Reinforcement Learning
Transformers
Safetensors
English
checkpoint-archive
knowledge-distillation
on-policy-distillation
qwen2.5
Instructions to use colored-dye/OPD-scaling-checkpoints with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use colored-dye/OPD-scaling-checkpoints with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("colored-dye/OPD-scaling-checkpoints", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Ctrl+K
- math-qwen2.5-0.5b-sft2ep-300k-offpd-from-qwen2.5-0.5b-rltrain-5resp-5ep
- math-qwen2.5-0.5b-sft2ep-300k-offpd-from-qwen2.5-1.5b-rltrain-5resp-5ep
- math-qwen2.5-0.5b-sft2ep-300k-offpd-from-qwen2.5-14b-rltrain-5resp-5ep
- math-qwen2.5-0.5b-sft2ep-300k-offpd-from-qwen2.5-3b-rltrain-5resp-5ep
- math-qwen2.5-0.5b-sft2ep-300k-offpd-from-qwen2.5-7b-rltrain-5resp-5ep
- math-qwen2.5-1.5b-sft2ep-300k-offpd-from-qwen2.5-0.5b-rltrain-5resp-5ep
- math-qwen2.5-1.5b-sft2ep-300k-offpd-from-qwen2.5-1.5b-rltrain-5resp-5ep
- math-qwen2.5-1.5b-sft2ep-300k-offpd-from-qwen2.5-14b-rltrain-5resp-5ep
- math-qwen2.5-1.5b-sft2ep-300k-offpd-from-qwen2.5-3b-rltrain-5resp-5ep
- math-qwen2.5-1.5b-sft2ep-300k-offpd-from-qwen2.5-7b-rltrain-5resp-5ep
- math-qwen2.5-14b-sft2ep-300k-offpd-from-qwen2.5-0.5b-rltrain-5resp-5ep
- math-qwen2.5-14b-sft2ep-300k-offpd-from-qwen2.5-1.5b-rltrain-5resp-5ep
- math-qwen2.5-14b-sft2ep-300k-offpd-from-qwen2.5-14b-rltrain-5resp-5ep
- math-qwen2.5-14b-sft2ep-300k-offpd-from-qwen2.5-3b-rltrain-5resp-5ep
- math-qwen2.5-14b-sft2ep-300k-offpd-from-qwen2.5-7b-rltrain-5resp-5ep
- math-qwen2.5-3b-sft2ep-300k-offpd-from-qwen2.5-0.5b-rltrain-5resp-5ep
- math-qwen2.5-3b-sft2ep-300k-offpd-from-qwen2.5-1.5b-rltrain-5resp-5ep
- math-qwen2.5-3b-sft2ep-300k-offpd-from-qwen2.5-14b-rltrain-5resp-5ep
- math-qwen2.5-3b-sft2ep-300k-offpd-from-qwen2.5-3b-rltrain-5resp-5ep
- math-qwen2.5-3b-sft2ep-300k-offpd-from-qwen2.5-7b-rltrain-5resp-5ep
- math-qwen2.5-7b-sft2ep-300k-offpd-from-qwen2.5-0.5b-rltrain-5resp-5ep
- math-qwen2.5-7b-sft2ep-300k-offpd-from-qwen2.5-1.5b-rltrain-5resp-5ep
- math-qwen2.5-7b-sft2ep-300k-offpd-from-qwen2.5-14b-rltrain-5resp-5ep
- math-qwen2.5-7b-sft2ep-300k-offpd-from-qwen2.5-3b-rltrain-5resp-5ep
- math-qwen2.5-7b-sft2ep-300k-offpd-from-qwen2.5-7b-rltrain-5resp-5ep