t-tech/T-lite-it-2.1
Full fine-tune vs Qwen/Qwen3-8B. Fine-tune: 100% of the weights changed, across 36 of 36 layers.
Tensors changed: Norms 145/145, MLP 108/108, Attention 144/144
5 derivatives checked
- t-tech/T-lite-it-2.1-GGUF: Quantization
- pimenovdv/T-lite-it-2.1-AWQ-4bits: Quantization
- t-tech/T-lite-it-2.1-FP8: Quantization
- AGmind/agmind-rag-splitter-ru: LoRA-style
- Xalk07/KSTU_T-lite-2.1: LoRA-style