History

x54-729 b9c813a972 fix(tools): fix streaming_chat and update docs (#467 ) * move hf model to tools/transformers/internlm_model * fix stream_chat * Add stream_chat example * fix import * Add __init__ to internlm_model * Add hf link * fix import of tools/tokenizer.py * fix huggingface url in readme		2023-11-03 16:12:37 +08:00
..
internlm_model	fix(tools): fix streaming_chat and update docs (#467 )	2023-11-03 16:12:37 +08:00
README-zh-Hans.md	[Develop] Pull Main Branch (#121 )	2023-07-21 20:44:33 +08:00
README.md	[Develop] Pull Main Branch (#121 )	2023-07-21 20:44:33 +08:00
convert2hf.py	fix(tools): fix streaming_chat and update docs (#467 )	2023-11-03 16:12:37 +08:00
interface.py	Merge main to develop (#203 )	2023-08-16 15:57:26 +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

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.