tiiuae/Falcon-H1-0.5B-Instruct
Full fine-tune vs tiiuae/Falcon-H1-0.5B-Base. Fine-tune: 100% of the weights changed, across 36 of 36 layers.
Tensors changed: lm_head 1/1, Embeddings 1/1, Norms 73/73, MLP 108/108, other 252/252, Attention 144/144
6 derivatives checked
- unsloth/Falcon-H1-0.5B-Instruct-GGUF: Same weights, converted
- mradermacher/Falcon-H1-0.5B-Instruct-i1-GGUF: Quantization
- mradermacher/Falcon-H1-0.5B-Instruct-GGUF: Same weights, converted
- unsloth/Falcon-H1-0.5B-Instruct: Identical copy
- mlx-community/Falcon-H1-0.5B-Instruct-4bit: Quantization
- megabytes/Falcon-H1-0.5B-Instruct-heretic: Abliterated
1 other repos hold byte-for-byte identical weight files.