SicariusSicariiStuff/Assistant_Pepe_70B
Full fine-tune vs meta-llama/Llama-3.1-70B-Instruct. Fine-tune: 100% of the weights changed, across 80 of 80 layers.
Tensors changed: Embeddings 1/1, Norms 161/161, MLP 240/240, Attention 320/320, lm_head 1/1
5 derivatives checked
- bartowski/SicariusSicariiStuff_Assistant_Pepe_70B-GGUF: Quantization
- mradermacher/Assistant_Pepe_70B-i1-GGUF: Quantization
- SicariusSicariiStuff/Assistant_Pepe_70B_GGUF: Quantization
- SicariusSicariiStuff/Assistant_Pepe_70B_GPTQ_AR_4-bit-128: Quantization
- mradermacher/Assistant_Pepe_70B-GGUF: Quantization
2 other repos hold byte-for-byte identical weight files.