CC/gpt_academic
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

Add GLM INT8

Browse Source
This commit is contained in:
binary-husky
2023-07-24 18:19:57 +08:00
parent dd4ba0ea22
commit e93b6fa3a6
3 changed files with 14 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
config.py
View File

@@ -80,7 +80,7 @@ ChatGLM_PTUNING_CHECKPOINT = "" # 例如"/home/hmp/ChatGLM2-6B/ptuning/output/6b
# 本地LLM模型如ChatGLM的执行方式 CPU/GPU
LOCAL_MODEL_DEVICE = "cpu" # 可选 "cuda"
LOCAL_MODEL_QUANT = "INT4" # 默认 "" "INT4" 启用量化INT4版本 "INT8" 启用量化INT8版本
LOCAL_MODEL_QUANT = "FP16" # 默认 "FP16" "INT4" 启用量化INT4版本 "INT8" 启用量化INT8版本
# 设置gradio的并行线程数（不需要修改）