Merge remote-tracking branch 'thu/main'

Fix position ids expand

Fix generate

Fix attention mask for prefix prompt

No padding for chat function

Fix attention_mask and position_ids

Fix encode method

Fix batch input

Implement batch generation

Fix position id for training

fix GLM6BBlock name typo (#20)

Add support for loading quantized model

Use dynamic dtype for prompts

Fix backward for quantization

Implement gradient checkpointing

Fix bugs

Add pad_token_id in config.json

Merge remote-tracking branch 'thu/main'

Change padding side

Set ignore_index for CrossEntropyLoss

Support batch training

Merge branch 'main' into dev_pt

Add p-tuning v2

Fix context length in get_position_ids

update readme

Merge remote-tracking branch 'thu/main'

Close CPU fusion on Mac

Merge remote-tracking branch 'thu/main'

Fix Chinese punctuation

Add English

merge from ChatGLM-6B

Fix typo in tokenization_chatglm.py

fix import issue

remove image tokens from chatglm-6b

Remove hardcode bos_token_id

Add support for streaming output

Remove hardcode bos_token_id

Add support for streaming output

fix import issue

update README.md

remove image tokens from chatglm-6b

Fix overflow in FP16

Set is_parallelizable to False

Remove image tokens when decoding

Revert "Update quantization"

Update quantization

Add logit processor for NaN or Inf scores

Fix default history argument

Merge branch 'main' of https://huggingface.co/THUDM/chatglm-6b

Add support for float32