Hugging Face's logo

nicholasKluge
/
RewardModel

Text Classification
Transformers
PyTorch
Safetensors
English
bert
reward model
alignment
preference model
RLHF
text-embeddings-inference
Model card Files
xet
Community
2
nicholasKluge commited on
Commit
d5be6bf
·
1 Parent(s): 8d0ac59

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -2
README.md CHANGED
@@ -61,9 +61,8 @@ config = AutoConfig.from_pretrained('nicholasKluge/RewardModel', trust_remote_co
61
  tokenizer = AutoTokenizer.from_pretrained('nicholasKluge/RewardModel', trust_remote_code=True, config=config, revision='main')
62
  rewardModel = AutoModel.from_pretrained('nicholasKluge/RewardModel', trust_remote_code=True, config=config, revision='main')
63
 
64
- rewardModel.to(device)
65
  rewardModel.eval()
66
-
67
 
68
  # Define the question and response
69
  question = "What is the capital of France?"
 
61
  tokenizer = AutoTokenizer.from_pretrained('nicholasKluge/RewardModel', trust_remote_code=True, config=config, revision='main')
62
  rewardModel = AutoModel.from_pretrained('nicholasKluge/RewardModel', trust_remote_code=True, config=config, revision='main')
63
 
 
64
  rewardModel.eval()
65
+ rewardModel.to(device)
66
 
67
  # Define the question and response
68
  question = "What is the capital of France?"