Update modeling_chatglm.py

use inference_mode

Fix decode

Update README

Update MODEL_LICENSE

Update config

Fix prefix projection

Remove redundant

Fix prefix prompt in evaluation

Fix gradient checkpointing and prefix prompt

Fix checkpointing

Add gradient checkpointing

Update slack link

Fix name_or_path in tokenizer_config.json

add default model_type (#10)

Remove pipeline tag

Change default max length

Fix invalid token returned by stream_chat

Add pad_token_id

add missing `model_type` (#9)

Add task to model card for discoverability (#6)

Add get_input_embeddings

Fix arange_cpu

Update requirement

Add vocab_file in tokenizer

Update repo link

Update change log

Update README.md

Add index

Update config

Update implementation

Upload tokenizer.model with huggingface_hub

Init commit

Upload pytorch_model-00005-of-00007.bin with huggingface_hub

Upload pytorch_model-00002-of-00007.bin with huggingface_hub

Upload pytorch_model-00006-of-00007.bin with huggingface_hub

Upload pytorch_model-00004-of-00007.bin with huggingface_hub

Upload pytorch_model-00001-of-00007.bin with huggingface_hub

Upload pytorch_model-00007-of-00007.bin with huggingface_hub

Upload pytorch_model-00003-of-00007.bin with huggingface_hub

Upload pytorch_model-00007-of-00007.bin with huggingface_hub

Upload pytorch_model-00003-of-00007.bin with huggingface_hub

initial commit