mradermacher/VeriReason-Qwen2.5-1.5b-RTLCoder-Verilog-GRPO-reasoning-tb-GGUF
Same weights, converted vs Nellyw888/VeriReason-Qwen2.5-1.5b-RTLCoder-Verilog-GRPO-reasoning-tb. Same weights stored in another dtype (F32 → F16/F32).
Tensors changed: Embeddings 0/1, Norms 0/57, MLP 0/84, Attention 0/196