gnh1201/Open-Llama
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

update server demo

Browse Source
This commit is contained in:
LiangSong 2023-04-04 17:35:51 +08:00
parent e89f5a5aa0
commit 7c7c4765fc
1 changed files with 3 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
server.py
View File

@ -32,7 +32,7 @@ raw_model = LlamaForCausalLM(
shared_input_output_embedding=True,
)
)
ckpt = torch.load("data/saved_ckpt/instruction_tuning/14001.pt", map_location="cpu")
ckpt = torch.load("data/saved_ckpt/instruction_tuning_3_epochs/23001.pt", map_location="cpu")
raw_model.load_state_dict(ckpt)
raw_model.eval()
model = raw_model.cuda()
@ -63,7 +63,8 @@ demo = gr.Interface(
"我今天肚子有点不舒服，晚饭有什么建议么",
"可以总结一下小说三体的核心内容么？",
"Can you explain to me what quantum mechanics is and how it relates to quantum computing?",
"I'm feeling a bit unwell in my stomach today. Do you have any suggestions for dinner?",
"请帮我写一个AI驱动的幼儿教育APP的商业计划书",
"用python实现一个快速排序",
],
title="Open-Llama",
description="不基于其他预训练模型，完全使用[Open-Llama](https://github.com/Bayes-Song/Open-Llama)项目从0开始训练的Instruct-GPT模型，总训练成本不超过2w美元。由于请求需要经Gradio进行转发，可能出现请求丢失的现象，当长时间无响应（如20s以上）可刷新重试。当前体验服务生成的所有内容都是由人工智能模型生成，我们对其生成内容的准确性、完整性和功能性不做任何保证，并且其生成的内容不代表我们的态度或观点。",