tiiuae/falcon-mamba-7b-instruct
Full fine-tune vs tiiuae/falcon-mamba-7b. Fine-tune: 100% of the weights changed, across 64 of 64 layers.
Tensors changed: Embeddings 1/1, other 575/576, Norms 65/65, lm_head 1/1
5 derivatives checked
- tiiuae/falcon-mamba-7b-instruct-Q4_K_M-GGUF: Quantization
- Felladrin/gguf-falcon-mamba-7b-instruct: Quantization
- tiiuae/falcon-mamba-7b-instruct-4bit: Quantization
- Felladrin/gguf-sharded-falcon-mamba-7b-instruct: Quantization
- KotshinZ/mamba-distill-7b: Full fine-tune
1 other repos hold byte-for-byte identical weight files.