Reinforcement Learning
Transformers
Safetensors
English
qwen3
text-generation
ipo
rlhf
alignment
qwen
text-generation-inference
Instructions to use AIPlans/Qwen3-0.6B-IPO with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use AIPlans/Qwen3-0.6B-IPO with Transformers:
# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("AIPlans/Qwen3-0.6B-IPO") model = AutoModelForCausalLM.from_pretrained("AIPlans/Qwen3-0.6B-IPO", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Xet hash:
- d297b914eb67827324f122711799a51250b897b321093c38cc27a035c460ae80
- Size of remote file:
- 1.19 GB
- SHA256:
- 34b7a8443524a59ff6c1b03f0d8ce95ed281089e0a8ee141a0df53806d25871e
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.