Update README.md

README.md

@@ -115,14 +115,15 @@ You will first need to install `transformers` and `accelerate` (just to ease the
 ```python
 import torch
 from transformers import AutoModelForCausalLM, AutoTokenizer
-model = AutoModelForCausalLM.from_pretrained("DRXD1000/Phoenix", torch_dtype=torch.bfloat16, device_map="auto")
-tokenizer = AutoTokenizer.from_pretrained("DRXD1000/Phoenix")
-prompt = """<|system|>
-</s>
-<|user|>
-Erkläre mir was KI ist.</s>
-<|assistant|>
-"""
+model = AutoModelForCausalLM.from_pretrained("DRXD1000/Phoenix-GPTQ", torch_dtype=torch.bfloat16, device_map="auto")
+tokenizer = AutoTokenizer.from_pretrained("DRXD1000/Phoenix-GPTQ")
+prompt = [
+    {
+        "role": "system",
+        "content": "", #Not recommended. Phoenix does not react well on system prompts
+    },
+    {"role": "user", "content": "Erkläre mir was KI ist"},
+]
 inputs = tokenizer.apply_chat_template(prompt,  return_tensors="pt").to("cuda")
 outputs = model.generate(inputs, num_return_sequences=1, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
 response = tokenizer.decode(outputs[0], skip_special_tokens=True)