Comments (5)
同问,我用lora也是
from chatglm.cpp.
目前还不支持转换 p-tuning 的模型,会考虑支持下。
lora 是支持的,需要加 -l
参数指定 lora checkpoint,参考 README:
For LoRA model, add -l <lora_model_name_or_path> flag to merge your LoRA weights into the base model.
from chatglm.cpp.
目前还不支持转换 p-tuning 的模型,会考虑支持下。
lora 是支持的,需要加
-l
参数指定 lora checkpoint,参考 README:For LoRA model, add -l <lora_model_name_or_path> flag to merge your LoRA weights into the base model.
我已经将p-tuning微调的参数合并到原模型中了,然后再对合并的模型量化,这样也不行吗?
from chatglm.cpp.
目前还不支持转换 p-tuning 的模型,会考虑支持下。
lora 是支持的,需要加
-l
参数指定 lora checkpoint,参考 README:For LoRA model, add -l <lora_model_name_or_path> flag to merge your LoRA weights into the base model.
我看了一下export的源码 ,发现-l貌似不起作用耶,在convert那个函数里
from chatglm.cpp.
目前还不支持转换 p-tuning 的模型,会考虑支持下。
lora 是支持的,需要加
-l
参数指定 lora checkpoint,参考 README:For LoRA model, add -l <lora_model_name_or_path> flag to merge your LoRA weights into the base model.
ptuning后的模型,大概啥时候可以支持?或者有解决思路吗?
from chatglm.cpp.
Related Issues (20)
- macos m2 芯片最后一步出现Illegal instruction: 4 HOT 1
- 我想启动web端提醒这个报错,你们遇到过吗,麻烦给指点一下 HOT 3
- 运行chatglm3-6b-ggml int4量化模型,采用clblast加速反而比cpu加速慢很多,正常吗? HOT 1
- streamlit run chatglm3_demo.py 执行后报错,No module named 'chatglm_cpp._C' ,是什么原因呢? HOT 2
- CMake 编译时出现错误 HOT 1
- 支持minicpm-2b HOT 1
- 多卡推理
- cmake --build build -j --config Release 命令报错
- 请求编译好的程序 HOT 1
- Illegal instruction
- Docker build failed【Parse error. Expected a command name, got bad character with text "".】
- 官方docker无法使用 HOT 1
- 如何保存会话,比如,我之前,已经告诉他,让他记住一个电话号码,以后重新启动这个程序,能让他告诉我这个电话号码吗? HOT 1
- 使用chatglm_cpp/openai_api.py 提供接口服务,oneapi一测试链接就崩溃 HOT 1
- 在量化模型的时候出现segmentation fault HOT 1
- 什么时候支持amd的gpu HOT 4
- 在启用 cuBLAS 之后,等权重数据加载到显存后,最好能释放内存里的权重数据 HOT 1
- docker运行镜像cpu模式下,cpu的利用率最大只有1600%,如何提升? HOT 4
- Windows系统 安装 chatGLM 分享 HOT 2
- 关于单次最大回复值的tokens值
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 chatglm.cpp.