GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
redflash6
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
redflash6
Model Tree
redflash6/singleshotgrpo
Input Modalities
Output Modalities
Supported Functionality
This release contains the planner, tokenizer, processor configuration, and chat template. Video generators, optimizer states, and training data are not included. The GRPO releases use BF16 inference exports of their selected training checkpoints.
Use a Transformers version with Qwen3_5ForConditionalGeneration support:
python
import torchfrom transformers import AutoProcessor, Qwen3_5ForConditionalGeneration model_id = "redflash6/multishotgrpo"processor = AutoProcessor.from_pretrained(model_id)model = Qwen3_5ForConditionalGeneration.from_pretrained( model_id, dtype=torch.bfloat16, device_map="auto")This loads the planner, not an end-to-end video generator. Use the REEL tool runtime and backend adapters to execute memory actions and connect separately deployed video-generation services.
SFT · Single-shot GRPO · Multi-shot GRPO
bibtex
@misc{xu2026reel, title = {REEL: Learning to Retrieve, Evaluate, and Evolve Visual Memory for Any Long-Horizon Multi-Shot Video Generation}, author = {Hang Xu and Guohui Zhang and Xiaoxiao Ma and Hu Yu and Jie Huang and Jiayin Xiao and Lin Song and Haoyang Huang and Nan Duan and Feng Zhao}, year = {2026}, note = {Preprint}, url = {https://xuhang07.github.io/REEL/}}import torchfrom transformers import AutoProcessor, Qwen3_5ForConditionalGeneration model_id = "redflash6/multishotgrpo"processor = AutoProcessor.from_pretrained(model_id)model = Qwen3_5ForConditionalGeneration.from_pretrained( model_id, dtype=torch.bfloat16, device_map="auto")@misc{xu2026reel, title = {REEL: Learning to Retrieve, Evaluate, and Evolve Visual Memory for Any Long-Horizon Multi-Shot Video Generation}, author = {Hang Xu and Guohui Zhang and Xiaoxiao Ma and Hu Yu and Jie Huang and Jiayin Xiao and Lin Song and Haoyang Huang and Nan Duan and Feng Zhao}, year = {2026}, note = {Preprint}, url = {https://xuhang07.github.io/REEL/}}