Commit Graph

1936 Commits

Author SHA1 Message Date
lingcai.wl
7757f3c64a [to #51336898] support eas deploy, fix minor problems
Link: https://code.alibaba-inc.com/Ali-MaaS/MaaS-lib/codereview/13541904
* [to #51336898] support eas deploy

* [to #51336898] support eas deploy, fix minor problems
2023-08-07 19:48:07 +08:00
zsl01670416
b0699fd8e2 support llama2 inputs to device in function generate
fix error inputs and model were not on the same device. if they are not on the same device, inputs will be implemented function to model device.
Link: https://code.alibaba-inc.com/Ali-MaaS/MaaS-lib/codereview/13546989
* support llama inputs to device in function generate

* modify test qwen text generation according to github code
2023-08-07 15:41:28 +08:00
wenmeng.zwm
63747824fa upgrade to 1.8.1 2023-08-03 16:01:41 +08:00
lukeming.lkm
9e033104af change use_fast_att and fix bfloat loading
Link: https://code.alibaba-inc.com/Ali-MaaS/MaaS-lib/codereview/13522792

* check flash att is installed even if  use_fast_att is set True and fix bfloat loading

* skip pipeline model placement for quantization

* update unittest for qwen
2023-08-03 15:59:51 +08:00
yuze.zyz
deda508acc fix streamer arg
Link: https://code.alibaba-inc.com/Ali-MaaS/MaaS-lib/codereview/13520666
* fix streamer arg
2023-08-03 14:34:52 +08:00
lukeming.lkm
b3a61ef6f4 update LICENSE
Link: https://code.alibaba-inc.com/Ali-MaaS/MaaS-lib/codereview/13516119
2023-08-03 11:07:34 +08:00
lukeming.lkm
914e9af3ad add LICENSE and related snippets
Link: https://code.alibaba-inc.com/Ali-MaaS/MaaS-lib/codereview/13513677
2023-08-03 09:39:20 +08:00
lukeming.lkm
561fbe9eb2 reformat stop_words_ids to sync QWen7b HF
Link: https://code.alibaba-inc.com/Ali-MaaS/MaaS-lib/codereview/13510247
2023-08-02 18:46:12 +08:00
lukeming.lkm
1ce78d648d add kwargs for save_vocabulary
Link: https://code.alibaba-inc.com/Ali-MaaS/MaaS-lib/codereview/13508568
2023-08-02 18:12:11 +08:00
lukeming.lkm
dece963ad5 resolve stopword logits processor
Link: https://code.alibaba-inc.com/Ali-MaaS/MaaS-lib/codereview/13504522

* resolve stopword logits processor
2023-08-02 16:14:48 +08:00
hejunjie.hjj
0c679d2e09 fix bug: referring_video-object-segmentation兼容Pillow10
Link: https://code.alibaba-inc.com/Ali-MaaS/MaaS-lib/codereview/13479152
* fix bug: referring_video-object-segmentation兼容Pillow10
2023-08-02 16:08:26 +08:00
lukeming.lkm
bd2f70a6eb add quantization in qwen pipelines and relevant unittests
Link: https://code.alibaba-inc.com/Ali-MaaS/MaaS-lib/codereview/13499600

* add quant features

* resolve import

* resolve format

* fix save vocab
2023-08-02 14:05:13 +08:00
lukeming.lkm
33bd74a7be add qwen 7b base and chat
添加QWen 7b base模型和chat模型及相关pipelines
Link: https://code.alibaba-inc.com/Ali-MaaS/MaaS-lib/codereview/13482235

* add qwen 7b base and chat

* fix logger

* update examples, lint test

* add unittest for qwen base and chat

* rename qwen to qwen-7b

* resolve imports and add a registry to text-generation

* reset load model from pretrained

* fix precheck

* skip qwen test case now

* remove strange file
2023-08-02 09:25:21 +08:00
wenmeng zhou
1a6583eee2 Feat/chatglm2 32k support (#433)
* add support for chatglm2 32k

* fix
2023-08-01 23:22:09 +08:00
suluyan.sly
f080603802 remove requirement realesrgan for basicsr
Link: https://code.alibaba-inc.com/Ali-MaaS/MaaS-lib/codereview/13488773
* remove requirement realesrgan for basicsr
2023-08-01 16:55:47 +08:00
mulin.lyh
c1df82acd8 init pip to aliyuncs
Link: https://code.alibaba-inc.com/Ali-MaaS/MaaS-lib/codereview/13487845

* init pip to aliyuncs
2023-08-01 16:55:33 +08:00
suluyan.sly
dc17c7d6ee remove cv requirements: basicsr
Link: https://code.alibaba-inc.com/Ali-MaaS/MaaS-lib/codereview/13471366
* rm req basicsr
2023-07-31 18:20:23 +08:00
mulin.lyh
da2badaacd [to #51274424]fix: easycv extension and tinycudann conflict
Link: https://code.alibaba-inc.com/Ali-MaaS/MaaS-lib/codereview/13471150
* fix easycv extension and tinycudann conflict
2023-07-31 18:08:53 +08:00
yuze.zyz
f856c04785 Ignore http error
忽略log打印,防止在check_model_is_latest时打出信息使用户不明所以。
将log改为Error栈
Link: https://code.alibaba-inc.com/Ali-MaaS/MaaS-lib/codereview/13463005
2023-07-31 17:14:12 +08:00
wenmeng.zwm
48a39244f1 Merge branch master-merge-github-230728 into master
Title: Merge branch 'master-github' into master-merge-github-230728 
Link: https://code.alibaba-inc.com/Ali-MaaS/MaaS-lib/codereview/13456249
2023-07-31 16:09:07 +08:00
suluyana
b68b90ba15 skip plugin 2023-07-30 00:30:30 +08:00
suluyana
9ece90ee84 skip plugin test case 2023-07-29 21:35:21 +08:00
suluyan.sly
d7cd2ce28e Merge branch 'master-github' into master-merge-github-230728 2023-07-29 10:42:54 +08:00
Jintao
312b63fe06 fix checkpoint, same device bug (#427) 2023-07-29 00:06:27 +08:00
zsl01670416
847607ab66 Merge branch 'debug_chatglm6b_json_dataset' fix conflict between hf dataset and to_hf_dataset
The type of dataset built from file is hf dataset, which can not use function to_hf_dataset.
2023-07-28 19:12:21 +08:00
suluyan.sly
05e1357c32 Merge branch 'master-github' into master-merge-github-230728 2023-07-28 16:40:34 +08:00
tastelikefeet
972298813b 1. add check model for training 2. add model_dir for automodel (#422) 2023-07-28 16:34:02 +08:00
wenmeng.zwm
3b485d5835 fix plugin python module missing files
Link: https://code.alibaba-inc.com/Ali-MaaS/MaaS-lib/codereview/13453749
* fix plugin python module missing files
2023-07-28 16:14:56 +08:00
frozoul
2566d028cd cv/cv nerf 3d reconstruction 4k nerf damo (#389)
* add 4k-nerf core files

* update configure file

* update dataloader and model path

* update unittest

* Delete test_4k.py

* update unittest

* update unittest

* update pre-commit

* update dataloader

* update cuda code path

* check with pre-commit

---------

Co-authored-by: zhongshu.wzs <zhongshu.wzs@alibaba-inc.com>
Co-authored-by: wenmeng zhou <wenmeng.zwm@alibaba-inc.com>
2023-07-28 10:37:13 +08:00
tongmu.wh
475924a421 correct language recognition taks name
modelscope平台同学最终定下语种识别任务名为speech-language-recognition,对应进行代码中的相关改动
Link: https://code.alibaba-inc.com/Ali-MaaS/MaaS-lib/codereview/13444517
* correct language recognition taks name
2023-07-27 21:03:04 +08:00
Xingjun.Wang
3bd395a0c9 Merge pull request #423 from modelscope/dev/del_redundancy_code
del redundant code
2023-07-27 20:53:01 +08:00
xingjun.wang
6748cd7370 del redundancy code in func: get_dataset_meta_file_list 2023-07-27 20:49:41 +08:00
Wang Qiang
34ea2b474a Upgrade stable diffusion version to a more powerful version 2.1 (#415) 2023-07-27 20:40:38 +08:00
suluyan.sly
76921561e6 Merge branch master-merge-github-230727 into master
Title: Merge branch 'master-github' into master-merge-github-230727 
Link: https://code.alibaba-inc.com/Ali-MaaS/MaaS-lib/codereview/13442869
2023-07-27 20:18:35 +08:00
mulin.lyh
a501f7a417 fix easycv cpu extension build issue, cpu not support
Link: https://code.alibaba-inc.com/Ali-MaaS/MaaS-lib/codereview/13441612
* fix easycv cpu extension build issue, cpu not support
2023-07-27 17:42:37 +08:00
suluyan.sly
1c6f5fe775 Merge branch 'master-github' into master-merge-github-230727
Conflicts:
       examples/pytorch/baichuan/finetune_baichuan.py
       examples/pytorch/chatglm6b/finetune.py
2023-07-27 17:29:27 +08:00
Wang Qiang
dca6143b8b support safetensors weight pipeline (#421) 2023-07-27 16:49:01 +08:00
tastelikefeet
9802dfe93b fix device error (#419) 2023-07-27 16:23:21 +08:00
mengyang.fmy
18f998a85c add text-to-360pano-image pipeline, mod cv requirements
7月份计划上线的360全景图生成模型,自研

模型权重文件地址https://www.modelscope.cn/models/damo/cv_diffusion_text-to-360panorama-image_generation/summary


#### 依赖项说明

##### 由于要使用xformers,torch版本最好使用1.13.1
```
pip install torch==1.13.1+cu116 torchvision==0.14.1+cu116 torchaudio==0.13.1 --extra-index-url https://download.pytorch.org/whl/cu116
```
##### 对应的diffusers和xformers版本如下
```
pip install -U diffusers==0.18.0
pip install xformers==0.0.16
pip install triton, accelerate, transformers
```

##### ModelScope Library 需要使用cv
```
pip install modelscope
pip install "modelscope[cv]" -f https://modelscope.oss-cn-beijing.aliyuncs.com/releases/repo.html
```

##### 此外,还需要安装第三方的一个库,Real-ESRGAN, 安装方法如下
```
# Install basicsr - https://github.com/xinntao/BasicSR
# We use BasicSR for both training and inference
pip install basicsr
# facexlib and gfpgan are for face enhancement
pip install facexlib
pip install gfpgan
pip install Pillow
pip install tqdm
pip install realesrgan==0.3.0
```
Link: https://code.alibaba-inc.com/Ali-MaaS/MaaS-lib/codereview/13346430
* add text-to-360pano-image pipeline

* add text-to-360pano-image pipeline, mod cv requirements

* rm redundant files and cv requirements; add standard input and output definations

* fix diffusers==0.18.0 and run test

* fix diffusers==0.18.0 in multi-modal and run test again

* add model_revision='v1.0.0'

* fix yapf

* add trycatch for enabling xformers

* fix key error

* add install xformers in test/setup

* skip highres.fix in ci

* feat: Fix conflict, auto commit by WebIDE
2023-07-27 11:33:39 +08:00
Wang Qiang
66cf72a75c Merge pull request #376 from XDUWQ/custom_diffusion
Custom method for finetuning stable diffusion
2023-07-27 10:41:38 +08:00
suluyana
534a020e93 Merge pull request #418 from tastelikefeet/feat/fix_device_split
fix CI
2023-07-27 10:03:41 +08:00
yuze.zyz
00c79428d5 fix 2023-07-26 21:30:38 +08:00
Jintao
4ca937d2ba support openbuddy-llama2-13b (#416) 2023-07-26 18:12:55 +08:00
Zackary Shen
ba4db97507 upload cv_nerf_3d-reconstruction_vector-quantize-compression (#407)
* add vq_compression model

* add vq_compression model

* check pre-commit for lint test

* fix by flake8

* update

* update

* update

* the last update

* the laast update

* update test_level>=0

---------

Co-authored-by: 剑匣 <zackary.sz@alibaba-inc.com>
2023-07-26 17:20:13 +08:00
XDUWQ
3a629bb2b4 pre 2023-07-26 16:58:58 +08:00
XDUWQ
99aa707995 fix bugs 2023-07-26 16:35:40 +08:00
XDUWQ
25d67a0b83 pre 2023-07-26 16:08:24 +08:00
XDUWQ
70da8b7809 fix bugs 2023-07-26 15:54:37 +08:00
XDUWQ
a7678bbb77 precommit 2023-07-26 15:06:42 +08:00
XDUWQ
c0b62cb0fb fix bugs 2023-07-26 15:03:46 +08:00