metadata
license: cc-by-nc-4.0
language:
- en
pipeline_tag: text-classification
tags:
- pytorch
- reward_model
- transformers
- RLHF
This is part of the Chai reward-model series, using the GPT2 architecture with a classification head, optimising for a user accepting the completion generated by the base model.
Its training dataset consists of purely user-generated content retry_and_continue_50m_reward_model, where a user has the option to decline the generated response via the retry button or end the conversation.
Model details
- Developed by Chai Research
- Model type: Transformer-based Classification Model
- Language: English
- License: cc-by-nc-4.0
- Contact: to ask questions about this model, join the Chai Discord. For general correspondence: hello@chai-research.com
Uses and limitations
Intended use
Out-of-scope use
How to use
This reward model can be loaded using the AutoModelForSequenceClassification
functionality, with a GPT2 tokenizer where the pad_token_id
is set to the EOS token id, padding sides need to be set according to the configurations used during model training.
from transformers import AutoTokenizer, AutoModelForSequenceClassification
tokenizer = AutoTokenizer.from_pretrained("gpt2")
model = AutoModelForSequenceClassification.from_pretrained("ChaiML/gpt2_base_retry_and_continue_5m_reward_model")
tokenizer.pad_token_id = 50256
tokenizer.truncation_side = ‘left’
tokenizer.padding_side = ‘right’
tokens = self.eval_tokenizer(candidates, return_tensors='pt', return_attention_mask=True, padding='longest', truncation=True, max_length=256)
reward = model(**tokens).logits