Hugging Face's logo

qgallouedec
/
online-dpo-qwen2-4

Text Generation
Transformers
Safetensors
qwen2
trl
Generated from Trainer
online-dpo
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
online-dpo-qwen2-4 / README.md
qgallouedec's picture
qgallouedec HF staff
End of training
044170d verified
preview code
|
raw
history blame contribute delete
1.49 kB
metadata
base_model: Qwen/Qwen2-0.5B-Instruct
datasets: trl-lib/ultrafeedback-prompt
library_name: transformers
model_name: online-dpo-qwen2-4
tags:
  - trl
  - generated_from_trainer
  - online-dpo
licence: license

Model Card for online-dpo-qwen2-4

This model is a fine-tuned version of Qwen/Qwen2-0.5B-Instruct on the trl-lib/ultrafeedback-prompt dataset. It has been trained using TRL.

Quick start 

from transformers import pipeline

question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
generator = pipeline("text-generation", model="qgallouedec/online-dpo-qwen2-4", device="cuda")
output = generator([{"role": "user", "content": question}], max_new_tokens=500)[0]
print(output["generated_text"][1]["content"])

Training procedure

Visualize in Weights & Biases

This model was trained with Online DPO, a method introduced in Direct Language Model Alignment from Online AI Feedback.

Framework versions

  • TRL: 0.12.0.dev0
  • Transformers: 4.45.0.dev0
  • Pytorch: 2.4.1
  • Datasets: 3.0.0
  • Tokenizers: 0.19.1