adding chat

app.py

@@ -1,63 +1,52 @@
+import torch
+from transformers import AutoModel, AutoTokenizer, AutoProcessor, LlavaForConditionalGeneration
 import gradio as gr
-from huggingface_hub import InferenceClient
-
-"""
-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")
-
-
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    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
-
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
-demo = gr.ChatInterface(
-    respond,
-    additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
-        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
-        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
-        gr.Slider(
-            minimum=0.1,
-            maximum=1.0,
-            value=0.95,
-            step=0.05,
-            label="Top-p (nucleus sampling)",
-        ),
-    ],
-)
-
-
-if __name__ == "__main__":
-    demo.launch()
+
+# Specify CPU usage
+device = torch.device("cpu")
+
+model_id = "hitmanonholiday/llava-1.5-7b-4bit-finetuned3"
+
+# Load the tokenizer
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+
+# Load the model without quantization
+model = LlavaForConditionalGeneration.from_pretrained(
+    model_id,
+    torch_dtype=torch.float32  # Use float32 for CPU compatibility
+).to(device)
+
+# Load the processor (if needed)
+processor = AutoProcessor.from_pretrained(model_id)
+processor.tokenizer = tokenizer
+
+# Define the chat template (if using Gradio)
+LLAVA_CHAT_TEMPLATE = """A chat between a curious user and an artificial intelligence assistant.
+The assistant gives helpful, detailed, and polite answers to the user's questions.
+{% for message in messages %}{% if message['role'] == 'user' %}
+USER: {% else %}ASSISTANT: {% endif %}{% for item in message['content'] %}{% if item['type'] == 'text' %}{{ item['text'] }}{% elif item['type'] == 'image' %}<image>{% endif %}{% endfor %}
+{% if message['role'] == 'user' %} {% else %}{{eos_token}}{% endif %}{% endfor %}"""
+
+tokenizer.chat_template = LLAVA_CHAT_TEMPLATE
+
+# Define the prediction function (if using Gradio)
+def predict(image, text):
+    # Process the image (if needed)
+    inputs = processor(images=image, text=text, return_tensors="pt").to(device)
+
+    # Generate response
+    with torch.no_grad():
+        outputs = model.generate(input_ids=inputs['input_ids'], attention_mask=inputs['attention_mask'])
+
+    response = tokenizer.decode(outputs[0], skip_special_tokens=True)
+    return response
+
+# Define Gradio interface (if using Gradio)
+inputs = [
+    gr.inputs.Image(type="pil", label="Upload an image"),
+    gr.inputs.Textbox(lines=2, placeholder="Type your text here...", label="Input Text")
+]
+
+outputs = gr.outputs.Textbox(label="Output")
+
+gr.Interface(fn=predict, inputs=inputs, outputs=outputs, title="LLAVA Multimodal Chatbot").launch(share=True)

requirements.txt

@@ -1 +1,6 @@
-huggingface_hub==0.22.2
+huggingface_hub==0.22.2
+transformers
+torch
+gradio
+torchvision
+torchaudio