Sakalti/SJT-7B-V1.1
Full fine-tune vs bunnycore/Qwen2.5-7B-RRP-1M. Fine-tune: 100% of the weights changed, across 28 of 28 layers.
Tensors changed: lm_head 1/1, Embeddings 1/1, Norms 57/57, MLP 84/84, Attention 196/196
4 derivatives checked
- mradermacher/SJT-7B-V1.1-i1-GGUF: Quantization
- mradermacher/SJT-7B-V1.1-GGUF: Same weights, converted
- Sakalti/SJT-8B-V1.1: Partial fine-tune
- Sakalti/SJT-7B-V1.1-Multilingal: Full fine-tune