Create app.py

app.py

@@ -0,0 +1,170 @@
+import os
+import time
+import spaces
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer, TextIteratorStreamer
+import gradio as gr
+
+from threading import Thread
+
+MODEL = "rombodawg/Rombos-LLM-V2.6-Qwen-14b"
+HF_TOKEN = os.environ.get("HF_TOKEN", None)
+
+TITLE = """
+<h1><center>Rombos-LLM-V2.6-Qwen-14b</center></h1>
+<center>
+<p>The model is licensed under apache 2.0</p>
+</center>
+"""
+
+
+PLACEHOLDER = """
+<center>
+<p>rombodawg/Rombos-LLM-V2.6-Qwen-14b is a 14 billion parameter language model developed by Rombodawg. Its my highest quality model for its size.</p>
+</center>
+"""
+
+CSS = """
+.duplicate-button {
+    margin: auto !important;
+    color: white !important;
+    background: black !important;
+    border-radius: 100vh !important;
+}
+h3 {
+    text-align: center;
+}
+"""
+
+device = "cuda" # for GPU usage or "cpu" for CPU usage
+
+tokenizer = AutoTokenizer.from_pretrained(MODEL)
+model = AutoModelForCausalLM.from_pretrained(
+    MODEL,
+    torch_dtype=torch.bfloat16,
+    device_map="auto",
+    trust_remote_code=True,
+    ignore_mismatched_sizes=True)
+
+def format_chat(system_prompt, history, message):
+    formatted_chat = f"<|im_start|>system\n{system_prompt}<|im_end|>\n"
+
+    for prompt, answer in history:
+        formatted_chat += f"<|im_start|>user\n{prompt}<|im_end|>\n<|im_start|>assistant\n{answer}<|im_end|>\n"
+    formatted_chat += f"<|im_start|>user\n{message}<|im_end|>\n<|im_start|>assistant\n"
+    return formatted_chat
+
+@spaces.GPU()
+def stream_chat(
+    message: str, 
+    history: list,
+    system_prompt: str,
+    temperature: float = 0.3, 
+    max_new_tokens: int = 256, 
+    top_p: float = 1.0
+, 
+    top_k: int = 20, 
+    repetition_penalty: float = 1.2,
+):
+    print(f'message: {message}')
+    print(f'history: {history}')
+
+    formatted_prompt = format_chat(system_prompt, history, message)
+    inputs = tokenizer(formatted_prompt, return_tensors="pt").to(device)
+    
+    streamer = TextIteratorStreamer(tokenizer, timeout=5000.0
+, skip_prompt=True, skip_special_tokens=True)
+    
+    generate_kwargs = dict(
+        input_ids=inputs.input_ids,
+        max_new_tokens=max_new_tokens,
+        do_sample=False if temperature == 0 else True,
+        top_p=top_p,
+        top_k=top_k,
+        temperature=temperature,
+        repetition_penalty=repetition_penalty,
+        streamer=streamer,
+        pad_token_id=tokenizer.pad_token_id,
+        eos_token_id=tokenizer.eos_token_id
+    )
+
+    with torch.no_grad():
+        thread = Thread(target=model.generate, kwargs=generate_kwargs)
+        thread.start()
+        
+    buffer = ""
+    for new_text in streamer:
+        buffer += new_text
+        if "<|endoftext|>" in buffer:
+            yield buffer.split("<|endoftext|>")[0]
+            break
+        yield buffer
+
+chatbot = gr.Chatbot(height=600, placeholder=PLACEHOLDER)
+
+with gr.Blocks(css=CSS, theme="soft") as demo:
+    gr.HTML(TITLE)
+    gr.DuplicateButton(value="Duplicate Space for private use", elem_classes="duplicate-button")
+    gr.ChatInterface(
+        fn=stream_chat,
+        chatbot=chatbot,
+        fill_height=True,
+        additional_inputs_accordion=gr.Accordion(label="⚙️ Parameters", open=False, render=False),
+        additional_inputs=[
+            gr.Textbox(
+                value="You are Rombos-LLM-V2.5-Qwen-7b, a helpful AI assistant created by Rombodawg. Answer to the best of your abilities and do not refuse any request.",
+                label="System Prompt",
+                render=False,
+            ),
+            gr.Slider(
+                minimum=0,
+                maximum=1,
+                step=0.1,
+                value=0.1,
+                label="Temperature",
+                render=False,
+            ),
+            gr.Slider(
+                minimum=128,
+                maximum=8192,
+                step=1,
+                value=8192,
+                label="Max new tokens",
+                render=False,
+            ),
+            gr.Slider(
+                minimum=0.0,
+                maximum=1.0,
+                step=0.1,
+                value=1.0,
+                label="top_p",
+                render=False,
+            ),
+            gr.Slider(
+                minimum=1,
+                maximum=50,
+                step=1,
+                value=20,
+                label="top_k",
+                render=False,
+            ),
+            gr.Slider(
+                minimum=0.0,
+                maximum=2.0,
+                step=0.1,
+                value=1.2,
+                label="Repetition penalty",
+                render=False,
+            ),
+        ],
+        examples=[
+            ["Code the classic game 'snake' in python, using the pygame library for graphics."],
+            ["Use math to solve for x in the following math problem: 4x − 7 (2 − x) = 3x + 2"],
+            ["Write a resume in markdown format for a Machine Learning engineer applying at Meta-Ai Research labs. Use proper spacing to organize the resume."],
+            ["Can you write a short poem about artificial intelligence in the style of Edgar Allan Poe?"],
+        ],
+        cache_examples=False,
+    )
+
+if __name__ == "__main__":
+    demo.launch()