Update README.md

README.md

@@ -13,35 +13,43 @@ This model is an int4 model with group_size 128 and symmetric quantization of [f
 from auto_round import AutoRoundConfig  ##must import for auto_round format
 from transformers import AutoModelForCausalLM, AutoTokenizer
 
-quantized_model_dir = "/data5/quant/iter2000/falcon3-3B-w4g128-auto-round/"
+quantized_model_dir = "OPEA/falcon3-3B-int4-sym-inc"
 tokenizer = AutoTokenizer.from_pretrained(quantized_model_dir)
 model = AutoModelForCausalLM.from_pretrained(
     quantized_model_dir,
     device_map="auto"
     ## revision="07a117c" ##AutoGPTQ format
 )
-text = "下面我来介绍一下阿里巴巴公司，"
+text = "how many r in strawberry? The ansnwer is "
 inputs = tokenizer(text, return_tensors="pt", return_token_type_ids=False).to(model.device)
 print(tokenizer.decode(model.generate(**inputs, max_new_tokens=50)[0]))
 ##INT4:
-## 下面我来介绍一下阿里巴巴公司，阿里巴巴公司是阿里网的首席执行官，他在阿里网的创始人，阿里巴巴公司的首席执行官，他在阿里
+## how many r in strawberry? The ansnwer is 10000000000000000000000000000000000000000000000000
 
 ##BF16:
-## 下面我来介绍一下阿里巴巴公司，以及阿里巴巴的产品和服务。
-## 阿里巴巴公司是阿里网公司的首席执行官，是阿里网公司的首席执行官，是阿
-
-text = "9.8和9.11哪个数字大？答案是"
+## how many r in strawberry? The ansnwer is 1.
+## Q: How many r in strawberry?
+## A: 1
+## Q: How many r in strawberry?
+## A: 1
+## Q: How many r in strawberry?
+## A: 1
+## Q: How many r
+
+text = "Which number is bigger, 9.8 or 9.11? The answer is"
 ##INT4:
-## 9.8和9.11哪个数字大？答案是9.8。
-## Q: 哪个数字大：9.8和9.11？
+## Which number is bigger, 9.8 or 9.11? The answer is 9.8.
+## Q: Which number is bigger, 9.8 or 9.11?
 ## A: 9.8
-## Q: 9.8和9.11哪个数字
+## Q: Which number is bigger, 9.8 or 9.11?
 
 ##BF16:
-## 9.8和9.11哪个数字大？答案是9.8。
-## Q: 哪个数字大：9.8和9.11？
-## A: 9.8
-## Q: 9.8和9.11哪个数字
+## Which number is bigger, 9.8 or 9.11? The answer is 9.8.
+## Q: Which number is bigger, 9.8 or 9.11?
+## Options:
+## - 9.8
+## - 9.11
+## Let's think step by step.
 
 text = "Once upon a time,"
 ##INT4: