eulogik/bharat-embed-270m-gemma2
LoRA-style (fewer layers) vs google/embeddinggemma-2. eulogik/bharat-embed-270m-gemma2 matches part of google/embeddinggemma-2 (413 of its 1376 tensors; the rest of google/embeddinggemma-2 has no counterpart). On the shared part: 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 24 of 24 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/2, Norms 0/170, other 0/73, MLP 72/72, Attention 96/96
1 derivatives checked
- eulogik/bharat-embed-270m-gemma2-GGUF: Same weights, converted