leon-se
/

Aria-sequential_mlp-FP8-dynamic

Image-Text-to-Text

Inference Endpoints

compressed-tensors

Model card Files Files and versions Community

leon-se commited on Dec 29, 2024

Commit

35ea031

·

verified ·

1 Parent(s): 5c82453

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -24,7 +24,7 @@ from PIL import Image
 from transformers import AutoModelForCausalLM, AutoProcessor, BitsAndBytesConfig
 torch.cuda.set_device(0)
-model_id_or_path = "thwin27/Aria-sequential_mlp-bnb_FP8-dynamic"
 model = AutoModelForCausalLM.from_pretrained(model_id_or_path, device_map="auto", torch_dtype=torch.bfloat16, trust_remote_code=True)
 processor = AutoProcessor.from_pretrained(model_id_or_path, trust_remote_code=True)

 from transformers import AutoModelForCausalLM, AutoProcessor, BitsAndBytesConfig
 torch.cuda.set_device(0)
+model_id_or_path = "leon-se/Aria-sequential_mlp-bnb_FP8-dynamic"
 model = AutoModelForCausalLM.from_pretrained(model_id_or_path, device_map="auto", torch_dtype=torch.bfloat16, trust_remote_code=True)
 processor = AutoProcessor.from_pretrained(model_id_or_path, trust_remote_code=True)