mradermacher/Gemma-SEA-LION-v4-4B-VL-GGUF

Same weights, converted (fewer layers) vs aisingapore/Gemma-SEA-LION-v4-4B-VL. mradermacher/Gemma-SEA-LION-v4-4B-VL-GGUF matches part of aisingapore/Gemma-SEA-LION-v4-4B-VL (444 of its 883 tensors; the rest of aisingapore/Gemma-SEA-LION-v4-4B-VL has no counterpart). On the shared part: Same weights stored in another dtype (BF16 → F16/F32).

Tensors changed: Embeddings 0/1, Norms 0/205, MLP 0/102, Attention 0/136

On the Hub · Downloads on Model Pulse