mradermacher/Anole-Zebra-CoT-i1-GGUF

Full fine-tune (fewer layers) vs multimodal-reasoning-lab/Anole-Zebra-CoT. mradermacher/Anole-Zebra-CoT-i1-GGUF matches part of multimodal-reasoning-lab/Anole-Zebra-CoT (419 of its 712 tensors; the rest of multimodal-reasoning-lab/Anole-Zebra-CoT has no counterpart). On the shared part: mradermacher/Anole-Zebra-CoT-i1-GGUF is a GGUF (Q6_K) of different weights. Fine-tune: 100% of the weights changed, across 32 of 32 layers.

Tensors changed: Embeddings 1/1, Norms 128/193, MLP 96/96, Attention 128/128, lm_head 1/1

On the Hub · Downloads on Model Pulse