Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Website
Tasks
HuggingChat
Collections
Languages
Organizations
Community
Blog
Posts
Daily Papers
Hardware
Learn
Discord
Forum
GitHub
Solutions
Team & Enterprise
Hugging Face PRO
Enterprise Support
Inference Providers
Inference Endpoints
Storage Buckets
Log In
Sign Up
prism-drift
/
RL-Repaired-V1
Like
0
Follow
Prism 2026 AI Preference Drift
8
Text Generation
PEFT
Safetensors
reinforcement-learning
dpo
grpo
ppo
lora
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
Deploy
Copy to bucket
new
Use this model
Instructions to use prism-drift/RL-Repaired-V1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
Libraries
PEFT
How to use prism-drift/RL-Repaired-V1 with PEFT:
Task type is invalid.
Notebooks
Google Colab
Kaggle
main
RL-Repaired-V1
/
4b
Commit History
Sep 7
14:06
Upload six repaired-v1 Step-125 RL checkpoints
xianglinyang
Verified signature
2f45ac5
Qwen3.5 4B/9B x DPO/GRPO/PPO, seed 0, exact repaired-v1 cohorts; normalize adapter base IDs and attach immutable provenance manifests.
