update docs

Author: xffxff

docs/inference.md

@@ -14,10 +14,11 @@ from PIL import Image
 from transformers import AutoModelForCausalLM, AutoProcessor
 
 model_id_or_path = "rhymes-ai/Aria"
+revision = "4844f0b5ff678e768236889df5accbe4967ec845"
 
-model = AutoModelForCausalLM.from_pretrained(model_id_or_path, device_map="auto", torch_dtype=torch.bfloat16, trust_remote_code=True)
+model = AutoModelForCausalLM.from_pretrained(model_id_or_path, revision=revision, device_map="auto", torch_dtype=torch.bfloat16, trust_remote_code=True)
 
-processor = AutoProcessor.from_pretrained(model_id_or_path, trust_remote_code=True)
+processor = AutoProcessor.from_pretrained(model_id_or_path, revision=revision, trust_remote_code=True)
 
 image_path = "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/cat.png"
 
@@ -96,17 +97,20 @@ from PIL import Image
 from transformers import AutoTokenizer
 from vllm import LLM, SamplingParams
 
+revision = "4844f0b5ff678e768236889df5accbe4967ec845"
+
 
 def main():
     llm = LLM(
         model="rhymes-ai/Aria",
+        revision=revision,
         tokenizer_mode="slow",
         dtype="bfloat16",
         trust_remote_code=True,
     )
 
     tokenizer = AutoTokenizer.from_pretrained(
-        "rhymes-ai/Aria", trust_remote_code=True, use_fast=False
+        "rhymes-ai/Aria", revision=revision, trust_remote_code=True, use_fast=False
     )
 
     messages = [