tickling tensors
-
ornith
A self-improving family of open-source models for agentic coding, correctly exported with reasoning and tool capabilities
tools thinking 9b 35b1,881 Pulls 2 Tags Updated 3 months ago
-
ornith-vision
A self-improving family of open-source models for agentic coding, correctly exported with vision, reasoning and tool capabilities
vision tools thinking 9b 35b1,181 Pulls 2 Tags Updated 3 months ago
-
qwen3.5-9b-r7-research-vision
Fine-tuned Qwen3.5-9B with distilled reasoning and full vision support. 883 tensors (427 text + 441 vision + 15 MTP) — vision tower preserved byte-for-byte from base via llama-export-lora merge.
vision tools thinking798 Pulls 1 Tag Updated 6 months ago
-
kolibri-1
Kolibri: A Sovereign European Model on the Pareto Frontier
tools thinking760 Pulls 2 Tags Updated 2 weeks ago
-
qwen3.5-9b-r5-vision
Fine-tuned Qwen3.5-9B with distilled reasoning and full vision support. 883 tensors — vision tower preserved byte-for-byte from base. R5 was the first vision-capable distilled model.
vision tools thinking621 Pulls 1 Tag Updated 6 months ago
-
qwen3.8-27b-obliterated-e03
Unshackled Qwen3.8 27B using Obliteratus
vision tools thinking 27b612 Pulls 1 Tag Updated 1 month ago
-
ornith-1.5
Ornith-1.5 Vision + Tools + Thinking, a major step toward building foundation models through end-to-end self-improvement.
vision tools thinking 9b594 Pulls 1 Tag Updated 1 month ago
-
ornith-1.5-omni-audio-bridgevision tools thinking
496 Pulls 2 Tags Updated 4 weeks ago
-
ornith-1.5-obliteratedvision tools thinking 9b
414 Pulls 1 Tag Updated 1 month ago
-
qwen3.5-9b-r7-research
Fine-tuned Qwen3.5-9B with distilled reasoning from research-backed datasets. Trained via LoRA SFT with an additive data strategy that preserves base model capabilities while improving instruction following and reasoning.
tools thinking176 Pulls 1 Tag Updated 6 months ago
-
qwen3.8-27b-e03-obliterated-omni
Hybrid Qwen3.8 + Qwen3-omni multi-modal bundle
vision tools thinking138 Pulls 2 Tags Updated 1 month ago
-
qwen3.5-9b-r5-research
Fine-tuned Qwen3.5-9B with distilled reasoning from research-backed datasets. R5 was the first round to use production-quality data sources (Bespoke-Stratos, Tulu-3, SlimOrca) and achieved 84.2% on diverse eval — surpassing the base model.
tools thinking88 Pulls 1 Tag Updated 6 months ago
-
qwen3.8-27b-e03-obliterated-omni-audio-bridgevision tools thinking
83 Pulls 2 Tags Updated 4 weeks ago
-
ornith-1.5-omni
Qwen3 Omni Multimodal Package
vision tools thinking35 Pulls 1 Tag Updated 1 month ago