nullxjx
I have my own datasets whose format are like pascal voc with labeled images only, i do not have the calibration file, how can I train on my own datasts?
如题
不使用fim，跑出来的分数跟官方给的比较接近，但是使用fim后分数很低，低了8个点，以下是我使用的fim格式，请问有啥问题吗？ ``` def get_full_prompt(model_name, prompt_prefix, prompt, suffix="\n"): """ get_full_prompt 通过匹配模型名，使用不同的FIM格式来准备prompt """ output = prompt if "star-coder" in model_name.lower(): ... elif "deep-seek" in model_name.lower() or "deepseek" in model_name.lower(): template = Template("${preprefix}${prefix}${suffix}")...
**Description** A clear and concise description of what the bug is. build command: ```bash BASE_CONTAINER_IMAGE_NAME=nvcr.io/nvidia/tritonserver:23.12-py3-min TENSORRTLLM_BACKEND_REPO_TAG=main PYTHON_BACKEND_REPO_TAG=main # Run the build script. The flags for some features or endpoints can...
### 📚 The doc issue I see one of the key features of lmdeploy is the "Interactive Inference Mode". As far as I know, most of the existing llm serving...
作者你好，最近用了一下你的这个小工具，非常好用。但是有个问题，比方说我想一次性获取forward函数中的多个变量，请问我该怎么做？
### Checklist - [X] 1. I have searched related issues but cannot get the expected help. - [X] 2. The bug has not been fixed in the latest version. -...