Comments (1)
Adding to this, this behavior is in direct contradiction to what's written in the documentation
from transformers.
Related Issues (20)
- Saving and loading `LlavaOnevisionProcessor` results in unexpected behavior HOT 4
- Clarify what kwargs can be accepted by "AutoModelForCausalLM.from_pretrained()"
- Tokenizer encode with fast or not get different tokens HOT 1
- passing past_key_values as a tuple is deprecated, but unclear how to resolve HOT 7
- Pixtral error: The following `model_kwargs` are not used by the model HOT 2
- add `private` parameter to trainer.push_to_hub HOT 2
- ValueError: Unrecognized configuration class with GPTQConfig HOT 6
- The attention mask is not set and cannot be inferred from input because pad token is same as eos token. As a consequence, you may observe unexpected behavior. Please pass your input's `attention_mask` to obtain reliable results. HOT 2
- HubertForSequenceClassification does not handle regression tasks correctly; always uses CrossEntropyLoss HOT 4
- Video Processor as a separate class HOT 1
- test_pt_flax_equivalence and test_encoder_decoder_model_standalone fail running on device (cuda or xpu)
- HQQ HOT 2
- Aviso "All model checkpoint layers were used" mas camadas são inicializadas do zero HOT 3
- Cosine LR Scheduler not decaying HOT 4
- DynamicCache support in vsion llm: "microsoft/Phi-3.5-vision-instruct" HOT 1
- Multi-GPU Training Object Detection HOT 3
- get_input_embeddings return None in SpeechT5Model, which will make testcase failure
- tokenizers v0.20 not supported HOT 2
- Whisper Generate with changed model HOT 1
- Numerical inaccuracy in unpad_image (LlavaOnevison) HOT 6
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.