update EVALUATION.md

Author: hzhwcmhf

eval/EVALUATION.md

@@ -8,7 +8,13 @@ mkdir data/ceval
 mv ceval-exam.zip data/ceval
 cd data/ceval; unzip ceval-exam.zip
 cd ../../
+
+# Qwen-7B
 python evaluate_ceval.py -d data/ceval/
+
+# Qwen-7B-Chat
+pip install thefuzz
+python evaluate_chat_ceval.py -d data/ceval/
 ```
 
 - MMLU
@@ -19,27 +25,42 @@ mkdir data/mmlu
 mv data.tar data/mmlu
 cd data/mmlu; tar xf data.tar
 cd ../../
+
+# Qwen-7B
 python evaluate_mmlu.py -d data/mmlu/data/
+
+# Qwen-7B-Chat
+pip install thefuzz
+python evaluate_chat_mmlu.py -d data/mmlu/data/
 ```
 
 - HumanEval
 
 Get the HumanEval.jsonl file from [here](https://github.com/openai/human-eval/tree/master/data)
 
 ```Shell
-python evaluate_humaneval.py -f HumanEval.jsonl -o HumanEval_res.jsonl
 git clone https://github.com/openai/human-eval
 pip install -e human-eval
+
+# Qwen-7B
+python evaluate_humaneval.py -f HumanEval.jsonl -o HumanEval_res.jsonl
 evaluate_functional_correctness HumanEval_res.jsonl
+# Qwen-7B-Chat
+python evaluate_chat_mmlu.py -f HumanEval.jsonl -o HumanEval_res_chat.jsonl
+evaluate_functional_correctness HumanEval_res_chat.jsonl
 ```
                                          
 When installing package human-eval, please note its following disclaimer:
 
 This program exists to run untrusted model-generated code. Users are strongly encouraged not to do so outside of a robust security sandbox. The execution call in execution.py is deliberately commented out to ensure users read this disclaimer before running code in a potentially unsafe manner. See the comment in execution.py for more information and instructions.
-                                                       
 
 - GSM8K
 
 ```Shell
+# Qwen-7B
 python evaluate_gsm8k.py
-```
+
+# Qwen-7B-Chat
+python evaluate_chat_gsm8k.py # zeroshot
+python evaluate_chat_gsm8k.py --use-fewshot # fewshot
+```