sgsystems/Falcon-H1-7B-FORGE-v2
Full fine-tune vs tiiuae/Falcon-H1-7B-Instruct. sgsystems/Falcon-H1-7B-FORGE-v2 is a GGUF (Q6_K/TQ2_0) of different weights. Fine-tune: 100% of the weights changed, across 44 of 44 layers.
Tensors changed: Embeddings 1/1, MLP 132/132, Norms 89/89, Attention 176/176, lm_head 1/1