lemon07r/Gemma-2-Ataraxy-v4d-9B
Full fine-tune vs lemon07r/Gemma-2-Ataraxy-v4c-9B. Fine-tune: 100% of the weights changed, across 42 of 42 layers.
Tensors changed: lm_head 1/1, Embeddings 1/1, Norms 158/169, MLP 126/126, Attention 168/168
16 derivatives checked
- mradermacher/Gemma-2-Ataraxy-v4d-9B-i1-GGUF: Quantization
- mradermacher/Gemma-2-Ataraxy-v4d-9B-GGUF: Same weights, converted
- zelk12/MT3-Gen5-MU-gemma-2-Av4dG-9B: Full fine-tune
- Alsebay/Gemma2-9b-KuwaNovelist-v4: LoRA-style
- zelk12/MT3-Gen5-MM-gemma-2-MT2Av4d-9B: Full fine-tune
- Alsebay/Gemma2-9B-KuwaNovelist-v3: LoRA-style
- zelk12/MT3-Gen5-IF-gemma-2-Av4dMT2-9B: Full fine-tune
- zelk12/MT3-Gen5-MM-gemma-2-MT2Av4d-9B_v1: Full fine-tune
- Alsebay/Gemma2-9b-KuwaNovelist-2: LoRA-style
- Alsebay/Gemma2-9B-KuwaNovelist: LoRA-style
- zelk12/MT1-Gen5-BB-gemma-2-S4Av4d-9B: Partial fine-tune
- zelk12/MT1-Gen3-MA-gemma-2-S5Av4d-9B: Partial fine-tune
- zelk12/MT5-Gen5-GP-gemma-2-Av4dMTg2-9B: Full fine-tune
- zelk12/MT1-Gen5-MM-gemma-2-Av4dS4-9B: Partial fine-tune
- zelk12/MT3-Gen5-MU-gemma-2-Av4dG-9B_v1: Full fine-tune
- zelk12/MT3-Gen5-IF-gemma-2-Av4dMT2-9B_v1: Full fine-tune
1 other repos hold byte-for-byte identical weight files.