Add stopping criteria to readme example (#2)

- Add stopping criteria to readme example (0b0b9ddd9b93fbc1250c64480607cbc819ae5e38)


Co-authored-by: dmayhem93 <[email protected]>

README.md

@@ -31,6 +31,14 @@ tokenizer = AutoTokenizer.from_pretrained("StabilityAI/stablelm-tuned-alpha-7b")
 model = AutoModelForCausalLM.from_pretrained("StabilityAI/stablelm-tuned-alpha-7b")
 model.half().cuda()
 
+class StopOnTokens(StoppingCriteria):
+    def __call__(self, input_ids: torch.LongTensor, scores: torch.FloatTensor, **kwargs) -> bool:
+        stop_ids = [50278, 50279, 50277, 1, 0]
+        for stop_id in stop_ids:
+            if input_ids[0][-1] == stop_id:
+                return True
+        return False
+
 system_prompt = """<|SYSTEM|># StableLM Tuned (Alpha version)
 - StableLM is a helpful and harmless open-source AI language model developed by StabilityAI.
 - StableLM is excited to be able to help the user, but will refuse to do anything that could be considered harmful to the user.
@@ -38,7 +46,7 @@ system_prompt = """<|SYSTEM|># StableLM Tuned (Alpha version)
 - StableLM will refuse to participate in anything that could harm a human.
 """
 
-prompt = f"{system_prompt}<|USER|>What's your mood today?"
+prompt = f"{system_prompt}<|USER|>What's your mood today?<|ASSISTANT|>"
 
 inputs = tokenizer(prompt, return_tensors="pt").to("cuda")
 tokens = model.generate(
@@ -46,6 +54,7 @@ tokens = model.generate(
   max_new_tokens=64,
   temperature=0.7,
   do_sample=True,
+  stopping_criteria=StoppingCriteriaList([StopOnTokens()])
 )
 print(tokenizer.decode(tokens[0], skip_special_tokens=True))
 ```