History

x54-729 0600b42c01 refactor(tools): move interface.py and import it to web_demo (#195 ) * move interface.py and import it to web_demo * typo		2023-08-14 22:32:29 +08:00
..
README-zh-Hans.md	Use tempfile for convert2hf.py (#23 )	2023-07-17 21:08:10 +08:00
README.md	Use tempfile for convert2hf.py (#23 )	2023-07-17 21:08:10 +08:00
configuration_internlm.py	initial commit	2023-07-06 12:55:23 +08:00
convert2hf.py	fix AutoModel map in convert2hf.py (#116 )	2023-07-24 12:07:47 +08:00
interface.py	refactor(tools): move interface.py and import it to web_demo (#195 )	2023-08-14 22:32:29 +08:00
intern_moss_example.py	initial commit	2023-07-06 12:55:23 +08:00
internlm_sft_on_moss.py	initial commit	2023-07-06 12:55:23 +08:00
modeling_internlm.py	Use tempfile for convert2hf.py (#23 )	2023-07-17 21:08:10 +08:00
tokenization_internlm.py	initial commit	2023-07-06 12:55:23 +08:00

README.md

InternLM Transformers

English | 简体中文

This folder contains the InternLM model in transformers format.

Weight Conversion

convert2hf.py can convert saved training weights into the transformers format with a single command. Execute the command in the root directory of repository:

python tools/transformers/convert2hf.py --src_folder origin_ckpt/ --tgt_folder hf_ckpt/ --tokenizer ./tools/V7_sft.model

Then, you can load it using the from_pretrained interface:

>>> from transformers import AutoTokenizer, AutoModel
>>> model = AutoModel.from_pretrained("hf_ckpt/", trust_remote_code=True).cuda()

intern_moss_example.py demonstrates an example of how to use LoRA for fine-tuning on the fnlp/moss-moon-002-sft dataset.