hanzla/Falcon3-Mamba-R1-v0
Partial fine-tune vs tiiuae/Falcon3-Mamba-7B-Instruct. Partial change: 65% of the weights changed (embeddings, norms, other), in 64 of 64 layers.
Tensors changed: Embeddings 1/1, other 208/576, Norms 1/65, lm_head 0/1
1 derivatives checked
- mradermacher/Falcon3-Mamba-R1-v0-GGUF: Partial fine-tune