tiiuae/Falcon-H1-1.5B-Instruct
Full fine-tune vs tiiuae/Falcon-H1-1.5B-Base. Fine-tune: 100% of the weights changed, across 24 of 24 layers.
Tensors changed: Norms 73/73, MLP 72/72, other 168/168, Attention 96/96
7 derivatives checked
- tiiuae/Falcon-H1-1.5B-Instruct-GGUF: Same weights, converted
- unsloth/Falcon-H1-1.5B-Instruct-GGUF: Same weights, converted
- mradermacher/Falcon-H1-1.5B-Instruct-i1-GGUF: Quantization
- mradermacher/Falcon-H1-1.5B-Instruct-GGUF: Same weights, converted
- tiiuae/Falcon-H1-1.5B-Instruct-GPTQ-Int4: Quantization
- tiiuae/Falcon-H1-1.5B-Instruct-GPTQ-Int8: Quantization
- DevQuasar/tiiuae.Falcon-H1-1.5B-Instruct-GGUF: Same weights, converted
2 other repos hold byte-for-byte identical weight files.