k/summary) |
| 25 | [Paraformer语音识别-英文-通用-16k-离线-1B-pytorch](https://modelscope.cn/models/damo/speech_paraformer_asr-en-16k-vocab4199-1B-pytorch/summary) |
| 26 | [Regularized DINO说话人确认-中文-CNCeleb-16k](https://modelscope.cn/models/damo/speech_rdino_ecapa_tdnn_sv_zh-cn_cnceleb_16k/summary) |


高亮功能

- video to video model support a10, v100
- funasr支持mossformer模型
- SDXL支持lora微调
- stable diffusion支持fp16训练和推理

不兼容更新

- 最低支持python3.8
- 镜像tensorflow 升级2.13.0
- numpy，pandas版本升级

功能列表


功能提升

- 更新qwen QA 示例
- 添加qwen QA langchain示例

BugFix

- 修复stable diffusion fp16 bug
- 修复图像上色模型加载问题
- 修复 chatglm2b rope_ratio config 缺失问题

English Version

New Model List and Quick Access

| No | Model Name & Link |
| --- | --- |
| 1 | [qwen-VL-Chat-Int4](https://modelscope.cn/models/qwen/Qwen-VL-Chat-Int4/summary) |
| 2 | [t5-base](https://modelscope.cn/models/AI-ModelScope/t5-base/summary) |
| 3 | [WizardMath-7B-V1.0](https://modelscope.cn/models/AI-ModelScope/WizardMath-7B-V1.0/summary) |
| 4 | [WizardCoder-3B-V1.0](https://www.modelscope.cn/models/AI-ModelScope/WizardCoder-3B-V1.0/summary) |
| 5 | [WizardCoder-Python-13B-V1.0](https://www.modelscope.cn/models/AI-ModelScope/WizardCoder-Python-13B-V1.0/summary) |
| 6 | [WizardCoder-Python-34B-V1.0](https://www.modelscope.cn/models/AI-ModelScope/WizardCoder-Python-34B-V1.0/summary) |
| 7 | [WizardMath-13B-V1.0](https://www.modelscope.cn/models/AI-ModelScope/WizardMath-13B-V1.0/summary) |
| 8 | [WizardLM-30B-V1.0](https://modelscope.cn/models/AI-ModelScope/WizardLM-30B-V1.0/summary/summary) |
| 9 | [WizardLM-7B-V1.0](https://modelscope.cn/models/AI-ModelScope/WizardLM-7B-V1.0/summary) |
| 10 | [CodeLlama-34b-Instruct-hf](https://modelscope.cn/models/AI-ModelScope/CodeLlama-34b-Instruct-hf/summary) |
| 11 | [CodeLlama-34b-Python-hf](https://modelscope.cn/models/AI-ModelScope/CodeLlama-34b-Python-hf/summary) |
| 12 | [CodeLlama-13b-Instruct-hf](https://modelscope.cn/models/AI-ModelScope/CodeLlama-13b-Instruct-hf/summary) |
| 13 | [CodeLlama-7b-hf](https://modelscope.cn/models/AI-ModelScope/CodeLlama-7b-hf/summary) |
| 14 | [CodeLlama-7b-Python-hf](https://modelscope.cn/models/AI-ModelScope/CodeLlama-7b-Python-hf/summary) |
| 15 | [CodeLlama-34b-hf](https://modelscope.cn/models/AI-ModelScope/CodeLlama-34b-hf/summary) |
| 16 | [CodeLlama-13b-hf](https://modelscope.cn/models/AI-ModelScope/CodeLlama-13b-hf/summary) |
| 17 | [CodeLlama-13b-Python-hf](https://modelscope.cn/models/AI-ModelScope/CodeLlama-13b-Python-hf/summary) |
| 18 | [CodeLlama-7b-Instruct-hf](https://modelscope.cn/models/AI-ModelScope/CodeLlama-7b-Instruct-hf/summary) |
| 19 | [WizardCoder-15B-V1.0](https://modelscope.cn/models/AI-ModelScope/WizardCoder-15B-V1.0/summary) |
| 20 | [WizardCoder-1B-V1.0](https://modelscope.cn/models/AI-ModelScope/WizardCoder-1B-V1.0/summary) |
| 21 | [WizardMath-7B-V1.0](https://modelscope.cn/models/AI-ModelScope/WizardMath-7B-V1.0/summary) |
| 22 | [WizardLM-13B-V1.2](https://modelscope.cn/models/AI-ModelScope/WizardLM-13B-V1.2/summary) |
| 23 | [ERes2Net-Base](https://modelscope.cn/models/damo/speech_eres2net_base_five_lre_8k/summary) |
| 24 | [ERes2Net-large](https://modelscope.cn/models/damo/speech_eres2net_large_five_lre_8k/summary) |
| 25 | [Paraformer](https://modelscope.cn/models/damo/speech_paraformer_asr-en-16k-vocab4199-1B-pytorch/summary) |
| 26 | [Regularized](https://modelscope.cn/models/damo/speech_rdino_ecapa_tdnn_sv_zh-cn_cnceleb_16k/summary) |

Highlight

- video to video model support a10, v100
- Add funasr support mossformer model
- Support sdxl finetune by lora method
- support float16 training and pipeline for stable diffusion


Breaking changes

- Deprecated python3.7 support
- tensorflow upgrade to 2.13.0 in image
- numpy, pandas version upgrade

Feature


Improvements

- upgrade qwen QA sample

BugFix

- Fix bugs of stable diffusion fp16
- fix image colorization model load issue
- fix chatglm2b rope_ratio config is missing

中文版本

新模型
[VideoComposer](https://modelscope.cn/models/damo/VideoComposer/summary)：组合视频合成 (#431)

改进
* 移除numpy版本 <=1.22.0 的限制 (453)
* 更改llama2的max_length默认值 (452)
* 在函数generate中支持llama2输入到设备
* 支持为llama加载数据集
* 更新qwen qa示例
* 添加readme和警告 (462)

Bug修复
* 修复chatglm2b rope_ratio配置参数缺失 (440)
* 修复pipeline检查错误 (455)
* 修复针对python37的copytree bug (464)

English Version

New models
[VideoComposer](https://modelscope.cn/models/damo/VideoComposer/summary): Compositional Video Synthesis with Motion Controllability (#431)

Improvement
* remove restriction of numpy version <=1.22.0 (453)
* change llama2 max_length default value (452)
* support llama2 inputs to device in function generate
* support load dataset for llama
* update qwen qa example
* add readme and warning (462)

Bugfix
* fix chatglm2b rope_ratio config is missing (440)
* fix pipeline check error (455)
* fix copytree python37 bug (464)

bugfix for qwen
* streamer pass error
* check flash attention installation even if use_fast_att is set True
* fix quantization model run failed