Hugging Face's logo

TMElyralab
/
lyraChatGLM

English
LLM
ChatGLM6B
Model card Files Community
49

Update lyraChatGLM/model.py

#21
by dawnranger - opened
base: refs/heads/main
←
from: refs/pr/21
Discussion Files changed
+510
-560
initial commitf2689899
Create README.mdd1850c3c
Upload 12 filesacff406e
Update README.md05581a1a
update demo5f232f54
Update README.md78ab63ee
Update README.mdf8cc4df8
Rename models/glm6b-kv-cache-dy-bs8.ftm to models/glm6b-bs8.ftm32a68d61
Update README.md2dc413ad
Update README.mdf3544b65
Update README.md79914652
fixed readme.935be87d
Remove misleading Readme (#3)34d9abf0
add missing files, fix readme and add docker file308345c5
Update README.mdb977cd17
Update README.md060055d9
Update README.md77bcf50b
Update README.mdb98f2619
update todolist14238158
Update README.md245f2b6d
Update README.md4e50c1a0
Update README.md9ba46d23
Update README.md9d60792a
Update README.md578fee7b
Create CHANGELOG.md298a091f
Delete lyraChatGLM/__init__.py~36bfa808
Delete models/glm6b-bs8.ftme91dabc6
Delete lyraChatGLM/libnvinfer_plugin.so37df8e58
Delete lyraChatGLM/glm.cpython-38-x86_64-linux-gnu.so6fa2ca09
NewAcceleration (#19)78728a3d
Upload model file and tokenizer model file.6b75211f
Update new version readme.997f5a98
Update README.md84865796
Update README.md3d947fee
upload two so files.222e086f
dawnranger
•
edited Jun 5, 2023

This is very slow, takes up to 10mins. Weight is loaded from file, no need to init.

Update lyraChatGLM/model.pye4f62127
vanewu
 Tencent Music Entertainment Lyra Lab org

@dawnranger Yes, this is a leftover from the initial random verification comparison. Thank you.

vanewu changed pull request status to merged

Sign up or log in to comment