THUDM
/

chatglm-6b

Inference Endpoints

Model card Files Files and versions Community

chatglm-6b / modeling_chatglm.py

Commit History

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

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

Fix bugs

0564795

zxdu20 commited on Mar 30, 2023

Add pad_token_id in config.json

2200e2b

zxdu20 commited on Mar 29, 2023

Set ignore_index for CrossEntropyLoss

5c64357

zxdu20 commited on Mar 29, 2023

Support batch training

8127ab6

zxdu20 commited on Mar 29, 2023

Merge branch 'main' into dev_pt

fbda120

zxdu20 commited on Mar 29, 2023

Add p-tuning v2

812f43f

zxdu20 commited on Mar 29, 2023

Fix context length in get_position_ids

096f3de

zxdu20 commited on Mar 28, 2023

Close CPU fusion on Mac

4a9b711

zxdu20 commited on Mar 23, 2023

Fix Chinese punctuation

d2bbc82

zxdu20 commited on Mar 22, 2023

Remove hardcode bos_token_id

2460dc2

zxdu20 commited on Mar 19, 2023

Add support for streaming output

42095d4

zxdu20 commited on Mar 19, 2023

Fix overflow in FP16

220f772

zxdu20 commited on Mar 16, 2023

Set is_parallelizable to False

f9f74fd

zxdu20 commited on Mar 15, 2023

Add logit processor for NaN or Inf scores

c3dece3

zxdu20 commited on Mar 15, 2023

Fix default history argument

9d1509a

zxdu20 commited on Mar 14, 2023

Add support for float32

d4832e8

zxdu20 commited on Mar 14, 2023

Fix past_key_values

cd8041e

zxdu20 commited on Mar 13, 2023

Add chatglm-6b

d11c6aa

Sengxian commited on Mar 13, 2023