DS-Archive/L3.3-70B-Magnum-v4-SE
Full fine-tune vs meta-llama/Llama-3.3-70B-Instruct. Fine-tune: 99% of the weights changed, across 80 of 80 layers.
Tensors changed: Embeddings 0/1, Norms 0/161, MLP 240/240, Attention 320/320, lm_head 1/1
12 derivatives checked
- bartowski/L3.3-70B-Magnum-v4-SE-GGUF: Quantization
- DS-Archive/L3.3-70B-Magnum-v4-SE-GGUF: Same weights, converted
- mradermacher/L3.3-70B-Magnum-v4-SE-i1-GGUF: Quantization
- mradermacher/L3.3-70B-Magnum-v4-SE-GGUF: Quantization
- DS-Archive/L3.3-70B-Magnum-Nexus: Full fine-tune
- Edens-Gate/llama-MagPicaro-Big: Full fine-tune
- TareksGraveyard/Ethos-Alpha-LLaMa-70B: Full fine-tune
- DS-Archive/L3.3-70B-Magnum-v4-SE-Cirrus-x1-ModelStock: Full fine-tune
- CuriousCat29/3-double-120-v3: Partial fine-tune (fewer layers)
- CuriousCat29/l3-stack-mocha-2: Full fine-tune (fewer layers)
- SanXM1/Vel-Magnum-SE: Full fine-tune
- knifeayumu/Anubis-v1-Magnum-v4-SE-70B: Full fine-tune