TareksGraveyard/Experimental-Base-V2.1-R1-LLaMa-70B
Full fine-tune vs NaniDAO/Llama-3.3-70B-Instruct-ablated. Fine-tune: 100% of the weights changed, across 80 of 80 layers.
Tensors changed: Embeddings 1/1, Norms 161/161, MLP 240/240, Attention 316/320, lm_head 1/1
1 derivatives checked
- mradermacher/Experimental-Base-V2.1-R1-LLaMa-70B-GGUF: Quantization
1 other repos hold byte-for-byte identical weight files.