Upload folder using huggingface_hub

.github/workflows/update_space.yml

@@ -0,0 +1,28 @@
+name: Run Python script
+
+on:
+  push:
+    branches:
+      - main
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+
+    steps:
+    - name: Checkout
+      uses: actions/checkout@v2
+
+    - name: Set up Python
+      uses: actions/setup-python@v2
+      with:
+        python-version: '3.9'
+
+    - name: Install Gradio
+      run: python -m pip install gradio
+
+    - name: Log in to Hugging Face
+      run: python -c 'import huggingface_hub; huggingface_hub.login(token="${{ secrets.hf_token }}")'
+
+    - name: Deploy to Spaces
+      run: gradio deploy

README.md

@@ -1,12 +1,6 @@
 ---
-title: Echo Chatbot
-emoji: ⚡
-colorFrom: gray
-colorTo: red
-sdk: gradio
-sdk_version: 5.5.0
+title: echo-chatbot
 app_file: app.py
-pinned: false
+sdk: gradio
+sdk_version: 5.0.2
 ---
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,6 @@
+import gradio as gr
+
+def slow_echo(message, history):
+    return message
+
+demo = gr.ChatInterface(slow_echo).queue().launch()

chatbot_hf.py

@@ -0,0 +1,65 @@
+from huggingface_hub import InferenceClient
+import gradio as gr
+
+client = InferenceClient(token="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")
+
+def respond(
+    prompt: str,
+    history,
+):
+    if not history:
+        history = [{"role": "system", "content": "You are a friendly chatbot"}]
+    history.append({"role": "user", "content": prompt})
+
+    yield history
+
+    response = {"role": "assistant", "content": ""}
+    for message in client.chat_completion(
+        history,
+        temperature=0.95,
+        top_p=0.9,
+        max_tokens=512,
+        stream=True,
+        model="HuggingFaceH4/zephyr-7b-beta"
+    ):
+        response["content"] += message.choices[0].delta.content or ""
+
+        yield history + [response]
+
+def handle_undo(history, undo_data: gr.UndoData): 
+    return history[:undo_data.index], history[undo_data.index]['content']
+
+def handle_retry(history, retry_data: gr.RetryData):
+    new_history = history[:retry_data.index]
+    previous_prompt = history[retry_data.index]['content']
+    yield from respond(previous_prompt, new_history)
+
+def handle_like(data: gr.LikeData):
+    if data.liked:
+        print("You upvoted this response: ", data.value)
+    else:
+        print("You downvoted this response: ", data.value)
+
+
+with gr.Blocks() as demo:
+    gr.Markdown("# Chat with Hugging Face Zephyr 7b 🤗")
+    chatbot = gr.Chatbot(
+        label="Agent",
+        type="messages",
+        avatar_images=(
+            None,
+            "https://em-content.zobj.net/source/twitter/376/hugging-face_1f917.png",
+        ),
+    )
+    
+    prompt = gr.Textbox(max_lines=1, label="Chat Message")
+    prompt.submit(respond, [prompt, chatbot], [chatbot])
+    prompt.submit(lambda: "", None, [prompt])
+    chatbot.undo(handle_undo, chatbot, [chatbot, prompt])
+    chatbot.retry(handle_retry, chatbot, [chatbot])
+    chatbot.like(handle_like, None, None)
+
+
+
+if __name__ == "__main__":
+    demo.launch()

test.ipynb

@@ -0,0 +1,75 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "I am going to yield something!\n",
+      "<generator object numberGenerator at 0x7e9ba9d18d60>\n",
+      "I am going to yield something!\n",
+      "<generator object numberGenerator at 0x7e9ba9d18d60>\n",
+      "I am going to yield something!\n",
+      "<generator object numberGenerator at 0x7e9ba9d18d60>\n",
+      "I am going to yield something!\n",
+      "<generator object numberGenerator at 0x7e9ba9d18d60>\n",
+      "I am going to yield something!\n",
+      "<generator object numberGenerator at 0x7e9ba9d18d60>\n",
+      "I am going to yield something!\n",
+      "<generator object numberGenerator at 0x7e9ba9d18d60>\n"
+     ]
+    }
+   ],
+   "source": [
+    "def numberGenerator(number_range: int):\n",
+    "\tfor i in range(number_range+1):\n",
+    "\t\tyield i\n",
+    "\n",
+    "\n",
+    "def loudNumberGenerator(number_range: int):\n",
+    "\tnormal_number_generator = numberGenerator(number_range=number_range)\n",
+    "\twhile True:\n",
+    "\t\tprint('I am going to yield something!')\n",
+    "\t\tyield normal_number_generator\n",
+    "\n",
+    "\n",
+    "zero_to_five = loudNumberGenerator(5)\n",
+    "\n",
+    "for _ in range(6):\n",
+    "\tprint(next(zero_to_five))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.10.12"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

transformer_hf_0.py

@@ -0,0 +1,51 @@
+"""
+Need GPU!
+"""
+
+import gradio as gr
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer, StoppingCriteria, StoppingCriteriaList, TextIteratorStreamer
+from threading import Thread
+
+tokenizer = AutoTokenizer.from_pretrained("togethercomputer/RedPajama-INCITE-Chat-3B-v1")
+model = AutoModelForCausalLM.from_pretrained("togethercomputer/RedPajama-INCITE-Chat-3B-v1", torch_dtype=torch.float16)
+model = model.to('cuda:0')
+
+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 = list(zip(history[:-1], history[1:])) + [[message, ""]]
+    stop = StopOnTokens()
+
+    messages = "".join(["".join(["\n<human>:"+item[0], "\n<bot>:"+item[1]])
+                for item in history_transformer_format])
+
+    model_inputs = tokenizer([messages], return_tensors="pt").to("cuda")
+    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=1.0,
+        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
+
+gr.ChatInterface(predict).launch()