kromvault/L3-Horizon-Anteros-v0.1-13B
Full fine-tune (fewer layers) vs Nitral-AI/Hathor_Tahsin-L3-8B-v0.85. Nitral-AI/Hathor_Tahsin-L3-8B-v0.85 matches part of kromvault/L3-Horizon-Anteros-v0.1-13B (291 of its 507 tensors; the rest of kromvault/L3-Horizon-Anteros-v0.1-13B has no counterpart). On the shared part: Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: lm_head 1/1, Embeddings 1/1, Norms 65/65, MLP 96/96, Attention 128/128
3 derivatives checked
- backyardai/L3-Horizon-Anteros-v0.1-13B-GGUF: Quantization
- mradermacher/L3-Horizon-Anteros-v0.1-13B-i1-GGUF: Quantization
- mradermacher/L3-Horizon-Anteros-v0.1-13B-GGUF: Quantization