python3.8用户需要加上__future__ (#1624)

* 增加了仅限GPT4的agent功能,陆续补充,中文版readme已写

* issue提到的一个bug

* 温度最小改成0,但是不应该支持负数

* 修改了最小的温度

* 增加了部分Agent支持和修改了启动文件的部分bug

* 修改了GPU数量配置文件

* 1

1

* 修复配置文件错误

* 更新readme,稳定测试

* 更新readme

* python3.8用户需要加这两行
This commit is contained in:
zR 2023-09-29 16:04:44 +08:00 committed by GitHub
parent 6b1e13a4e2
commit d9056a8df6
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
5 changed files with 6 additions and 2 deletions

View File

@ -70,6 +70,7 @@ If you want to run the native model (int4 version) on the GPU without problems,
+ LLaMA-30B Minimum Memory Requirement: 22GB Recommended Cards: RTX A5000,RTX 3090,RTX 4090,RTX 6000,Tesla V100,RTX Tesla P40
+ Minimum memory requirement for LLaMA-65B: 40GB Recommended cards: A100,A40,A6000
If int8 then memory x1.5 fp16 x2.5 requirement.
For example: using fp16 to reason about the Qwen-7B-Chat model requires 16GB of video memory.

View File

@ -92,6 +92,7 @@ MODEL_PATH = {
# 选用的 Embedding 名称
EMBEDDING_MODEL = "m3e-base" # 可以尝试最新的嵌入式sota模型piccolo-large-zh
# Embedding 模型运行设备。设为"auto"会自动检测,也可手动设定为"cuda","mps","cpu"其中之一。
EMBEDDING_DEVICE = "auto"

View File

@ -1,3 +1,4 @@
from __future__ import annotations
from uuid import UUID
from langchain.callbacks import AsyncIteratorCallbackHandler
import json

View File

@ -1,3 +1,4 @@
from __future__ import annotations
from langchain.agents import Tool, AgentOutputParser
from langchain.prompts import StringPromptTemplate
from typing import List, Union