prithivMLmods/Qwen3-4B-ft-bf16
Same weights, repacked vs Qwen/Qwen3-4B. Same weights in different files (re-saved, re-sharded or new metadata).
Tensors changed: Embeddings 0/1, Norms 0/145, MLP 0/108, Attention 0/144
6 derivatives checked
- prithivMLmods/Blitzar-Coder-4B-F.1: Full fine-tune
- prithivMLmods/Bootes-Qwen3_Coder-Reasoning: LoRA-style
- prithivMLmods/Lacaille-MoT-4B-Supreme2: LoRA-style
- prithivMLmods/Cetus-Qwen3_4B-GeneralThought: LoRA-style
- prithivMLmods/Canum-Qwen3_R1-4B-iCoT: LoRA-style
- prithivMLmods/BetaCeti-Beta-4B-Prime1: Abliterated