allura-org/TQ2.5-14B-Neon-v1
Partial fine-tune vs arcee-ai/SuperNova-Medius. Partial change: 89% of the weights changed (attention, mlp, norms), in 48 of 48 layers.
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 12/97, MLP 144/144, Attention 207/336
7 derivatives checked
- bartowski/TQ2.5-14B-Neon-v1-GGUF: Same weights, converted
- mradermacher/TQ2.5-14B-Neon-v1-i1-GGUF: Quantization
- allura-org/TQ2.5-14B-Neon-v1-GGUF: Same weights, converted
- featherless-ai-quants/allura-org-TQ2.5-14B-Neon-v1-GGUF: Quantization
- mradermacher/TQ2.5-14B-Neon-v1-GGUF: Quantization
- MaziyarPanahi/TQ2.5-14B-Neon-v1-GGUF: Same weights, converted
- allura-org/TQ2.5-14B-Aletheia-v1: Partial fine-tune