mirror of https://github.com/InternLM/InternLM
aaaf4d7b0e
* fixed the issue that the HF model spontaneously conducted multiple rounds of Q&A and stream_chat method generates garbled characters Signed-off-by: daijun1 <daijun1@eccom.com.cn> * Update modeling_internlm.py fixed the issue that the HF model spontaneously conducted multiple rounds of Q&A and stream_chat method generates garbled characters * Update modeling_internlm.py Correct spelling mistakes: chche -> cache --------- Signed-off-by: daijun1 <daijun1@eccom.com.cn> Co-authored-by: daijun1 <daijun1@eccom.com.cn> |
||
|---|---|---|
| .. | ||
| README-zh-Hans.md | ||
| README.md | ||
| configuration_internlm.py | ||
| convert2hf.py | ||
| interface.py | ||
| intern_moss_example.py | ||
| internlm_sft_on_moss.py | ||
| modeling_internlm.py | ||
| tokenization_internlm.py | ||
README.md
InternLM Transformers
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.