update readme

README.md

@@ -23,7 +23,7 @@ We use the LLaMA.13B model for measurement, but this optimized inference is appl
 
 * Evaluated at tokens/s
 * test on A100 40G
-* fp16 and int8 precision
+* fp16 and MEMOPT precision
 
 ### LLaMA-Ziya-13B
 
@@ -31,7 +31,7 @@ We use the LLaMA.13B model for measurement, but this optimized inference is appl
 | --- | --- | --- | --- | --- | --- |
 | Torch LLaMA | 31.74 | 289.2 | 521.37 | 775.69 | OOM |
 | lyraLLaMA fp16 | 73.2 | 565.6 | 1179.59 | 1795.63 | 3061.27 |
-| lyraLLaMA int8 | 104 | 770.5 | 1389.9 | 2390.4 | 3782.1 |
+| lyraLLaMA MEMOPT | 104 | 770.5 | 1389.9 | 2390.4 | 3782.1 |
 
 ### LLaMA-Vicuna-13B
 
@@ -39,7 +39,7 @@ We use the LLaMA.13B model for measurement, but this optimized inference is appl
 | --- | --- | --- | --- | --- | --- |
 | Torch LLaMA | 24.65| 167.3 | 322.97 | 407.99 | OOM |
 | lyraLLaMA fp16 | 53.67 | 421.38 | 804.31 | 1519.28| 2679.82 |
-| lyraLLaMA int8 | 79.81 | 603.15 | 1117.27 | 1966.52 | 3200.32 |
+| lyraLLaMA MEMOPT | 79.81 | 603.15 | 1117.27 | 1966.52 | 3200.32 |
 
 ## Docker Environment Recommendation
 
@@ -64,9 +64,9 @@ tokenizer_path = "./models/"
 dtype='fp16'
 prompt = "今天天气大概 25度，有点小雨，吹着风，我想去户外散步，应该穿什么样的衣服 裤子鞋子搭配"
 max_output_length = 512
-int8_mode = 0 # To use int8 mode, set int8_mode=1
+memopt_mode = 0 # To use MEMOPT mode, set memopt_mode=1
 
-model = lyraLLaMA(model_path, tokenizer_path, dtype, int8_mode)
+model = lyraLLaMA(model_path, tokenizer_path, dtype, memopt_mode)
 
 prompt = '<human>:' + prompt.strip() + '\n<bot>:'