This is functionaly similar to vidore/colqwen2-v1.0, but only 87M and based on the upstream Qwen/Qwen2-VL-2B-Instruct
Model tree for LeakyAbstraction/colqwen2-v1.0-lite
Base model
Qwen/Qwen2-VL-2B
Finetuned
Qwen/Qwen2-VL-2B-Instruct
Finetuned
vidore/colqwen2-base
Finetuned
vidore/colqwen2-v1.0