Web server demo Int4
#3
by
lktinhtemp
- opened
Can I replace code in README.md for web_server demo to use int4 ?
Yes, you should replace the model initialization to AutoGPTQForCausalLM.from_quantized
Can I replace code in README.md for web_server demo to use int4 ?
Yes, you should replace the model initialization to AutoGPTQForCausalLM.from_quantized