PredyDaddy

Hey, I am looking at this repo. Could you add my wechat to talk together about how to deploy this to TensorRT and Deepstream. My wechat account is 1642942273

Hello could you provide me the pretained model? My gmail is [email protected] with the wechat: 1642942273

> Hi @PredyDaddy, Thank you very much for your interest in CVCUDA. Did you follow the steps described in the samples' readme [here](https://github.com/CVCUDA/CV-CUDA/blob/main/samples/README.md)? If not, what were the steps you...

> Hi @PredyDaddy, if you would like to execute the `run_samples.sh` script, you also have to [build the C++ samples](https://github.com/CVCUDA/CV-CUDA/tree/main/samples#build-the-samples-from-source-not-required-for-python-samples), as the script also executes those. In order to build...

> This looks like CVCUDA is not installed on your system. I recommend a [deb package installation](https://github.com/CVCUDA/CV-CUDA/tree/main?tab=readme-ov-file#deb-file-installation). I use this package then I make build_sample ```bash cd /workspace/cvcuda_install/ # Assuming...

I have the same problem, I used followed command start serve ```bash python3 -m llama_cpp.server --model /app/vlm_weights/MiniCPM-V-2_6-gguf/ggml-model-Q2_K.gguf --n_gpu_layers -1 ``` then I used example clinet code with ```python from openai...

> 应该可以，我2.5版本做了一个教程[https://modelbest.feishu.cn/wiki/HLRiwNgKEic6cckGyGucFvxQnJw?from=from_copylink，你可以先看，如果后续有时间我会补上2.6版本的](https://modelbest.feishu.cn/wiki/HLRiwNgKEic6cckGyGucFvxQnJw?from=from_copylink%EF%BC%8C%E4%BD%A0%E5%8F%AF%E4%BB%A5%E5%85%88%E7%9C%8B%EF%BC%8C%E5%A6%82%E6%9E%9C%E5%90%8E%E7%BB%AD%E6%9C%89%E6%97%B6%E9%97%B4%E6%88%91%E4%BC%9A%E8%A1%A5%E4%B8%8A2.6%E7%89%88%E6%9C%AC%E7%9A%84) 请问按照您这种方式微调之后是否会出现灾难性的遗忘呢？

> 你好，只要是微调就一定存在遗忘，我并没有做实验对原来的影响有多大 请问2.6是否可以按照同样的方式进行训练呢？