mradermacher/boomerang-qwen3-2.3B-GGUF
Same weights, converted vs Harvard-DCML/boomerang-qwen3-2.3B. Same weights stored in another dtype (F32 → F16/F32).
Tensors changed: Embeddings 0/1, Norms 0/77, MLP 0/57, Attention 0/76, lm_head 0/1
Same weights, converted vs Harvard-DCML/boomerang-qwen3-2.3B. Same weights stored in another dtype (F32 → F16/F32).
Tensors changed: Embeddings 0/1, Norms 0/77, MLP 0/57, Attention 0/76, lm_head 0/1