Back to AIBriefs
LaunchAI Models

DeepReinforce releases Ornith-1.0 self-improving open-source models

DeepReinforce releases Ornith-1.0 self-improving open-source modelsHugging Face Models

Ornith-1.0 includes 9B Dense, 31B Dense, 35B MoE, and 397B MoE models. The 397B MoE flagship matches leading proprietary models, and models learn task scaffolds during training instead of using human-designed harnesses.

deepreinforce-ai/Ornith-1.0-9B2 hours agodeepreinforce-ai
deepreinforce-ai/Ornith-1.0-35B-GGUF10 hours agodeepreinforce-ai
deepreinforce-ai/Ornith-1.0-35B4 hours agodeepreinforce-ai
deepreinforce-ai/Ornith-1.0-397B4 hours agodeepreinforce-ai
DeepReinforce has released Ornith-1.0, their new self-improving family of open-source models...16 hours agoTestingCatalog News
DeepReinforce Releases Ornith-1.0: An Open-Source Coding Model Family That Learns Its Own RL Scaffolds14 hours agoAsif Razzaq
Ornith-1.0 released on Hugging Face15 hours agopaf1138Discuss
Stop waiting for Qwen3.7 Openweights.5 hours ago-OpenSourcerDiscuss
·
Jun 25, 4:56 AM
DeepReinforce releases Ornith-1.0 self-improving open-source models — AIBriefs