Update README.md

README.md

@@ -20,14 +20,14 @@ base_model: Qwen/Qwen-VL-Chat-Int4
 - **Developed by:** Agora Research
 - **Model type:** Vision Language Model
 - **Language(s) (NLP):** English/Chinese
-- **Finetuned from model [optional]:** Qwen-VL
+- **Finetuned from model:** Qwen-VL
 
 ### Model Sources [optional]
 
 <!-- Provide the basic links for the model. -->
 
 - **Repository:** https://github.com/QwenLM/Qwen-VL
-- **Paper [optional]:** https://arxiv.org/pdf/2308.12966.pdf
+- **Paper:** https://arxiv.org/pdf/2308.12966.pdf
 
 ## Uses
 ```
@@ -47,7 +47,7 @@ model = AutoPeftModelForCausalLM.from_pretrained(
     trust_remote_code=True
 ).eval()
 ```
-# Specify hyperparameters for generation (if transformers < 4.32.0)
+# Specify hyperparameters for generation (generation_config if transformers < 4.32.0)
 ```
 #model.generation_config = GenerationConfig.from_pretrained("Qwen/Qwen-VL-Chat", trust_remote_code=True)
 
@@ -117,7 +117,7 @@ Just send an image and put [FUNCTION CALL] in the text. Can also be used for nor
 
 <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
 
-Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+(recommended) transformers >= 4.32.0
 
 ## How to Get Started with the Model
 ```
@@ -136,13 +136,6 @@ https://huggingface.co/datasets/AgoraX/OpenImage-FNCall-50k
 
 qlora for 1 epoch, 1000 steps
 
-### Results
-
-[More Information Needed]
-
-#### Summary
-
-
 ### Framework versions
 
 - PEFT 0.7.1