VOOZH about

URL: https://huggingface.co/SicariusSicariiStuff/Negative_LLAMA_70B_EXL3_d_2.5bpw

⇱ SicariusSicariiStuff/Negative_LLAMA_70B_EXL3_d_2.5bpw · Hugging Face


Configuration Parsing Warning:In config.json: "quantization_config.bits" must be an integer

Note

This was made to test extremely low quants. 70B is pretty usable at 2.50 bpw. A custom strategy for quanting was used, for details check EXL3 repo. This was made to fit a single 32GB card like the 5090.

Downloads last month
1
Safetensors
Model size
12B params
Tensor type
F16
·
I16
·

Model tree for SicariusSicariiStuff/Negative_LLAMA_70B_EXL3_d_2.5bpw

Dataset used to train SicariusSicariiStuff/Negative_LLAMA_70B_EXL3_d_2.5bpw