mradermacher/OpenSparX-3b-cabin-intent-GGUF

Same weights, converted (fewer layers) vs qualcomm-ai-hub-community/OpenSparX-3b-cabin-intent. mradermacher/OpenSparX-3b-cabin-intent-GGUF matches part of qualcomm-ai-hub-community/OpenSparX-3b-cabin-intent (435 of its 825 tensors; the rest of qualcomm-ai-hub-community/OpenSparX-3b-cabin-intent has no counterpart). On the shared part: Same weights stored in another dtype (BF16 → F16/F32).

Tensors changed: Embeddings 0/1, Norms 0/73, MLP 0/108, Attention 0/252, lm_head 0/1

On the Hub · Downloads on Model Pulse