Comments (6)
2132660698
commented on August 11, 2024
应该是huggingface.co'对国内墙了，需要下载模型到本地，然后在代码里面修改模型路径。
from internlm-xcomposer.
XingchenMengxiang
commented on August 11, 2024
应该是huggingface.co'对国内墙了，需要下载模型到本地，然后在代码里面修改模型路径。
已经本地地址了
self.llm_model = AutoModel.from_pretrained(
'/home/batch/data/internlm-xcomposer-vl-7b', local_files_only=True ,trust_remote_code=True)
tokenizer = AutoTokenizer.from_pretrained(
'/home/batch/data/internlm-xcomposer-vl-7b', local_files_only=True ,trust_remote_code=True)
是不是哪里还需改 ？
from internlm-xcomposer.
2132660698
commented on August 11, 2024
bert-base-uncased从huggingface.co下载后修改
huggingface\internlm-xcomposer\modeling_InternLM_XComposer.py
from internlm-xcomposer.
myownskyW7
commented on August 11, 2024
感谢报告这个问题，我们会很快检查和修复这个bug。
Thank you for reporting this bug. We will check and fix it very soon.
from internlm-xcomposer.
myownskyW7
commented on August 11, 2024
这个问题我们已经在Hugging Face的代码里面修复了，麻烦重新下载最新的代码试一下。如果有其他问题还请反馈，谢谢
The issue regarding Hugging Face access has been resolved. Please pull the latest version of the code on Hugging Face. If necessary, feel free to reopen this issue.
from internlm-xcomposer.
sssssshf
commented on August 11, 2024
这个问题我们已经在Hugging Face的代码里面修复了，麻烦重新下载最新的代码试一下。如果有其他问题还请反馈，谢谢
The issue regarding Hugging Face access has been resolved. Please pull the latest version of the code on Hugging Face. If necessary, feel free to reopen this issue.
我把模型下载到本地了 用的最新的代码还是会出现这个问题
from internlm-xcomposer.
Related Issues (20)
- 已解决
- 预训练阶段段loss下降后升高了，模型训崩了
- The XC2-7B model tends to reply in Chinese HOT 1
- InternLM-XComposer2-4KHD-7B 多卡推理报错 HOT 2
- Interleaved inputs for InternLM-XC-4KHD HOT 1
- fastapi部署报错 HOT 1
- Can we run 4bit Model on RTX4090 with 25GB memory? HOT 1
- Fine-tune Support for InternLM-XComposer2-4KHD-7B HOT 2
- How is the bounding box of the images preprocessed in 4K HD? HOT 1
- 无法连接huggingface找到openai/clip-vit-large-patch14-336，请问这个模型离线怎么跑推理demo？ HOT 1
- 请问INternXCOmperse用的Vit原始的权重链接是哪个？ HOT 1
- When will the proj and vit freeze? HOT 1
- InternLM-XComposer2-4KHD-7B 多卡推理 HOT 1
- IXC2-VL的训练策略 HOT 2
- train模式和test模式差别很大 HOT 6
- Does it support multi-image interleaved conversations? HOT 1
- 能否给出合并lora权重和原模型权重的代码，peft中的merge方法不适用于本代码
- lora微调后的模型权重要如何在finetune.py中加载，进行二次微调 HOT 3
- 推理的时候找不到模型文件中pytorch_model.bin HOT 1
- I would like to ask whether the 100k data of sharegpt4v is brushed with the openai gpt4v interface or the azure gpt4v interface, and what is the version of the interface model?
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 internlm-xcomposer.