code help

.gitignore

@@ -0,0 +1,7 @@
+dschatbot/
+.DS_Store
+.env
+
+__pycache__/
+
+flagged

README.md

@@ -11,4 +11,28 @@ license: mit
 short_description: This is a simple chatbot to generte code using DeepSeeK
 ---
 
-An example chatbot using [Gradio](https://gradio.app), [`huggingface_hub`](https://huggingface.co/docs/huggingface_hub/v0.22.2/en/index), and the [Hugging Face Inference API](https://huggingface.co/docs/api-inference/index).
+An example chatbot using [Gradio](https://gradio.app), [`huggingface_hub`](https://huggingface.co/docs/huggingface_hub/v0.22.2/en/index), and the [Hugging Face Inference API](https://huggingface.co/docs/api-inference/index).
+
+
+This is a chatbot that interacts with the Fantasy Premier League (FPL) API to provide information about players, teams, and stats.
+
+```bash
+python3 -m venv dschatbot  
+source dschatbot/bin/activate
+```
+
+## Installation
+
+1. Install the dependencies:
+
+    ```bash
+    pip install -r requirements.txt
+    ```
+
+2. Run the chatbot:
+
+    ```bash
+    python app.py
+    ```
+
+## Usage

app.py

@@ -1,64 +1,60 @@
+import os
 import gradio as gr
-from huggingface_hub import InferenceClient
+from transformers import AutoTokenizer, AutoModelForCausalLM
+import torch
 
-"""
-For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
-"""
-client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
+tokenizer = AutoTokenizer.from_pretrained(
+    "deepseek-ai/deepseek-coder-1.3b-instruct", trust_remote_code=True)
+model = AutoModelForCausalLM.from_pretrained(
+    "deepseek-ai/deepseek-coder-1.3b-instruct", trust_remote_code=True, torch_dtype=torch.bfloat16)
 
+# Disable tokenizers parallelism warning
+os.environ["TOKENIZERS_PARALLELISM"] = "false"
 
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
 
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
+# Use CPU if CUDA is not available
+device = torch.device("cpu" if not torch.cuda.is_available() else "cuda")
+model = model.to(device)
 
-    messages.append({"role": "user", "content": message})
+# Theme builder
+# gr.themes.builder()
 
-    response = ""
+theme = gr.themes.Soft(
+    primary_hue="sky",
+    neutral_hue="slate",
+)
 
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
+# Function to handle user input and generate a response
 
-        response += token
-        yield response
 
+def chatbot_response(query):
+    response = "Lets see what I can do for you!"
+    # if response if a JSON boject iterate over the elements and conver is a list like "a": "b" "/n" "c": "d"
+    if isinstance(response, dict):
+        response = "\n".join(
+            [f"{key}: {value}" for key, value in response.items()])
 
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
-demo = gr.ChatInterface(
-    respond,
-    additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
-        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
-        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
-        gr.Slider(
-            minimum=0.1,
-            maximum=1.0,
-            value=0.95,
-            step=0.05,
-            label="Top-p (nucleus sampling)",
-        ),
-    ],
-)
+    # Generate response using the model
+    messages = [{'role': 'user', 'content': query}]
+    inputs = tokenizer.apply_chat_template(
+        messages, add_generation_prompt=True, return_tensors="pt").to(model.device)
+
+    outputs = model.generate(inputs, max_new_tokens=512, do_sample=True, top_k=50,
+                             top_p=0.95, num_return_sequences=1, eos_token_id=tokenizer.eos_token_id)
+    model_response = tokenizer.decode(
+        outputs[0][len(inputs[0]):], skip_special_tokens=True)
 
+    return response + "\n\n" + model_response
+
+
+# Set up the Gradio interface
+iface = gr.Interface(
+    fn=chatbot_response,
+    inputs=gr.Textbox(label="Ask our DSChatbot Expert"),
+    outputs=gr.Textbox(label="Hope it helps!"),
+    theme=theme,
+    title="DSChatbot"
+)
 
 if __name__ == "__main__":
-    demo.launch()
+    iface.launch()