You can deploy this model and start earning money today!

tzwilliam0/
maxmin-dpo-init-kl-coef-0.5-fix-reward-norm-dongnan

Name: maxmin-dpo-init-kl-coef-0.5-fix-reward-norm-dongnan
Availability: InStock

reinforcement-learning

apache-2.0

endpoints_compatible

Views

No views yet

TRL Model

This is a TRL language model that has been fine-tuned with reinforcement learning to guide the model outputs according to a value, function, or human feedback. The model can be used for text generation.

Usage

To use this model for inference, first install the TRL library:

python -m pip install trl

You can then generate text as follows:

python

from transformers import pipeline

generator = pipeline("text-generation", model="dn/logs_morlhf/maxmin-dpo-init-kl-coef-0.5-fix-reward-norm/batch_16")
outputs = generator("Hello, my llama is cute")

If you want to use the model for training or to obtain the outputs from the value head, load the model as follows:

python

from transformers import AutoTokenizer
from trl import AutoModelForCausalLMWithValueHead

tokenizer = AutoTokenizer.from_pretrained("dn/logs_morlhf/maxmin-dpo-init-kl-coef-0.5-fix-reward-norm/batch_16")
model = AutoModelForCausalLMWithValueHead.from_pretrained("dn/logs_morlhf/maxmin-dpo-init-kl-coef-0.5-fix-reward-norm/batch_16")

inputs = tokenizer("Hello, my llama is cute", return_tensors="pt")
outputs = model(**inputs, labels=inputs["input_ids"])

tzwilliam0/maxmin-dpo-init-kl-coef-0.5-fix-reward-norm-dongnan

TRL Model

Usage

tzwilliam0/
maxmin-dpo-init-kl-coef-0.5-fix-reward-norm-dongnan