mradermacher/AceGPT-v2-32B-Chat-GGUF
Full fine-tune vs FreedomIntelligence/AceGPT-v2-32B-Chat. mradermacher/AceGPT-v2-32B-Chat-GGUF is a GGUF (Q8_0) of different weights. Fine-tune: 100% of the weights changed, across 64 of 64 layers.
Tensors changed: Embeddings 1/1, Norms 0/129, MLP 192/192, Attention 384/512, lm_head 1/1