Hugging Face's logo

tencent
/
WeDLM-8B-Instruct

Text Generation
Transformers
Safetensors
English
Chinese
wedlm
language model
parallel-decoding
conversational
custom_code
Model card Files
xet
Community
9

it run on cpu colab

#9
by asdgad - opened
Discussion
asdgad

https://github.com/kmnnmk212-source/suc-tencent_WeDLM-8B-Instruct-cpu/blob/main/suc_tencent_WeDLM_8B_Instruct_cpu(1).ipynb
thulaw
•
edited 1 day ago

Currently, the fast generation feature supports GPU environments only, and it requires using the wedlm library instead of the official Hugging Face library.

Sign up or log in to comment