Gryphe/Pantheon-RP-1.8-24b-Small-3.1
Full fine-tune (fewer layers) vs mistralai/Mistral-Small-3.1-24B-Instruct-2503. Gryphe/Pantheon-RP-1.8-24b-Small-3.1 matches part of mistralai/Mistral-Small-3.1-24B-Instruct-2503 (363 of its 585 tensors; the rest of mistralai/Mistral-Small-3.1-24B-Instruct-2503 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
17 derivatives checked
- bartowski/Gryphe_Pantheon-RP-1.8-24b-Small-3.1-GGUF: Same weights, converted
- BasedAGI/Pantheon-RP-1.8-24b-Small-3.1-i1-GGUF: Quantization
- mradermacher/Pantheon-RP-1.8-24b-Small-3.1-i1-GGUF: Quantization
- mradermacher/Pantheon-RP-1.8-24b-Small-3.1-GGUF: Quantization
- ewald1976/Pantutu-24b-1.0: Full fine-tune
- yvvki/Erotophobia-24B-v2.0: Full fine-tune
- h34v7/DXP-Zero-V1.0-24b-Small-Instruct: Full fine-tune
- OddTheGreat/Core_24B_V.1: Full fine-tune
- h34v7/DansXPantheon-RP-Engine-V1.2-24b-Small-Instruct-Ties-Merge: Full fine-tune
- win10/Mistral-RP-24b-karcher-pro: Full fine-tune
- yvvki/Erotophobia-24B-v1.0: Full fine-tune
- h34v7/DXP-Zero-V1.2-24b-Small-Instruct: Full fine-tune
- Sorawiz/MistralCreative-24B-Instruct: Full fine-tune
- Vortex5/NovaSage-24B: Full fine-tune
- mergekit-community/Mistral-rp-24b-karcher: Full fine-tune
- mergekit-community/24B-karcher-1000: Full fine-tune
- h34v7/Euro-DDXPv1.0: Full fine-tune
1 other repos hold byte-for-byte identical weight files.