Create app.py

app.py

@@ -0,0 +1,51 @@
+import spaces
+import torch
+
+import transformers
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model_name = "meta-llama/Meta-Llama-3-8B-Instruct"
+
+pipeline = transformers.pipeline(
+    "text-generation",
+    model=model_name,
+    model_kwargs={"torch_dtype": torch.bfloat16},
+    device="cpu",
+)
+
+@spaces.GPU
+def chat_function(message, history, system_prompt,max_new_tokens,temperature):
+    messages = [
+        {"role": "system", "content": system_prompt},
+        {"role": "user", "content": message},
+    ]
+    prompt = pipeline.tokenizer.apply_chat_template(
+        messages,
+        tokenize=False,
+        add_generation_prompt=True
+    )
+    terminators = [
+        pipeline.tokenizer.eos_token_id,
+        pipeline.tokenizer.convert_tokens_to_ids("<|eot_id|>")
+    ]
+    temp = temperature + 0.1
+    outputs = pipeline(
+        prompt,
+        max_new_tokens=max_new_tokens,
+        eos_token_id=terminators,
+        do_sample=True,
+        temperature=temp,
+        top_p=0.9,
+    )
+    return outputs[0]["generated_text"][len(prompt):]
+
+
+history = [("Hi!", "I'm doing well, thanks for asking!")]
+temperature = 0.7
+max_new_tokens = 50
+prompt = "Act as an english tutor. Always correct grammar and spelling mistakes. Always keep the conversation going by asking follow up questions"
+
+response = chat_function(message=message, history= history, system_prompt= prompt, max_new_tokens= max_new_tokens, temperature= temperature)
+
+print(response)