Sakalti/SJT-8B-V1.1

Partial fine-tune vs Sakalti/SJT-7B-V1.1. Partial change: 43% of the weights changed (attention, mlp, norms), in 14 of 28 layers.

Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 28/57, MLP 42/84, Attention 98/196

2 derivatives checked

• mradermacher/SJT-8B-V1.1-i1-GGUF: Quantization
• mradermacher/SJT-8B-V1.1-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse