| { |
| "qwen3-vl-2b": { |
| "base": "Qwen/Qwen3-VL-Embedding-2B", |
| "revision": "9f2f7e710d6d81056aa5c0a4f04764fec6bb7bda", |
| "frame_lora": "qwen3-vl-2b/frame_adapter.safetensors", |
| "query_lora": "qwen3-vl-2b/query_lora.safetensors", |
| "scale": 1.0, |
| "architecture": "qwen3-vl", |
| "description": "Qwen3-VL-Embedding-2B with a screenshot retrieval LoRA for questions and a consistency adapter for pruned, streamed frames" |
| }, |
| "qwen3-vl-8b": { |
| "base": "Qwen/Qwen3-VL-Embedding-8B", |
| "revision": "2c4565515e0f265c6511776e7193b22c0968ddc7", |
| "frame_lora": "qwen3-vl-8b/frame_adapter.safetensors", |
| "query_lora": "qwen3-vl-8b/query_lora.safetensors", |
| "scale": 1.0, |
| "architecture": "qwen3-vl", |
| "description": "Qwen3-VL-Embedding-8B with a screenshot retrieval LoRA for questions and a consistency adapter for pruned, streamed frames" |
| }, |
| "siglip2-so400m": { |
| "base": "google/siglip2-so400m-patch16-naflex", |
| "revision": "cc24074f717b612951c2dead130904ab9b65a81e", |
| "frame_lora": "siglip2-so400m/frame_adapter.safetensors", |
| "query_lora": "siglip2-so400m/query_lora.safetensors", |
| "scale": 1.0, |
| "architecture": "siglip2", |
| "max_num_patches": 1024, |
| "description": "SigLIP2 So400m NaFlex with a screenshot retrieval LoRA and a consistency adapter for pruned frames" |
| }, |
| "siglip2-base": { |
| "base": "google/siglip2-base-patch16-naflex", |
| "revision": "b53b807d3a2d5e2b3911292f2d69e5341cdc064c", |
| "frame_lora": "siglip2-base/frame_adapter.safetensors", |
| "query_lora": "siglip2-base/query_lora.safetensors", |
| "scale": 1.0, |
| "architecture": "siglip2", |
| "max_num_patches": 1024, |
| "description": "SigLIP2 Base NaFlex with a screenshot retrieval LoRA and a consistency adapter for pruned frames" |
| }, |
| "vultron-0.8b": { |
| "base": "vultr/VultronRetrieverFlash-Qwen3.5-0.8B", |
| "revision": "6f6b6757e9ea3ad93f4f2cbd839bc6f2f0b93739", |
| "frame_lora": "vultron-0.8b/frame_adapter.safetensors", |
| "query_lora": "vultron-0.8b/query_lora.safetensors", |
| "scale": 1.0, |
| "architecture": "qwen3.5", |
| "description": "VultronRetrieverFlash (Qwen3.5 0.8B) with a screenshot retrieval LoRA and a consistency adapter for pruned, streamed frames" |
| } |
| } |
|
|
