Text Classification
Transformers
PyTorch
English
deberta-v2
reward-model
reward_model
RLHF
text-embeddings-inference
Instructions to use OpenAssistant/reward-model-deberta-v3-large-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use OpenAssistant/reward-model-deberta-v3-large-v2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="OpenAssistant/reward-model-deberta-v3-large-v2")# Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("OpenAssistant/reward-model-deberta-v3-large-v2") model = AutoModelForSequenceClassification.from_pretrained("OpenAssistant/reward-model-deberta-v3-large-v2") - Inference
- Notebooks
- Google Colab
- Kaggle
np.int deprecation issue
#5
by whiteg671 - opened
The np.int type has gone from being deprecated when this repository was released to now unsupported. Running the model results in an exception in the following script:
lib/python3.10/site-packages/transformers/models/deberta_v2/modeling_deberta_v2.py", line 538, in make_log_bucket_position
bucket_pos = np.where(abs_pos <= mid, relative_pos, log_pos * sign).astype(np.int)
The astype input needs to be changed to either "int" or "np.int_" as shown in the np release below.
https://numpy.org/doc/stable/release/1.20.0-notes.html#deprecations