sbintuitions/sarashina2.2-1b-instruct-v0.1
Full fine-tune vs sbintuitions/sarashina2.2-1b. Fine-tune: 100% of the weights changed, across 24 of 24 layers.
Tensors changed: lm_head 1/1, Embeddings 1/1, Norms 49/49, MLP 72/72, Attention 96/96
2 derivatives checked
- mmnga/sarashina2.2-1b-instruct-v0.1-gguf: Quantization
- DevQuasar-9/sbintuitions.sarashina2.2-1b-instruct-v0.1-GGUF: Same weights, converted