update readme

README.md

@@ -2,6 +2,15 @@
 
 Finetune an LLM, within a few clicks!
 
+<p align="center">
+  <a href="https://discord.gg/kghtMX7v" target="_blank">
+    <img src="https://img.shields.io/badge/FinetuneLLMs-chat_with_us-blue" alt="Discord">
+  </a>
+  <a href="https://github.com/jazelly/FinetuneLLMs/blob/main/LICENSE" target="_blank">
+      <img src="https://img.shields.io/static/v1?label=license&message=MIT&color=white" alt="License">
+  </a>
+
+</p>
 ## 🔥Goal & Roadmap🔥
 
 The main objective of this project is to lower the barrier to training large language models, especially for startup companies that have hardware in hands. With this project, it should be easy for a company to start experimenting with LLM training within a basic setup on servers with GPU/CPU resources.

trainer/trainer_api/finetune/README.md

@@ -7,6 +7,3 @@ This holds all the python finetune scripts
 - [x] make finetune scripts configurable for method
 - [x] make finetune scripts configurable for model
 - [ ] make finetune scripts configurable for training arguments
-- [ ] make finetune scripts configurable for quantization
-- [ ] make finetune scripts built with a buidler/factory
-- [ ] make finetune scripts can only be executed when there is enough memory