Create bot.py

bot.py

@@ -0,0 +1,46 @@
+import discord
+import os
+from discord.ext import commands
+from huggingface_hub import InferenceClient
+
+client = commands.Bot(command_prefix='!')
+inference_client = InferenceClient("HuggingFaceH4/zephyr-7b-alpha")
+
+@client.event
+async def on_ready():
+    print(f'Logged in as {client.user.name}')
+
+@client.command(name="ask")
+async def ask(ctx, *, question):
+    history = []  # Add the conversation history if needed
+    response = next(generate(question, history))
+    await ctx.send(response)
+
+def generate(prompt, history, temperature=0.9, max_new_tokens=500, top_p=0.95, repetition_penalty=1.0):
+    temperature = float(temperature)
+    if temperature < 1e-2:
+        temperature = 1e-2
+    top_p = float(top_p)
+
+    generate_kwargs = dict(
+        temperature=temperature,
+        max_new_tokens=max_new_tokens,
+        top_p=top_p,
+        repetition_penalty=repetition_penalty,
+        do_sample=True,
+        seed=42,
+    )
+
+    formatted_prompt = format_prompt(prompt, history)
+
+    # Use the InferenceClient for text generation
+    stream = inference_client.text_generation(
+        formatted_prompt, **generate_kwargs, stream=True, details=True, return_full_text=False
+    )
+    
+    output = ""
+    for response in stream:
+        output += response.token.text
+    return output
+
+client.run(os.getenv("token"))