AI is happening. The future is updating.Qwen2-0.5B-IMat-GGUF
Original Model: Qwen/Qwen2-0.5B Original dtype: `BF16` (`bfloat16`) Quantized by: llama.cpp b3091 IMatrix dataset: here If the model file is big, it has been split into multiple files. In order to download them all to a local folder, run: According to this investigation, it appears that lower quantizations are the only ones that benefit from the imatrix input (as per hellaswag results).
Original Model: Qwen/Qwen2-0.5B Original dtype: `BF16` (`bfloat16`) Quantized by: llama.cpp b3091 IMatrix dataset: here If the model file is big, it has been split into multiple files. In order to download them all to a local folder, run: According to this investigation, it appears that lower quantizations are the only ones that benefit from the imatrix input (as per hellaswag results).