Galaxy-Ding

train with return code = -9

1

## Summary I have read the related [issue100,](https://github.com/databrickslabs/dolly/issues/100) and it runs smoothly. However, unlike issue 100, I return -9 directly ## Background: The purpose is to train the 2.9b model...

自己的知识库生成的是乱码？

1

环境： vicuna-13b 的基础模型 ubuntu18.04.6 其他环境按照 ReadMe 所建立 我的知识库文件：(部分)  问题：  已经尝试过了： 1，重启server，重启webserver. 还是得到一样的结果 llm server 后台日志如下：  webserver 后台日志如下 

How could I convert my model to hf

1

Hi, I'm new to this huggingface transformation. I now have: - vicuuna13b.pth(which i finetune with my data) I want to convert it into a huggingface model like yours repo [https://huggingface.co/Tribbiani/vicuna-7b/tree/main]...

Target： For me, I am new to huggingface, just want to convert my fine-tuned model(pth) into huggingface, which can be directly downloaded and used. Done: #113 I've seen this issue,...

CONCAT, uid 9 must have same quantize parameter

2

## 环境版本说明 OS: ubuntu20.04下 docker: docker rknntoolkit 1.7.3 环境 ## 背景： 需要转换Y8的网络，在Q群讨论过了，做了y8的网络层修改， 具体是用原生的y8的网络，做如下 修改 1， 将ultrralytics 文件夹下的所有chunk 算子 等效替换成chunk； 接着便开始输出onnx： ``` from ultralytics import YOLO # Load a model model...