Comments (1)
DeepSeek-Coder-V2-Instruct 与 deepseek-moe 的架构一致, template 也一致,用deepseek应该就可以微调。我理解应该是无需增加的。
from llama-factory.
Related Issues (20)
- 什么时候支持基于Ray的分布式Lora微调呢?
- 使用A10对qwen-14b-chat进行Lora微调,2机2卡训练比1机2卡慢了10倍 HOT 3
- RuntimeError: "addmm_impl_cpu_" not implemented for 'Half' 华为910 命令行推理报错 HOT 1
- ModuleNotFoundError: No module named 'vllm.lora' HOT 2
- 训练34B-reward,Assertion `srcIndex < srcSelectDimSize` failed HOT 2
- windows上start直接Fail并出现llamafactory-cli乱码 HOT 2
- 4张M40 配置,使用accelerate启动训练,出现TypeError: unsupported operand type(s) for *: 'NoneType' and 'int' HOT 2
- 大模型微调分类任务,但是预测结果是不固定的 HOT 3
- Yi-1.5-9B推理gpu利用率为0 HOT 1
- deepspeed ds_z3_offload_config单卡全量微调训练glm4出现exits with return code = -9。出现该问题时,CPU内存(252G)占满,想问一下这个问题该如何解决? HOT 1
- 请问可以微调没有lm head模型吗 HOT 1
- Qwen dpo训练卡住 HOT 1
- 910b qwen2 lora生成的模型如何合并权重 HOT 1
- 如何在yaml中配置环境变量中tensorboard的路径呢 HOT 1
- PiSSA训练和推理的疑问? HOT 1
- Qwen2 debug 发现 labels全为-100 HOT 2
- 能不能把eval loss曲线加到训练过程中?
- 预测推理特别慢,跑完GPU利用率为0了一直卡在那里好像是构建generation HOT 1
- Qwen2 lora微调后用llamafactory-cli export命令合并模型 推理结果有"assstant: "前缀 HOT 8
- 无法加载safetensor格式的权重 HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from llama-factory.