afrizalha
/

Bakpia-V1-9B-Javanese-4bit

Text Generation

text-generation-inference

Inference Endpoints

4-bit precision

Model card Files Files and versions Community

afrizalha commited on Jul 7

Commit

2889544

•

1 Parent(s): 7cb3f94

Update README.md

Files changed (1) hide show

README.md +1 -0

README.md CHANGED Viewed

@@ -68,6 +68,7 @@ from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig
 tokenizer = AutoTokenizer.from_pretrained("afrizalha/Bakpia-V1-9B-Javanese-4bit")
 model = AutoModelForCausalLM.from_pretrained("afrizalha/Bakpia-V1-9B-Javanese-4bit", quantization_config=BitsAndBytesConfig(load_in_4bit=True))
 template = """<start_of_turn>user
 {prompt}<end_of_turn>

 tokenizer = AutoTokenizer.from_pretrained("afrizalha/Bakpia-V1-9B-Javanese-4bit")
 model = AutoModelForCausalLM.from_pretrained("afrizalha/Bakpia-V1-9B-Javanese-4bit", quantization_config=BitsAndBytesConfig(load_in_4bit=True))
+model.to("cuda")
 template = """<start_of_turn>user
 {prompt}<end_of_turn>