Update app.py

app.py

@@ -29,7 +29,7 @@ import re
 """
 For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
 """
-client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
+# client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
 
 # Functions for inference
 def image_parser(args):
@@ -53,8 +53,10 @@ def load_images(image_files):
         out.append(image)
     return out
 
-model_path = "liuhaotian/llava-v1.6-mistral-7b"
+# model_path = "liuhaotian/llava-v1.6-mistral-7b"
+mode_path = "model_weights/"
 model_name = get_model_name_from_path(model_path)
+
 # tokenizer = AutoTokenizer.from_pretrained(model_path)
 # model = LlavaMistralForCausalLM.from_pretrained(
 #                     model_path,
@@ -166,30 +168,31 @@ def respond(
     temperature,
     top_p,
 ):
-    messages = [{"role": "system", "content": system_message}]
-
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
-
-    messages.append({"role": "user", "content": message})
-
-    response = ""
-
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
-
-        response += token
-        yield response
-
+    # messages = [{"role": "system", "content": system_message}]
+
+    # for val in history:
+    #     if val[0]:
+    #         messages.append({"role": "user", "content": val[0]})
+    #     if val[1]:
+    #         messages.append({"role": "assistant", "content": val[1]})
+
+    # messages.append({"role": "user", "content": message})
+
+    # response = ""
+
+    # for message in client.chat_completion(
+    #     messages,
+    #     max_tokens=max_tokens,
+    #     stream=True,
+    #     temperature=temperature,
+    #     top_p=top_p,
+    # ):
+    #     token = message.choices[0].delta.content
+
+    #     response += token
+    #     yield response
+    yield "ungaa bungaa"
+    
 
 """
 For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface