Update app.py

app.py

@@ -8,8 +8,6 @@ import gradio as gr
 import os
 from spaces import GPU
 from dotenv import load_dotenv
-import torch
-from diffusers import DiffusionPipeline
 
 load_dotenv()
 
@@ -39,9 +37,11 @@ model_configs = [
     {"repo_id": "Ffftdtd5dtft/Qwen2-7B-Instruct-Q2_K-GGUF", "filename": "qwen2-7b-instruct-q2_k.gguf", "name": "Qwen2 7B Instruct"},
     {"repo_id": "Ffftdtd5dtft/starcoder2-3b-Q2_K-GGUF", "filename": "starcoder2-3b-q2_k.gguf", "name": "Starcoder2 3B"},
     {"repo_id": "Ffftdtd5dtft/Qwen2-1.5B-Instruct-Q2_K-GGUF", "filename": "qwen2-1.5b-instruct-q2_k.gguf", "name": "Qwen2 1.5B Instruct"},
+    {"repo_id": "Ffftdtd5dtft/Meta-Llama-3.1-70B-Q2_K-GGUF", "filename": "meta-llama-3.1-70b-q2_k.gguf", "name": "Meta Llama 3.1-70B"},
     {"repo_id": "Ffftdtd5dtft/Mistral-Nemo-Instruct-2407-Q2_K-GGUF", "filename": "mistral-nemo-instruct-2407-q2_k.gguf", "name": "Mistral Nemo Instruct 2407"},
     {"repo_id": "Ffftdtd5dtft/Hermes-3-Llama-3.1-8B-IQ1_S-GGUF", "filename": "hermes-3-llama-3.1-8b-iq1_s-imat.gguf", "name": "Hermes 3 Llama 3.1-8B"},
     {"repo_id": "Ffftdtd5dtft/Phi-3.5-mini-instruct-Q2_K-GGUF", "filename": "phi-3.5-mini-instruct-q2_k.gguf", "name": "Phi 3.5 Mini Instruct"},
+    {"repo_id": "Ffftdtd5dtft/Meta-Llama-3.1-70B-Instruct-Q2_K-GGUF", "filename": "meta-llama-3.1-70b-instruct-q2_k.gguf", "name": "Meta Llama 3.1-70B Instruct"},
     {"repo_id": "Ffftdtd5dtft/codegemma-2b-IQ1_S-GGUF", "filename": "codegemma-2b-iq1_s-imat.gguf", "name": "Codegemma 2B"},
     {"repo_id": "Ffftdtd5dtft/Phi-3-mini-128k-instruct-IQ2_XXS-GGUF", "filename": "phi-3-mini-128k-instruct-iq2_xxs-imat.gguf", "name": "Phi 3 Mini 128K Instruct XXS"},
     {"repo_id": "Ffftdtd5dtft/TinyLlama-1.1B-Chat-v1.0-IQ1_S-GGUF", "filename": "tinyllama-1.1b-chat-v1.0-iq1_s-imat.gguf", "name": "TinyLlama 1.1B Chat"},
@@ -88,13 +88,7 @@ def remove_duplicates(text):
             seen_lines.add(line)
     return '\n'.join(unique_lines)
 
-dtype = torch.bfloat16 if torch.cuda.is_available() else torch.float32
-device = "cuda" if torch.cuda.is_available() else "cpu"
-pipe = DiffusionPipeline.from_pretrained("black-forest-labs/FLUX.1-schnell", torch_dtype=dtype).to(device)
-MAX_SEED = np.iinfo(np.int32).max
-MAX_IMAGE_SIZE = 2048
-
-@spaces.GPU()
+@GPU(duration=1)
 def generate_model_response(model, inputs):
     try:
         response = model(inputs)
@@ -103,21 +97,6 @@ def generate_model_response(model, inputs):
         print(f"Error generating model response: {e}")
         return ""
 
-@spaces.GPU()
-def infer(prompt, seed=42, randomize_seed=False, width=1024, height=1024, num_inference_steps=4):
-    if randomize_seed:
-        seed = random.randint(0, MAX_SEED)
-    generator = torch.Generator(device=device).manual_seed(seed)
-    image = pipe(
-            prompt=prompt,
-            width=width,
-            height=height,
-            num_inference_steps=num_inference_steps,
-            generator=generator,
-            guidance_scale=0.0
-    ).images[0]
-    return image, seed
-
 def remove_repetitive_responses(responses):
     unique_responses = {}
     for response in responses:
@@ -145,88 +124,15 @@ async def process_message(message):
     """
     return formatted_response, curl_command
 
-examples = [
-    "a tiny astronaut hatching from an egg on the moon",
-    "a cat holding a sign that says hello world",
-    "an anime illustration of a wiener schnitzel",
-]
 
-css="""
-#col-container {
-    margin: 0 auto;
-    max-width: 520px;
-}
-"""
-
-with gr.Blocks(css=css) as demo:
-    with gr.Column(elem_id="col-container"):
-        gr.Markdown(f"""# FLUX.1 [schnell]
-12B param rectified flow transformer distilled from [FLUX.1 [pro]](https://blackforestlabs.ai/) for 4 step generation
-[[blog](https://blackforestlabs.ai/announcing-black-forest-labs/)] [[model](https://huggingface.co/black-forest-labs/FLUX.1-schnell)]
-        """)
-
-        with gr.Row():
-            prompt = gr.Text(
-                label="Prompt",
-                show_label=False,
-                max_lines=1,
-                placeholder="Enter your prompt",
-                container=False,
-            )
-            run_button = gr.Button("Run", scale=0)
-        
-        result = gr.Image(label="Result", show_label=False)
-        
-        with gr.Accordion("Advanced Settings", open=False):
-            seed = gr.Slider(
-                label="Seed",
-                minimum=0,
-                maximum=MAX_SEED,
-                step=1,
-                value=0,
-            )
-            randomize_seed = gr.Checkbox(label="Randomize seed", value=True)
-            
-            with gr.Row():
-                width = gr.Slider(
-                    label="Width",
-                    minimum=256,
-                    maximum=MAX_IMAGE_SIZE,
-                    step=32,
-                    value=1024,
-                )
-                height = gr.Slider(
-                    label="Height",
-                    minimum=256,
-                    maximum=MAX_IMAGE_SIZE,
-                    step=32,
-                    value=1024,
-                )
-            
-            with gr.Row():
-                num_inference_steps = gr.Slider(
-                    label="Number of inference steps",
-                    minimum=1,
-                    maximum=50,
-                    step=1,
-                    value=4,
-                )
-
-        gr.Examples(
-            examples=examples,
-            fn=infer,
-            inputs=[prompt],
-            outputs=[result, seed],
-            cache_examples="lazy"
-        )
-
-    gr.on(
-        triggers=[run_button.click, prompt.submit],
-        fn=infer,
-        inputs=[prompt, seed, randomize_seed, width, height, num_inference_steps],
-        outputs=[result, seed]
-    )
+iface = gr.Interface(
+    fn=process_message,
+    inputs=gr.Textbox(lines=2, placeholder="Enter your message here..."),
+    outputs=[gr.Markdown(), gr.Textbox(label="cURL command")],
+    title="Multi-Model LLM API",
+    description="Enter a message and get responses from multiple LLMs.",
+)
 
 if __name__ == "__main__":
     port = int(os.environ.get("PORT", 7860))
-    demo.launch(server_port=port)
+    iface.launch(server_port=port)