tiiuae/Falcon-H1-1.5B-Deep-Instruct
Full fine-tune vs tiiuae/Falcon-H1-1.5B-Deep-Base. Fine-tune: 100% of the weights changed, across 66 of 66 layers.
Tensors changed: Norms 199/199, MLP 198/198, other 462/462, Attention 264/264
7 derivatives checked
- unsloth/Falcon-H1-1.5B-Deep-Instruct-GGUF: Same weights, converted
- tiiuae/Falcon-H1-1.5B-Deep-Instruct-GGUF: Same weights, converted
- mradermacher/Falcon-H1-1.5B-Deep-Instruct-i1-GGUF: Quantization
- mradermacher/Falcon-H1-1.5B-Deep-Instruct-GGUF: Same weights, converted
- tiiuae/Falcon-H1-1.5B-Deep-Instruct-GPTQ-Int8: Quantization
- tiiuae/Falcon-H1-1.5B-Deep-Instruct-GPTQ-Int4: Quantization
- DevQuasar/tiiuae.Falcon-H1-1.5B-Deep-Instruct-GGUF: Same weights, converted
1 other repos hold byte-for-byte identical weight files.