Upload inference.py with huggingface_hub

inference.py

@@ -0,0 +1,54 @@
+from transformers import AutoTokenizer, AutoProcessor, AutoModelForCausalLM
+from qwen_vl_utils import process_vision_info
+model_path = "/vlm/yinxie/code/megatron_ricevl/checkpoint/date_2025_09_12_85malign_26msft_qwen3_8b_resample_oldparameters_pp2-hf"
+
+# default: Load the model on the available device(s)
+model = AutoModelForCausalLM.from_pretrained(
+    model_path, torch_dtype="auto", device_map="auto", trust_remote_code=True
+)
+
+# default processer
+processor = AutoProcessor.from_pretrained(model_path, trust_remote_code=True)
+
+# The default range for the number of visual tokens per image in the model is 4-16384.
+# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
+# min_pixels = 256*28*28
+# max_pixels = 1280*28*28
+# processor = AutoProcessor.from_pretrained("Qwen/Qwen2.5-VL-7B-Instruct", min_pixels=min_pixels, max_pixels=max_pixels)
+
+messages = [
+    {
+        "role": "user",
+        "content": [
+            {
+                "type": "image",
+                "image": "/vlm/yinxie/code/sakura.png",
+            },
+            {"type": "text", "text": "Describe this image."},
+        ],
+    }
+]
+
+# Preparation for inference
+text = processor.apply_chat_template(
+    messages, tokenize=False, add_generation_prompt=True
+)
+image_inputs, video_inputs = process_vision_info(messages)
+inputs = processor(
+    text=[text],
+    images=image_inputs,
+    videos=video_inputs,
+    padding=True,
+    return_tensors="pt",
+)
+inputs = inputs.to("cuda")
+
+# Inference: Generation of the output
+generated_ids = model.generate(**inputs, max_new_tokens=1024)
+generated_ids_trimmed = [
+    out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)
+]
+output_text = processor.batch_decode(
+    generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False
+)
+print(output_text)