Downloads · 30 days
1
1% of all-time downloads
Yuhan123/reading-level-pairwise-reward-chosen-12th-grade-rejected-7th-grade-1-steps-1000
reading-level-pairwise-reward-chosen-12th-grade-rejected-7th-grade-1-steps-1000 is a text generation model from Yuhan123. Use it when you need the model to write or continue text. The card lists the license as apache-2.0.
This model was fine-tuned using PPO (Proximal Policy Optimization) as part of RLHF (Reinforcement Learning from Human Feedback).
Downloads · 30 days
1
1% of all-time downloads
All-time downloads
69
Public
Parameters
1.5B
5.9 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors5.9 GB · 100%
From the Hugging Face model README
This model was fine-tuned using PPO (Proximal Policy Optimization) as part of RLHF (Reinforcement Learning from Human Feedback).
data/olmo_reading_level_pairwise_reward_chosen_12th_grade_rejected_7th_grade_-1_steps_1000/best_modelfrom transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("Yuhan123/reading-level-pairwise-reward-chosen-12th-grade-rejected-7th-grade-1-steps-1000")
model = AutoModelForCausalLM.from_pretrained("Yuhan123/reading-level-pairwise-reward-chosen-12th-grade-rejected-7th-grade-1-steps-1000")
# Generate text
inputs = tokenizer("Hello, world!", return_tensors="pt")
outputs = model.generate(**inputs, max_length=100)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
This repository contains the best checkpoint from the training run, including:
.safetensors format)This model represents the best performing checkpoint from a PPO training run. For more details about the training process, please refer to the original training logs.