PocketDoc/Dans-PersonalityEngine-V1.3.0-24b
Full fine-tune (fewer layers) vs mistralai/Mistral-Small-3.1-24B-Base-2503. PocketDoc/Dans-PersonalityEngine-V1.3.0-24b matches part of mistralai/Mistral-Small-3.1-24B-Base-2503 (363 of its 585 tensors; the rest of mistralai/Mistral-Small-3.1-24B-Base-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 15/81, MLP 120/120, Attention 160/160, lm_head 1/1
6 derivatives checked
- bartowski/PocketDoc_Dans-PersonalityEngine-V1.3.0-24b-GGUF: Same weights, converted
- mradermacher/Dans-PersonalityEngine-V1.3.0-24b-i1-GGUF: Quantization
- mradermacher/Dans-PersonalityEngine-V1.3.0-24b-GGUF: Quantization
- DevQuasar/PocketDoc.Dans-PersonalityEngine-V1.3.0-24b-GGUF: Same weights, converted
- MuXodious/Dans-PersonalityEngine-V1.3.0-24b-absolute-heresy: Abliterated
- FlareRebellion/DarkHazard-v2.1-24b: Full fine-tune