ZeroWw/DeepSeek-V2-Lite-Chat-GGUF

license: mit language:

• —en ---

My own (ZeroWw) quantizations. output and embed tensors quantized to f16. all other tensors quantized to q5k or q6k.

Result: both f16.q6 and f16.q5 are smaller than q8_0 standard quantization and they perform as well as the pure f16.

Updated on: Fri Jul 12, 13:14:04