nitky/Swallow-70b-NVE-RP
Full fine-tune vs DS-Archive/lzlv-limarpv3-l2-70b. Fine-tune: 100% of the weights changed, across 80 of 80 layers.
Tensors changed: Embeddings 1/1, Norms 161/161, MLP 240/240, Attention 320/320, lm_head 1/1
3 derivatives checked
- mradermacher/Swallow-70b-NVE-RP-GGUF: Quantization
- mradermacher/Swallow-70b-NVE-RP-i1-GGUF: Quantization
- nitky/Swallow-70b-RP: Full fine-tune