Comments (2)
We could try that. Not sure how important it is though. Did you try it?
from transformers.
Ok I think we will stick to the normal_initializer for now. Thanks for indicating this option!
from transformers.
Related Issues (20)
- BERT output is different even in an eval() mode for the same input string in single vs batch mode. HOT 1
- examples/pytorch/language_modeling/requirements.txt needs to be updated HOT 1
- Incompatibility Issue between RAG Model Code and Faiss Library HOT 1
- Official guide for classification task is False, it reports an error HOT 3
- Question about an error when using mixed-precision-training on V100 HOT 3
- Google Colab: ValueError: Connection error, and we cannot find the requested files in the cached path. HOT 1
- `device_map='auto' support for BertForSequenceClassification for inference using large models HOT 1
- WhisperForAudioClassification cannot evaluate during training using use_weighted_layer_sum HOT 3
- Loss calculation bug in BartForCausalLM
- Unused or unrecognized kwargs: padding, max_length, truncation. HOT 7
- Can Transformers AutoModel Support to(dml) HOT 2
- Layer_drop interferes with gradient_checkpoint operation in DDP. HOT 1
- Image classification pipeline fails with base64.encodebytes() input HOT 2
- llama-2 device_map (2,3) & `model.generate` HOT 4
- Possible issue with safetensors loading for TF models HOT 5
- Training model constantly increases memory consumption HOT 2
- What is the default multi-GPU training type? HOT 5
- Inconsitent module names (state_dict keys). HOT 6
- LayoutLM.from_pretrained doesn't load embeddings' weights when using safetensors HOT 1
- [Bug] Owlv2 Zero-Shot Object Detection HOT 5
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 transformers.