Duplicate from jdoexbox360/chagpt-2-convo-finally

.gitattributes

@@ -0,0 +1,34 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,13 @@
+---
+title: Stablelm Tuned Alpha Chat
+emoji: 👀
+colorFrom: purple
+colorTo: pink
+sdk: gradio
+sdk_version: 3.27.0
+app_file: app.py
+pinned: false
+duplicated_from: jdoexbox360/chagpt-2-convo-finally
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,100 @@
+import gradio as gr
+import torch
+import tensorflow as tf
+from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline, StoppingCriteria, StoppingCriteriaList, TextIteratorStreamer, GPT2LMHeadModel, GPT2Tokenizer
+import time
+import numpy as np
+from torch.nn import functional as F
+import os
+from threading import Thread
+
+print(f"Starting to load the model to memory")
+
+tok = GPT2Tokenizer.from_pretrained("ethzanalytics/ai-msgbot-gpt2-XL-dialogue")
+m = GPT2LMHeadModel.from_pretrained("ethzanalytics/ai-msgbot-gpt2-XL-dialogue", pad_token_id=tok.eos_token_id)
+generator = pipeline('text-generation', model=m, tokenizer=tok)
+print(f"Sucessfully loaded the model to the memory")
+
+start_message = """You are an AI called assistant."""
+
+
+class StopOnTokens(StoppingCriteria):
+    def __call__(self, input_ids: torch.LongTensor, scores: torch.FloatTensor, **kwargs) -> bool:
+        stop_ids = [50278, 50279, 50277, 1, 0]
+        for stop_id in stop_ids:
+            if input_ids[0][-1] == stop_id:
+                return True
+        return False
+
+
+def user(message, history):
+    # Append the user's message to the conversation history
+    return "", history + [[message, ""]]
+
+
+def chat(curr_system_message, history):
+    # Initialize a StopOnTokens object
+    stop = StopOnTokens()
+
+    # Construct the input message string for the model by concatenating the current system message and conversation history
+    messages = curr_system_message + \
+        "".join(["".join(["\nperson alpha:"+item[0], "\nperson beta:"+item[1]])
+                for item in history])
+
+    # Tokenize the messages string
+    model_inputs = tok([messages], return_tensors="pt")
+    streamer = TextIteratorStreamer(
+        tok, 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=1.0,
+        num_beams=1,
+        stopping_criteria=StoppingCriteriaList([stop])
+    )
+    t = Thread(target=m.generate, kwargs=generate_kwargs)
+    t.start()
+
+    # print(history)
+    # Initialize an empty string to store the generated text
+    partial_text = ""
+    for new_text in streamer:
+        # print(new_text)
+        partial_text += new_text
+        history[-1][1] = partial_text
+        # Yield an empty string to cleanup the message textbox and the updated conversation history
+        yield history
+    return partial_text
+
+
+with gr.Blocks() as demo:
+    # history = gr.State([])
+    gr.Markdown("## StableLM-Tuned-Alpha-7b Chat")
+    gr.HTML('''<center><a href="https://huggingface.co/spaces/stabilityai/stablelm-tuned-alpha-chat?duplicate=true"><img src="https://bit.ly/3gLdBN6" alt="Duplicate Space"></a>Duplicate the Space to skip the queue and run in a private space</center>''')
+    chatbot = gr.Chatbot().style(height=500)
+    with gr.Row():
+        with gr.Column():
+            msg = gr.Textbox(label="Chat Message Box", placeholder="Chat Message Box",
+                             show_label=False).style(container=False)
+        with gr.Column():
+            with gr.Row():
+                submit = gr.Button("Submit")
+                stop = gr.Button("Stop")
+                clear = gr.Button("Clear")
+    system_msg = gr.Textbox(
+        start_message, label="System Message", interactive=False, visible=False)
+
+    submit_event = msg.submit(fn=user, inputs=[msg, chatbot], outputs=[msg, chatbot], queue=False).then(
+        fn=chat, inputs=[system_msg, chatbot], outputs=[chatbot], queue=True)
+    submit_click_event = submit.click(fn=user, inputs=[msg, chatbot], outputs=[msg, chatbot], queue=False).then(
+        fn=chat, inputs=[system_msg, chatbot], outputs=[chatbot], queue=True)
+    stop.click(fn=None, inputs=None, outputs=None, cancels=[
+               submit_event, submit_click_event], queue=False)
+    clear.click(lambda: None, None, [chatbot], queue=False)
+
+demo.queue(max_size=32, concurrency_count=2)
+demo.launch()

requirements.txt

@@ -0,0 +1,8 @@
+gradio
+tensorflow
+torch
+torchvision
+torchaudio
+transformers
+numpy
+