MHA2MLA-VLM The MHA2MLA-VLM model published in the paper "MHA2MLA-VLM: Enabling DeepSeek's Economical Multi-Head Latent Attention across Vision-Language Models" cnxup/Qwen2.5-VL-7B-MLA-stage1-rope32 8B • Updated Jan 23 • 10 • 1 cnxup/Qwen2.5-VL-7B-MLA-stage2-rope32-d_kv_32 8B • Updated Jan 27 • 2 • 1 cnxup/Qwen2.5-VL-7B-MLA-stage2-rope32-d_kv_64 8B • Updated Jan 27 • 3 • 1 cnxup/Qwen2.5-VL-7B-MLA-stage2-rope32-d_kv_128 8B • Updated Jan 27 • 4 • 1
MHA2MLA-VLM The MHA2MLA-VLM model published in the paper "MHA2MLA-VLM: Enabling DeepSeek's Economical Multi-Head Latent Attention across Vision-Language Models" cnxup/Qwen2.5-VL-7B-MLA-stage1-rope32 8B • Updated Jan 23 • 10 • 1 cnxup/Qwen2.5-VL-7B-MLA-stage2-rope32-d_kv_32 8B • Updated Jan 27 • 2 • 1 cnxup/Qwen2.5-VL-7B-MLA-stage2-rope32-d_kv_64 8B • Updated Jan 27 • 3 • 1 cnxup/Qwen2.5-VL-7B-MLA-stage2-rope32-d_kv_128 8B • Updated Jan 27 • 4 • 1
