zsl01670416 e87d04e869 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

2023-08-09 20:18:23 +08:00

..

cli

fix torch 2.x compatible issue

2023-06-27 14:40:51 +08:00

export

Stable Diffusion model checkpoint export to onnx. (#340)

2023-06-28 13:26:19 +08:00

fileio

fix jsonplus, support ndarray

2023-03-21 18:10:10 +08:00

hub

Support FlexTrain and update the structure of trainer

2023-05-13 12:12:04 +08:00

metrics

Add trainer for UniTE

2023-05-11 14:41:08 +08:00

models

Compatibility for huggingface transformers (#391)

2023-07-24 20:53:27 +08:00

msdatasets

Support jsonl format in meta data

2023-06-27 11:58:19 +08:00

outputs

[to #42322933]fix bugs relate to token cls

2022-10-31 20:52:27 +08:00

pipelines

support llama2 inputs to device in function generate

2023-08-09 20:18:23 +08:00

preprocessors

[to #47563396]Fix bug: two ckpt hooks save in the same dir

2023-02-13 16:54:02 +00:00

taskdataset

Refactor the task_datasets module

2023-03-10 09:03:32 +08:00

trainers

Merge branch 'master-github' into master-merge-github-230727

2023-07-27 17:29:27 +08:00

tuners

Add Lora/Adapter/Prompt and support for chatglm6B and chatglm2-6B

2023-06-27 14:38:18 +08:00

utils

skip plugin

2023-07-30 00:30:30 +08:00

__init__.py

…

run_analysis.py

Refactor the task_datasets module

2023-03-10 09:03:32 +08:00

run_config.yaml

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

2023-07-27 11:33:39 +08:00

run.py

remove profiling log (#113)

2023-02-17 12:01:54 +08:00