aiplanet
/

effi-7b-awq

Text Generation

text-generation-inference

4-bit precision

Model card Files Files and versions Community

bhavyaaiplanet commited on Feb 10

Commit

1ff7374

•

1 Parent(s): 3f20f63

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -46,7 +46,7 @@ from transformers import AutoTokenizer , AutoModelForCausalLM
 quant_path = "aiplanet/effi-7b-awq"
-model = AutoModelForCausalLM.from_pretrained(quant_path).to(0)
 tokenizer = AutoTokenizer.from_pretrained(quant_path, trust_remote_code=True , safetensors=True , fuse_layers=True)

 quant_path = "aiplanet/effi-7b-awq"
+model = AutoModelForCausalLM.from_pretrained(quant_path , device_map='cuda')
 tokenizer = AutoTokenizer.from_pretrained(quant_path, trust_remote_code=True , safetensors=True , fuse_layers=True)