mkrussell411/llamauncensoredbetter3.3-70b
Full fine-tune (fewer layers) vs EVA-UNIT-01/EVA-LLaMA-3.33-70B-v0.1. mkrussell411/llamauncensoredbetter3.3-70b matches part of EVA-UNIT-01/EVA-LLaMA-3.33-70B-v0.1 (291 of its 723 tensors; the rest of EVA-UNIT-01/EVA-LLaMA-3.33-70B-v0.1 has no counterpart). On the shared part: Fine-tune: 97% of the weights changed, across 32 of 32 layers.
Tensors changed: lm_head 1/1, Embeddings 1/1, Norms 65/65, MLP 93/96, Attention 124/128
2 derivatives checked
- mradermacher/llamauncensoredbetter3.3-70b-i1-GGUF: Quantization
- mradermacher/llamauncensoredbetter3.3-70b-GGUF: Quantization