HuiHui Sun

Results 9 comments of HuiHui Sun

pipeline部署模型，出现lod报错，_get_bbox_result无法返回bbox_results

> > 你好 这个问题解决了嘛 目前我也是这个情况 > > 暂未解决，我还未想到如何解决，官方技术同学也还未答复这个问题 你好，请问这个问题现在解决了吗？

pipline 部署 cascade 模型 http 分析了多张图像后报 Segmentation fault

> 您好，从错误信息上看缺少模型结果缺少save_infer_model/scale_0.tmp_1.lod，您可以直接修改一下python3.7/site-packages/paddle_serving_app/reader/image_reader.py中_get_bbox_result的代码，判断lod存在在取值。至于为什么会出现lod不存在的情况，我们要和模型的同学反馈一下，再决定如何修改。 您好，这个问题原因找到了吗？

'PromptForGeneration' object has no attribute 'can_generate'

> Faced the same error. tried with transformers 4.19.0 and it worked. But 4.19.0 doesnt have LlamaConfig, LlamaForCausalLM or LlamaTokenizer. > > Does anyone know how can i use llama2...

High validation loss for depth prediction

> Hi, thanks for sharing your codebase for great work! > > I'm trying to reproduce HULC++'s evaluation results in CALVIN. I found that the validation loss of depth prediction...

"socket.timeout: timed out" when attempting to launch "generate_snapshot.py."

Hello! I'm meeting the same error. Did you solve it?

Physics simulation causes "time_out" during render_script

Hello! I'm meeting the same error. Did you solve it?

Does OpenPrompt support LLaMa2?

> Recently, im trying to instruct tuning by LLaMa2 under my domain, and no idea about how to write Prompt . So I would like to try to using OpenPrompt...

HTTPConnectionPool(host='127.0.0.1', port=8080): Read timed out.

Hello! I'm meeting the same error. Did you solve it?

HTTPConnectionPool(host='127.0.0.1', port=8080): Read timed out.

> Hello! I'm meeting the same error. Did you solve it? 你可以试试将 mode 改为auto