jinaai/jina-embeddings-v4-text-code-GGUF
LoRA-style (fewer layers) vs jinaai/jina-embeddings-v4. jinaai/jina-embeddings-v4-text-code-GGUF matches part of jinaai/jina-embeddings-v4 (434 of its 826 tensors; the rest of jinaai/jina-embeddings-v4 has no counterpart). On the shared part: jinaai/jina-embeddings-v4-text-code-GGUF is a GGUF (F16) of different weights. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of down_proj, gate_proj, k_proj, o_proj, q_proj, up_proj, v_proj changed, in 36 of 36 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/1, Norms 0/73, MLP 108/108, Attention 144/252