DeepSeek-Coder-V2

DeepSeek-Coder-V2 copied to clipboard

 continue 插件访问coder-v2模型

healerwhy

1. when inferring from a model to FIM, I want to fine-tune it with a dataset, but the format of the dataset is {"instruction" : "", "output": ""} should I...

Yindy07

Hey there, Trying to fine-tune your model. What is the FSDP value for `fsdp_transformer_layer_cls_to_wrap`? Thanks!

Metaspectral

WentaoTan

OutOfMemoryError: CUDA out of memory on RunPod

2

**Description:** While running DeepSeek Coder v2 on RunPod, I encountered a `CUDA out of memory` error. The error message indicated that the system attempted to allocate 20.00 MiB of memory,...

loyal812

请问怎么把deepseek和知识库结合生成私有化的AI Agent，之前是用字节的coze做的，但是coze的模型效果不太好，最近试了一下deepseek，感觉不错，请问是否有比较靠谱的落地方案

zhanghanting

When will the vllm PR be merged to the main branch?

8

Thank you for your impressive work on this project. I'm eager to try this model, but I've noticed that the `vllm` deployment [pull request](https://github.com/vllm-project/vllm/pull/4650) has conflicts with the main branch,...

zuxin666

请问用于代码修复能力评估的prompt是啥呀

renmengjie7

I want to implement code completion based on the company's self-developed component source code fine-tuning model. How should I build the dataset? Is instruction based dialogue generation code built in...

FWLamb

Any changes on repo level concatenation?

13

In deepseek coder v1, I was able to find a detailed explanation of repo level concat in an issue. Has anything changed from the method used in v1 to v2?

IQ179