Update app.py

app.py

@@ -9,7 +9,7 @@ model_id = "doubledsbv/Llama-3-Kafka-8B-v0.1"
 
 model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16)
 tokenizer = transformers.AutoTokenizer.from_pretrained(model_id)
-streamer = TextStreamer(tokenizer)
+#streamer = TextStreamer(tokenizer)
 
 pipeline = transformers.pipeline(
     model=model, tokenizer=tokenizer,
@@ -47,8 +47,9 @@ def chat_function(message, history, system_prompt,max_new_tokens,temperature):
         eos_token_id=terminators,
         do_sample=True,
         temperature=temperature,
-        top_p=0.9,
-        streamer=streamer
+        #top_p=0.9,
+        min_p=0.075,
+        #streamer=streamer
     )
     return outputs[0]["generated_text"][len(prompt):]