compressed-llm
/

vicuna-13b-v1.3-awq

Model card Files Files and versions

jhao commited on Oct 5, 2023

Commit

06332c4

·

1 Parent(s): 77848b5

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -5,7 +5,7 @@ from auto_gptq import AutoGPTQForCausalLM
 import torch
 model_path = 'efficient-llm/vicuna-13b-v1.3-awq'
-config = AutoConfig.from_pretrained(model_path, trust_remote_code=True)
 enc = AutoTokenizer.from_pretrained('meta-llama/Llama-2-7b-hf', trust_remote_code=True)
 kwargs = {"torch_dtype": torch.float16, "low_cpu_mem_usage": True}
 model = AutoModelForCausalLM.from_pretrained(

 import torch
 model_path = 'efficient-llm/vicuna-13b-v1.3-awq'
+config = AutoConfig.from_pretrained(model_path, revision='3bit_128g', trust_remote_code=True)
 enc = AutoTokenizer.from_pretrained('meta-llama/Llama-2-7b-hf', trust_remote_code=True)
 kwargs = {"torch_dtype": torch.float16, "low_cpu_mem_usage": True}
 model = AutoModelForCausalLM.from_pretrained(