Downloads · 30 days
497
27% of all-time downloads
reward-model-deberta-v3-unit-test
MaxJeblick/reward-model-deberta-v3-unit-test
reward-model-deberta-v3-unit-test is a text classification model from MaxJeblick. Use it when you need a label for a piece of text. It is set up for transformers.
Small dummy deberta-v3-type Reward Model useable for Unit/Integration tests for RLHF. Suitable for CPU only machines, see H2O LLM Studio for an example integration test.
All-time downloads
1.8K
Public
Repo size
14.9 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.json8.7 MB · 50%
At a glance
- Task
- Text Classification
- Library
- transformers
- Model type
- deberta-v2
- Access
- Public
- Created
- Oct 26, 2023
- Updated
- Oct 26, 2023
- SHA
- 5ec7191c
Try a prompt
Model card
From the Hugging Face model README
Small dummy deberta-v3-type Reward Model useable for Unit/Integration tests for RLHF. Suitable for CPU only machines, see H2O LLM Studio for an example integration test.
Model was created as follows:
from transformers import AutoConfig, AutoTokenizer, AutoModelForSequenceClassification
repo_name = "MaxJeblick/reward-model-deberta-v3-unit-test"
model_name = "OpenAssistant/reward-model-deberta-v3-large-v2"
config = AutoConfig.from_pretrained(model_name)
config.hidden_size = 12
config.intermediate_size = 24
config.num_attention_heads = 2
config.num_hidden_layers = 2
config.pooler_hidden_size = 12
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForSequenceClassification.from_config(config)
print(model.num_parameters()) # 1_546_129
model.push_to_hub(repo_name, private=False)
tokenizer.push_to_hub(repo_name, private=False)
config.push_to_hub(repo_name, private=False)
- Task
- Text Classification
- Library
- transformers
- Type
- deberta-v2
- Created
- Oct 26, 2023
- Updated
- Oct 26, 2023