mradermacher/Qwen2_Audio_Engine_Sound-GGUF

Same weights, converted (fewer layers) vs yasinarafatbd/Qwen2_Audio_Engine_Sound. mradermacher/Qwen2_Audio_Engine_Sound-GGUF matches part of yasinarafatbd/Qwen2_Audio_Engine_Sound (387 of its 876 tensors; the rest of yasinarafatbd/Qwen2_Audio_Engine_Sound has no counterpart). On the shared part: Same weights stored in another dtype (F16 → F16/F32).

Tensors changed: Embeddings 0/1, Norms 0/65, MLP 0/96, Attention 0/224, lm_head 0/1

On the Hub · Downloads on Model Pulse