LatitudeGames/Hearthfire-24B
Full fine-tune (fewer layers) vs mistralai/Mistral-Small-3.2-24B-Instruct-2506. LatitudeGames/Hearthfire-24B 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 0/81, MLP 120/120, Attention 160/160, lm_head 1/1
5 derivatives checked
- LatitudeGames/Hearthfire-24B-GGUF: Same weights, converted
- bartowski/LatitudeGames_Hearthfire-24B-GGUF: Same weights, converted
- mradermacher/Hearthfire-24B-i1-GGUF: Quantization
- mradermacher/Hearthfire-24B-GGUF: Quantization
- MuXodious/Hearthfire-24B-absolute-heresy: Abliterated
1 other repos hold byte-for-byte identical weight files.