mradermacher/Llama_3.x_70b_Gutenberg-Doppel-L3.3-TDRussel-Storywriter_abliterated_fusion-i1-GGUF

Quantization vs Nexesenex/Llama_3.x_70b_Gutenberg-Doppel-L3.3-TDRussel-Storywriter_abliterated_fusion. mradermacher/Llama_3.x_70b_Gutenberg-Doppel-L3.3-TDRussel-Storywriter_abliterated_fusion-i1-GGUF is a GGUF quantization (Q5_K_M) of the same weights: 161 tensors match exactly and 562 within quantization error.

Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/161, MLP 0/240, Attention 0/320

On the Hub · Downloads on Model Pulse