Update README.md

README.md

@@ -4,10 +4,11 @@ base_model:
 - rhymes-ai/Aria-sequential_mlp
 - rhymes-ai/Aria
 pipeline_tag: image-text-to-text
+library_name: transformers
 ---
 # Aria-sequential_mlp-FP8-dynamic
-FP8-Dynamic quantization from [Aria-sequential_mlp](https://huggingface.co/rhymes-ai/Aria-sequential_mlp) made with [llm-compressor](https://github.com/vllm-project/llm-compressor), requires about xx.x GB of VRAM.
-### Installation
+FP8-Dynamic quantization from [Aria-sequential_mlp](https://huggingface.co/rhymes-ai/Aria-sequential_mlp) made with [llm-compressor](https://github.com/vllm-project/llm-compressor), requires about 24.8 GB of VRAM.
+### Installationcompressed-tensors
 ```
 pip install transformers==4.45.0 accelerate==0.34.1 sentencepiece==0.2.0 torchvision requests torch Pillow compressed-tensors
 pip install flash-attn --no-build-isolation
@@ -24,7 +25,7 @@ torch.cuda.set_device(0)
 
 model_id_or_path = "thwin27/Aria-sequential_mlp-bnb_FP8-dynamic"
 
-model = AutoModelForCausalLM.from_pretrained(model_id_or_path, torch_dtype=torch.bfloat16, trust_remote_code=True)
+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)
 
 image_path = "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/cat.png"