feat: gradio demo integration (#16)

Co-authored-by: Bo Liu <benjaminliu.eecs@gmail.com>
Co-authored-by: Haoyu Lu <ruclhy1998@163.com>

inference.py

@@ -1,37 +1,52 @@
+# Copyright (c) 2023-2024 DeepSeek.
+#
+# Permission is hereby granted, free of charge, to any person obtaining a copy of
+# this software and associated documentation files (the "Software"), to deal in
+# the Software without restriction, including without limitation the rights to
+# use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies of
+# the Software, and to permit persons to whom the Software is furnished to do so,
+# subject to the following conditions:
+#
+# The above copyright notice and this permission notice shall be included in all
+# copies or substantial portions of the Software.
+#
+# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS
+# FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR
+# COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER
+# IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+# CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
+
 import torch
 from transformers import AutoModelForCausalLM
 
-from deepseek_vl.models import VLChatProcessor, MultiModalityCausalLM
+from deepseek_vl.models import MultiModalityCausalLM, VLChatProcessor
 from deepseek_vl.utils.io import load_pil_images
 
-
 # specify the path to the model
 model_path = "deepseek-ai/deepseek-vl-7b-chat"
 vl_chat_processor: VLChatProcessor = VLChatProcessor.from_pretrained(model_path)
 tokenizer = vl_chat_processor.tokenizer
 
-vl_gpt: MultiModalityCausalLM = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True)
+vl_gpt: MultiModalityCausalLM = AutoModelForCausalLM.from_pretrained(
+    model_path, trust_remote_code=True
+)
 vl_gpt = vl_gpt.to(torch.bfloat16).cuda().eval()
 
 conversation = [
     {
         "role": "User",
         "content": "<image_placeholder>Describe each stage of this image.",
-        "images": ["./images/training_pipelines.jpg"]
+        "images": ["./images/training_pipelines.jpg"],
     },
-    {
-        "role": "Assistant",
-        "content": ""
-    }
+    {"role": "Assistant", "content": ""},
 ]
 
 
 # load images and prepare for inputs
 pil_images = load_pil_images(conversation)
 prepare_inputs = vl_chat_processor(
-    conversations=conversation,
-    images=pil_images,
-    force_batchify=True
+    conversations=conversation, images=pil_images, force_batchify=True
 ).to(vl_gpt.device)
 
 # run image encoder to get the image embeddings
@@ -46,7 +61,7 @@ outputs = vl_gpt.language_model.generate(
     eos_token_id=tokenizer.eos_token_id,
     max_new_tokens=512,
     do_sample=False,
-    use_cache=True
+    use_cache=True,
 )
 
 answer = tokenizer.decode(outputs[0].cpu().tolist(), skip_special_tokens=True)