Create app.py

app.py

@@ -0,0 +1,98 @@
+"""
+  This is a Hugging Face Spaces demo for Fin-RWKV-1B5 attention free finanacial export modal.
+  Author: Umut (Hope) YILDIRIM <[email protected]>
+"""
+
+import gradio as gr
+from transformers import AutoTokenizer, AutoModelForCausalLM, StoppingCriteria, StoppingCriteriaList, TextIteratorStreamer
+from threading import Thread
+import torch
+
+tokenizer = AutoTokenizer.from_pretrained("umuthopeyildirim/fin-rwkv-1b5")
+model = AutoModelForCausalLM.from_pretrained("umuthopeyildirim/fin-rwkv-1b5")
+
+
+class StopOnTokens(StoppingCriteria):
+    def __call__(self, input_ids: torch.LongTensor, scores: torch.FloatTensor, **kwargs) -> bool:
+        stop_ids = [29, 0]
+        for stop_id in stop_ids:
+            if input_ids[0][-1] == stop_id:
+                return True
+        return False
+
+
+def predict(message, history):
+
+    history_transformer_format = history + [[message, ""]]
+    stop = StopOnTokens()
+
+    messages = "".join(["".join(["\nuser :"+item[0], "\nbot:"+item[1]])  # curr_system_message +
+                        for item in history_transformer_format])
+
+    print(messages)
+
+    model_inputs = tokenizer([messages], return_tensors="pt")
+    streamer = TextIteratorStreamer(
+        tokenizer, timeout=10., skip_prompt=True, skip_special_tokens=True)
+    generate_kwargs = dict(
+        model_inputs,
+        streamer=streamer,
+        max_new_tokens=1024,
+        do_sample=True,
+        top_p=0.95,
+        top_k=1000,
+        temperature=0.5,
+        num_beams=1,
+        stopping_criteria=StoppingCriteriaList([stop])
+    )
+    t = Thread(target=model.generate, kwargs=generate_kwargs)
+    t.start()
+
+    partial_message = ""
+    for new_token in streamer:
+        if new_token != '<':
+            partial_message += new_token
+            yield partial_message
+
+
+def generate_text(prompt, tokenizer, model):
+    # Tokenize the input
+    input_ids = tokenizer.encode(prompt, return_tensors="pt")
+
+    # Generate a response
+    output = model.generate(input_ids, max_length=333, num_return_sequences=1)
+
+    # Decode the output
+    generated_text = tokenizer.decode(output[0], skip_special_tokens=True)
+
+    return generated_text
+
+
+title = "# Fin-RWKV: Attention Free Financal Expert (WIP)"
+description = """Demo for **Fin-RWKV: Attention Free Financal Expert (WIP)**.
+To download the model, please visit [Fin-RWKV: Attention Free Financal Expert (WIP)](https://huggingface.co/umutyildirim/fin-rwkv-1b5)."""
+
+css = """
+#img-display-container {
+    max-height: 100vh;
+    }
+#img-display-input {
+    max-height: 80vh;
+    }
+#img-display-output {
+    max-height: 80vh;
+    }
+"""
+
+with gr.Blocks(css=css) as demo:
+    gr.Markdown(title)
+    gr.Markdown(description)
+    with gr.Tab("Chatbot"):
+        gr.ChatInterface(predict)
+    with gr.Tab("E-Commerce"):
+        gr.Markdown("e-commerce")
+    with gr.Tab("OpenBB"):
+        gr.Markdown("openbb")
+
+if __name__ == '__main__':
+    demo.queue().launch()