sthenno-com/miscii-14b-0218
Full fine-tune vs Qwen/Qwen2.5-14B-Instruct. Fine-tune: 100% of the weights changed, across 48 of 48 layers.
Tensors changed: Norms 94/97, MLP 144/144, Attention 336/336
7 derivatives checked
- mradermacher/miscii-14b-0218-i1-GGUF: Quantization
- mradermacher/miscii-14b-0218-GGUF: Quantization
- suayptalha/Lix-14B-v0.1: Full fine-tune
- sthenno/tempesthenno-ms-0309-001: LoRA-style
- sthenno/tempesthenno-sft-0314-stage1-ckpt50: LoRA-style
- sthenno/tempesthenno-sft-0314: LoRA-style
- sthenno/tempesthenno-ms-0314-001: LoRA-style
1 other repos hold byte-for-byte identical weight files.