Cornell-RelaxML/quip-sharp Issues
model size confirmation
Closed 3Group-wise Quantization
Closed 1Pytorch dequantization
Closed 33 bit quantization
Closed 4What could went wrong
Closed 3support qwen model
Closed 38ROCm Build Error
Updated 3In the same vein as #17
Closed 1trouble building quip_tools
Closed 3Problem with namespace nvcuda
Closed 6mistral-7b
Closed 7mixtral 8x7b
Closed 1Load LORA?
Closed 1custom 1.3B llama quant
Closed 22How to quant 1.3B model to 2bit
Closed 3Low Ppl benchmark results
Closed 1Mistral models output gibberish
Closed 1