Update README.md

README.md

@@ -43,11 +43,11 @@ model = transformers.LlamaForCausalLM.from_pretrained(model_name, torch_dtype=to
 def stream(user_prompt):
     runtimeFlag = "cuda:0"
     system_prompt = ''
-    B_INST, E_INST = "[INST]", "[/INST]"
+    B_INST, E_INST = "<s> [INST]", "[/INST]"
     prompt = f"{system_prompt}{B_INST}{user_prompt.strip()}\n{E_INST}"
     inputs = tokenizer([prompt], return_tensors="pt").to(runtimeFlag)
     streamer = TextStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True)
-    _ = model.generate(**inputs, streamer=streamer, max_new_tokens=100, num_return_sequences=1)
+    _ = model.generate(**inputs, streamer=streamer, max_new_tokens=200, temperature=0.0001, eos_token_id=2, num_return_sequences=1)
 
 domanda = """Quale è la media tra questi valori?"""
 contesto = """