bloom

load_model.py

@@ -1,6 +1,6 @@
 from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
 
-model = AutoModelForCausalLM.from_pretrained("microsoft/Phi-3-mini-4k-instruct", trust_remote_code=True)
-tokenizer = AutoTokenizer.from_pretrained("microsoft/Phi-3-mini-4k-instruct", trust_remote_code=True)
+model = AutoModelForCausalLM.from_pretrained("bigscience/bloom-1b7")
+tokenizer = AutoTokenizer.from_pretrained("bigscience/bloom-1b7")
 
-pipe = pipeline("text-generation", model=model, tokenizer=tokenizer, max_new_tokens=2048)
+pipe = pipeline("text-generation", model=model, tokenizer=tokenizer, max_new_tokens=2048, repetition_penalty=1.2)