chatglm-6b / modeling_chatglm.py

Commit History

Remove delete inputs_embeds in _update_model_kwargs_for_generation

238dc29

zxdu20 commited on Apr 18, 2023

Add warning

29868f4

zxdu20 commited on Apr 18, 2023

Merge branch 'main' into pr/45

34a7f82

zxdu20 commited on Apr 18, 2023

Fix input embeds

35ca523

zxdu20 commited on Apr 18, 2023

Update modeling_chatglm.py for inputs_embeds

3118bcb

Xipotzzz commited on Apr 18, 2023

Change mask positions to batch

4de8efe

zxdu20 commited on Apr 14, 2023

Add empty_init option

eb55ff0

zxdu20 commited on Apr 13, 2023

Fix attention score on mps

cde457b

zxdu20 commited on Apr 9, 2023

Fix LogitsProcessor using slim checkpoint (#29)

61eee50

zxdu20

bcol commited on Apr 8, 2023

Use gmask in first place

9324de7

zxdu20 commited on Apr 6, 2023

Update code for slim

63ce1ba

zxdu20 commited on Apr 6, 2023

fix typo in use_gmask (#21)

551a50e

zxdu20

fzhang commited on Apr 5, 2023

Fix position ids expand

f82b180

zxdu20 commited on Apr 3, 2023

Fix generate

fb23542

zxdu20 commited on Apr 2, 2023

Fix attention mask for prefix prompt

08bc851

zxdu20 commited on Apr 1, 2023

No padding for chat function

4b7ffbf

zxdu20 commited on Apr 1, 2023

Implement batch generation

cc96a22

zxdu20 commited on Apr 1, 2023

Fix position id for training

11c270c

zxdu20 commited on Mar 31, 2023

fix GLM6BBlock name typo (#20)

9c7416d

zxdu20

richbrain commited on Mar 31, 2023

Add support for loading quantized model

2e1be30

zxdu20 commited on Mar 31, 2023

Use dynamic dtype for prompts

c949d03

zxdu20 commited on Mar 30, 2023

Fix backward for quantization

0cfae21

zxdu20 commited on Mar 30, 2023

Implement gradient checkpointing

aea6cef

zxdu20 commited on Mar 30, 2023