yasserrmd/Human-Like-Qwen2.5-1.5B-Instruct
Same weights, converted vs Qwen/Qwen2.5-1.5B-Instruct. Same weights stored in another dtype (BF16 → F32).
Tensors changed: Embeddings 0/1, Norms 0/57, MLP 0/84, Attention 0/196
3 derivatives checked
- mradermacher/Human-Like-Qwen2.5-1.5B-Instruct-i1-GGUF: Quantization
- mradermacher/Human-Like-Qwen2.5-1.5B-Instruct-GGUF: Same weights, converted
- yasserrmd/Human-Like-Qwen2.5-1.5B-Instruct-gguf: Full fine-tune
66 other repos hold byte-for-byte identical weight files.