update

README.md

@@ -1,14 +1,17 @@
-# open-o1
-o1 like 
+# Open-o1
+
+It thinks like o1
 
 ## TODO
-[ ] add fallback llms 
-[ ] better error handling
+
+[ ] Add fallback llms 
+[ ] Better error handling
 [ ] Add Tools (web, math, code)
 [ ] Make cli
 
 
 ## What it does
+
 - It takes a prompt , thinks, thinks again, critics itself, then returns answer 
 
 ## Installation
@@ -18,9 +21,26 @@ git clone https://github.com/tikendraw/open-o1.git
 
 cd open-o1
 
-pip install -r requirements.txt
-
 streamlit run app.py
 ```
 
-HAVE FUN.
+HAVE FUN.
+
+## Helpful Papers
+
+ 1. To Cot or not to Cot? CHAIN-OF-THOUGHT HELPS MAINLY ON MATH AND SYMBOLIC REASONING
+
+2. The Impact of Reasoning Step Length on Large Language Models
+
+3. Towards Understanding Chain-of-Thought Prompting: An Empirical Study of What Matters [2212.10001](https://arxiv.org/abs/2212.10001)
+```bibtex
+@misc{wang2023understandingchainofthoughtpromptingempirical,
+      title={Towards Understanding Chain-of-Thought Prompting: An Empirical Study of What Matters}, 
+      author={Boshi Wang and Sewon Min and Xiang Deng and Jiaming Shen and You Wu and Luke Zettlemoyer and Huan Sun},
+      year={2023},
+      eprint={2212.10001},
+      archivePrefix={arXiv},
+      primaryClass={cs.CL},
+      url={https://arxiv.org/abs/2212.10001}, 
+}
+```

input_config.json

@@ -3,6 +3,6 @@
     "max_steps": 3,
     "temperature": 0.2,
     "timeout": 30.0,
-    "sleeptime": 2.0,
+    "sleeptime": 0.0,
     "force_max_steps": true
 }