v0.2.0 (#330)

Co-authored-by: jinz2014 <7799920+jinz2014@users.noreply.github.com>
Co-authored-by: Jin Z <5zj@cousteau.ftpn.ornl.gov>

examples/basic_quant.py → examples/quantize.py

 from awq import AutoAWQForCausalLM
 from transformers import AutoTokenizer
 
-model_path = 'lmsys/vicuna-7b-v1.5'
-quant_path = 'vicuna-7b-v1.5-awq'
+model_path = 'mistralai/Mistral-7B-Instruct-v0.2'
+quant_path = 'mistral-instruct-v0.2-awq'
 quant_config = { "zero_point": True, "q_group_size": 128, "w_bit": 4, "version": "GEMM" }
 
 # Load model
-# NOTE: pass safetensors=True to load safetensors
 model = AutoAWQForCausalLM.from_pretrained(
     model_path, **{"low_cpu_mem_usage": True, "use_cache": False}
 )