mradermacher/jina-embeddings-v4-vllm-retrieval-GGUF

Same weights, converted (fewer layers) vs jinaai/jina-embeddings-v4-vllm-retrieval. mradermacher/jina-embeddings-v4-vllm-retrieval-GGUF matches part of jinaai/jina-embeddings-v4-vllm-retrieval (434 of its 824 tensors; the rest of jinaai/jina-embeddings-v4-vllm-retrieval has no counterpart). On the shared part: Same weights stored in another dtype (BF16 → F16/F32).

Tensors changed: Embeddings 0/1, Norms 0/73, MLP 0/108, Attention 0/252

On the Hub · Downloads on Model Pulse