Dat1710/nexus-1.5b

Same weights, converted vs Qwen/Qwen2.5-Math-1.5B-Instruct. Same weights stored in another dtype (BF16 → F16).

Tensors changed: Embeddings 0/1, Norms 0/57, MLP 0/84, Attention 0/196

2 derivatives checked

• mradermacher/nexus-1.5b-i1-GGUF: Quantization
• mradermacher/nexus-1.5b-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse