Comments (3)
cc @gante too :)
from transformers.
Hey! These models are not supported yet! We could actually open this to the community and get all decoder models to support compile soon-ish.
Do you want to open a PR?
from transformers.
Hi @ArthurZucker, I would love to contribute. However, I am not sure what you mean by get all decoder models to support compile
. Aren't nn.Module
s compile friendly out of the box?
from transformers.
Related Issues (20)
- The implementations of `LlamaAttention` and `LlamaSdpaAttention` are not equivalent. HOT 2
- Can you please provide:
- Model load when dtypes match is broken HOT 4
- [Error] with Trainer: TypeError: Unsupported types (<class 'NoneType'>) passed to `_gpu_broadcast_one`.
- Extra dataset features not passing to the custom collator HOT 3
- max_length calculation for padding the generation outputs in the Seq2SeqTrainer prediction_step function HOT 2
- cannot import name 'Conversation' from 'transformers' HOT 1
- Unrecognized configuration class ChameleonConfig HOT 5
- Using Trainer + a pretrained tokenizer + 4D attention mask is extremely slow
- gemma2 + flash atten Error: RuntimeError: linalg.vector_norm: Expected a floating point or complex tensor as input. Got Long HOT 3
- Licence HOT 2
- ValueError: The checkpoint you are trying to load has model type `chameleon` but Transformers does not recognize this architecture. This could be because of an issue with the checkpoint, or because your version of Transformers is out of date. HOT 1
- Gemma template won't end with eos_token HOT 9
- LlavaNextVideo always assumes left padding when batch size is 1 HOT 1
- _prepare_4d_causal_attention_mask mask inversion should work boolean masks HOT 2
- Output from model.Generate & model.forward not same when output attention/hidden_state is True
- Metadata HOT 1
- RuntimeError: Failed to import transformers.pipelines because of the following error (look up to see its traceback): module 'tensorflow' has no attribute 'data' HOT 1
- Exception raised when running `T5-like span-masked language modeling` example in `examples/flax/language-modeling/` HOT 2
- TF Lite model created from TFWhisperForConditionalGeneration.from_pretrained craches HOT 2
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.