1.78B Qwen2 image-text record
The captured configuration identifies Qwen2ForCausalLM with model type qwen2, and Safetensors metadata reports about 1.78B parameters.
Open Source Model Profile · Ricky06662
TaskRouter-1.5B
TaskRouter-1.5B is a 1.78B-parameter Qwen2 image-text-to-text model from Ricky06662. Its model card references the VisionReasoner paper and publisher code.
- Publisher
- Ricky06662
- Task
- image-text-to-text
- Model type
- qwen2
- License
- Unknown
- Library
- transformers
- Publication status
- Accepted · not indexed
Model overview
TaskRouter-1.5B is published by Ricky06662 as a Qwen2 image-text-to-text model. The captured configuration identifies Qwen2ForCausalLM with model type qwen2, and Safetensors metadata reports 1,777,088,000 parameters. According to the model card, the repository references the VisionReasoner paper and publisher code, with no extracted license value.
Recorded capabilities
VisionReasoner card references
According to the model card, the repository references the VisionReasoner paper and links publisher code, without extracted training or evaluation detail for this repo.
Transformers-compatible hub record
The hub record lists Transformers support with image-text-to-text, text-generation, conversational, and endpoints-compatible tags.
Use cases in the source record
- Image-text-to-text experiments using the captured Qwen2 configuration and Transformers setup.
Limitations and unknowns
- According to the captured model card text, only paper and code references were extracted; training, evaluation, and usage detail for TaskRouter-1.5B itself are not established.
- No license value, evaluation results, or context-window value were extracted.
- Provider state is historical snapshot data and should be refreshed before being presented as current.
Source and provenance
Source: Ricky06662/TaskRouter-1.5B
Captured: Unknown. Processed: 2026-09-07T19:35:15.476148+00:00.
VisionReasoner: Unified Visual Perception and Reasoning via Reinforcement Learning This repository contains the code for the model described in the paper VisionReasoner: Unified Visual Perception and Reasoning via Reinforcement Learning . Code: https://github.com/dvlab-research/VisionReasoner
F001F002F003F004F005F006F007F008F009F010F011