Aratako/sarashina2.2-3b-RP-v0.1

Full fine-tune vs sbintuitions/sarashina2.2-3b-instruct-v0.1. Fine-tune: 100% of the weights changed, across 32 of 32 layers.

Tensors changed: lm_head 1/1, Embeddings 1/1, Norms 7/65, MLP 96/96, Attention 128/128

3 derivatives checked

• Aratako/sarashina2.2-3b-RP-v0.1-GGUF: Same weights, converted
• mradermacher/sarashina2.2-3b-RP-v0.1-i1-GGUF: Quantization
• mradermacher/sarashina2.2-3b-RP-v0.1-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse