mradermacher/text-to-cypher-Gemma-3-4B-Instruct-2025.04.0-GGUF
Same weights, converted (fewer layers) vs neo4j/text-to-cypher-Gemma-3-4B-Instruct-2025.04.0. mradermacher/text-to-cypher-Gemma-3-4B-Instruct-2025.04.0-GGUF matches part of neo4j/text-to-cypher-Gemma-3-4B-Instruct-2025.04.0 (444 of its 883 tensors; the rest of neo4j/text-to-cypher-Gemma-3-4B-Instruct-2025.04.0 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