Update app.py

app.py

@@ -4,6 +4,53 @@ import os
 import logging
 from datetime import datetime
 from transformers import pipeline
+import spaces
+
+device = "cuda" if torch.cuda.is_available() else "cpu"
+
+# Load the model and tokenizer
+model_name = "mixtral/instruct-v0.1"
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(model_name).to(device)
+
+def stream_chat(
+    message: str,
+    history: list,
+    system_prompt: str,
+    temperature: float = 0.8,
+    max_new_tokens: int = 1024,
+    top_p: float = 1.0,
+    top_k: int = 20,
+    penalty: float = 1.2,
+):
+    conversation = [
+        {"role": "system", "content": system_prompt}
+    ]
+    for prompt, answer in history:
+        conversation.extend([
+            {"role": "user", "content": prompt},
+            {"role": "assistant", "content": answer},
+        ])
+
+    conversation.append({"role": "user", "content": message})
+
+    input_ids = tokenizer.apply_chat_template(conversation, add_generation_prompt=True, return_tensors="pt").to(device)
+
+    streamer = TextStreamer(tokenizer, timeout=60.0, skip_prompt=True, skip_special_tokens=True)
+
+    generate_kwargs = dict(
+        input_ids=input_ids,
+        max_new_tokens=max_new_tokens,
+        do_sample=temperature != 0,
+        top_p=top_p,
+        top_k=top_k,
+        temperature=temperature,
+        eos_token_id=[128001, 128008, 128009],
+        streamer=streamer,
+    )
+
+    output = model.generate(**generate_kwargs)
+    return tokenizer.decode(output[0], skip_special_tokens=True)
 
 # Initialize the pipeline
 pipe = pipeline("text-generation", model="mistralai/Mixtral-8x7B-Instruct-v0.1")