mradermacher/Anole-7b-i1-GGUF
Full fine-tune (fewer layers) vs GAIR/Anole-7b. mradermacher/Anole-7b-i1-GGUF matches part of GAIR/Anole-7b (419 of its 712 tensors; the rest of GAIR/Anole-7b has no counterpart). On the shared part: mradermacher/Anole-7b-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