Xiaojian9992024/Qwen2.5-Dyanka-7B-Preview
Full fine-tune vs Xiaojian9992024/Qwen2.5-THREADRIPPER-Small. Fine-tune: 100% of the weights changed, across 28 of 28 layers.
Tensors changed: lm_head 1/1, Embeddings 1/1, Norms 33/57, MLP 84/84, Attention 194/196
7 derivatives checked
- mradermacher/Qwen2.5-Dyanka-7B-Preview-GGUF: Same weights, converted
- suayptalha/Clarus-7B-v0.3: Full fine-tune
- lkoenig/BBAI_230_Xiaqwen: Full fine-tune
- marcuscedricridia/cursa-o1-7b: Full fine-tune
- Xiaojian9992024/Qwen2.5-Dyanka-7B-Pharaoh: LoRA-style
- ZeroXClem/Qwen2.5-7B-HomerFuse-NerdExp: Full fine-tune
- nkpz/Qwen2.5-Dyanka-7B-Preview-Uncensored-DeLMAT: LoRA-style
1 other repos hold byte-for-byte identical weight files.