yasinarafatbd/Qwen2_Audio_Engine_Sound
LoRA-style vs Qwen/Qwen2-Audio-7B-Instruct. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of q_proj, v_proj changed, in 32 of 32 layers; norms, biases and embeddings are untouched.
Tensors changed: other 0/6, Embeddings 0/2, Norms 0/195, MLP 0/224, Attention 64/448, lm_head 0/1
1 derivatives checked
- mradermacher/Qwen2_Audio_Engine_Sound-GGUF: Same weights, converted (fewer layers)