BNarayanaReddy/higgs-telugu-e5-lora-epoch_9
LoRA-style (fewer layers) vs bosonai/higgs-tts-3-4b. BNarayanaReddy/higgs-telugu-e5-lora-epoch_9 matches part of bosonai/higgs-tts-3-4b (398 of its 929 tensors; the rest of bosonai/higgs-tts-3-4b 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 36 of 36 layers; norms, biases and embeddings are untouched.
Tensors changed: Norms 0/145, MLP 108/108, Attention 144/144, Embeddings 0/1