jensjepsen/danish-lm-400m-icl-v3
Full fine-tune vs jensjepsen/danish-lm-400m-sft-v31-avg-top3. Fine-tune: 100% of the weights changed, across 16 of 16 layers.
Tensors changed: Embeddings 1/1, Norms 33/33, MLP 48/48, Attention 64/64
Full fine-tune vs jensjepsen/danish-lm-400m-sft-v31-avg-top3. Fine-tune: 100% of the weights changed, across 16 of 16 layers.
Tensors changed: Embeddings 1/1, Norms 33/33, MLP 48/48, Attention 64/64