TheDrummer/Cydonia-24B-v4.3
Full fine-tune (fewer layers) vs mistralai/Mistral-Small-3.2-24B-Instruct-2506. TheDrummer/Cydonia-24B-v4.3 matches part of mistralai/Mistral-Small-3.2-24B-Instruct-2506 (363 of its 585 tensors; the rest of mistralai/Mistral-Small-3.2-24B-Instruct-2506 has no counterpart). On the shared part: Fine-tune: 100% of the weights changed, across 40 of 40 layers.
Tensors changed: Embeddings 1/1, Norms 7/81, MLP 120/120, Attention 160/160, lm_head 1/1
19 derivatives checked
- bartowski/TheDrummer_Cydonia-24B-v4.3-GGUF: Same weights, converted
- tacodevs/Cydonia-24B-v4.3-AWQ: Quantization
- mradermacher/Cydonia-24B-v4.3-i1-GGUF: Quantization
- mradermacher/Cydonia-24B-v4.3-GGUF: Quantization
- Tete-Cohete/Cydonia-24B-v4.3-mlx-8Bit: Quantization
- ealexeev/TheDrummer-Cydonia-24B-v4.3-NVFP4: Quantization
- garrison/Cydonia-24B-v4.3-mlx-2Bit: Quantization
- MuXodious/Cydonia-24B-v4.3-absolute-heresy: Abliterated
- Urucum/Cydonia-24B-v4.3-Q4_K_M-GGUF: Quantization
- coder3101/Cydonia-24B-v4.3-heretic-v4: Abliterated
- coder3101/Cydonia-24B-v4.3-heretic-v2: Abliterated
- coder3101/Cydonia-24B-v4.3-heretic: Abliterated
- coder3101/Cydonia-24B-v4.3-heretic-v3: Abliterated
- Ateron/Predonia-24B-V2.1: Full fine-tune
- Ateron/Sketch-Cydonia: Full fine-tune
- Ateron/Predonia_V2: Full fine-tune
- WarlordHermes/Chekhov-24B-v1.0: LoRA-style
- Sorihon/Amended-Journey-24B: Full fine-tune
- Sorihon/Celestial-Order-24B: Full fine-tune
3 other repos hold byte-for-byte identical weight files.