Comments (5)
lewtun
commented on May 29, 2024
2
Thanks for the snippet!
Yes, SetFitModel isn't (yet) compatible with the pipeline() function from transformers. Instead you can run inference as follows:
# Save trained model to disk
trainer.model.save_pretrained("tuned-model")
# Load SetFit model
tuned_model = SetFitModel.from_pretrained("tuned-model")
# Run inference
tuned_model(["i didnt feel humiliated", "i feel romantic too", "im grabbing a minute to post i feel greedy wrong"])from setfit.
lewtun
commented on May 29, 2024
Hey @jrivd thanks for reporting the issue! Could you please share a code snippet with how the error is being generated?
from setfit.
jrivd
commented on May 29, 2024
Sure, there it is:
tokenizer = AutoTokenizer.from_pretrained("sentence-transformers/paraphrase-mpnet-base-v2")
model = SetFitModel.from_pretrained("sentence-transformers/paraphrase-mpnet-base-v2")
trainer = SetFitTrainer(
model=model,
train_dataset=hg_dataset_train,
eval_dataset=hg_dataset_test,
loss_class=CosineSimilarityLoss,
batch_size=16,
num_epochs=1,
num_iterations=2,
)
!echo CUDA_VISIBLE_DEVICES
trainer.train()
metrics = trainer.evaluate()
torch.save(trainer, 'model.pt')
saved_model = torch.load('model.pt')
pipe = pipeline(task="sentiment-analysis", model=saved_model, tokenizer=tokenizer)
>>>'SetFitTrainer' object has no attribute 'config'
from setfit.
jrivd
commented on May 29, 2024
That is great. Many thanks!
El El mié, 28 sept 2022 a las 14:37, lewtun ***@***.***>
escribió:
… Thanks for the snippet!
Yes, SetFitModel isn't (yet) compatible with the pipeline() function from
transformers. Instead you can run inference as follows:
# Save trained model to disktrainer.model.save_pretrained("tuned-model")# Load SetFit modeltuned_model = SetFitModel.from_pretrained("tuned-model")# Run inferencetuned_model(["i didnt feel humiliated", "i feel romantic too", "im grabbing a minute to post i feel greedy wrong"])
—
Reply to this email directly, view it on GitHub
<#67 (comment)>,
or unsubscribe
<https://github.com/notifications/unsubscribe-auth/AYO4QYSVCOFRYIGPEG5X7HDWAQ3W5ANCNFSM6AAAAAAQWYHBLE>
.
You are receiving this because you were mentioned.Message ID:
***@***.***>
from setfit.
lewtun
commented on May 29, 2024
Great! Closing this issue for now - feel free to reopen if needed :)
from setfit.
Related Issues (20)
- trust_remote_code not passed in properly
- Totally unreliable results. What I'm doing wrong? HOT 1
- ABSA for Non-English Language HOT 4
- facing issue while importing setfit classifier HOT 1
- Warning from sentence-transformer, version 2.3.1 HOT 1
- Hyperparameter tuning for AbsaModel
- No timeout downloading model card data from hub api when loading pretrained model in disconnected environment
- model_config = model.config.to_dict() - AttributeError: 'dict' object has no attribute 'to_dict' HOT 9
- ValueError: Multioutput target data is not supported with label binarization
- Mis-alignment between Sentence Embeddings and Classifier in multi-label classification ?
- EarlyStoppingCallback early_stopping_patience_counter and Trainer.state not reset between hyperparameter search trials HOT 1
- Custom TF classification head HOT 2
- `TypeError: __init__() got an unexpected keyword argument '_name_or_path'` for `SetFitModel.from_pretrained` HOT 4
- TemplateAssertionError: no test named 'False' HOT 2
- Can we use Setfit just for finetuning ST Embedding model to create embeddings HOT 2
- MultiGPU support or better intergration for loading models
- i found a typo in docs HOT 1
- Methodological error in zero cost, zero time, zero shot notebook HOT 2
- Usage of deprecated `evaluation_strategy` in TrainingArguments HOT 1
- Data validation when using differentiable_head
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 setfit.