step_into_llm

step_into_llm copied to clipboard

ChatPDF功能存在的问题运行complex_ui.py直接报如下错误。 (mindspore) root@autodl-container-bff2469f3e-a4796232:~/autodl-tmp/ChatPDF# python complex_ui.py Building prefix dict from the default dictionary ... Loading model from cache /tmp/jieba.cache Loading model cost 0.529 seconds. Prefix dict has been built successfully. The...

kevinwei1975

运行python simple_ui.py直接报如下错误。 (mindspore) root@autodl-container-bff2469f3e-a4796232:~/autodl-tmp/ChatPDF# python simple_ui.py Building prefix dict from the default dictionary ... Loading model from cache /tmp/jieba.cache Loading model cost 0.559 seconds. Prefix dict has been built successfully....

kevinwei1975

执行以下命令时，虽得到了正确结果，但推理没有使用GPU，运行了5分钟才出结果，太慢了。 (mindspore) root@autodl-container-bff2469f3e-a4796232:~/autodl-tmp/ChatPDF# python chatpdf.py Building prefix dict from the default dictionary ... Loading model from cache /tmp/jieba.cache Loading model cost 0.960 seconds. Prefix dict has been built successfully. Namespace(sim_model_name='shibing624/text2vec-base-multilingual',...

kevinwei1975

ChatGLM notebook增加Mindspore2.3 Ascend平台注解，更新ppt最后一页的部署教程与notebook同步。 对应issue：[https://gitee.com/mindspore/community/issues/IA5LCW](url)

ChineseAegis

#68

zzh578

zzh578

之前02.chatglm2文件夹下有chatglm2_demo.py，虽然这个demo文件跑不通。。 最近更新了一版本，这个demo.py被删除了是吗？ 后续会继续上线嘛，mindspore适配大模型，必须走mindformers嘛，这个只能等官方的适配呀。。

Tonywang0350

transformer loss函数计算有误

2

def forward(enc_inputs, dec_inputs): """前向网络 enc_inputs: [batch_size, src_len] dec_inputs: [batch_size, trg_len] """ logits, _, _, _ = model(enc_inputs, dec_inputs[:, :-1], src_pad_idx, trg_pad_idx) targets = dec_inputs[:, 1:].view(-1) loss = loss_fn(logits, targets) return...

ywbgithub

Update README.md

2

修改了第二期readme文档

lyqcom

Update README.md

1

修改了readme文档

lyqcom