trashpanda-org/MS-24B-Bline-v0
Full fine-tune vs arcee-ai/Arcee-Blitz. Fine-tune: 100% of the weights changed, across 40 of 40 layers.
Tensors changed: lm_head 1/1, Norms 15/81, MLP 120/120, Attention 160/160, Embeddings 1/1
1 derivatives checked
- mradermacher/MS-24B-Bline-v0-GGUF: Quantization