Merge branch 'main' into Jack-devnlp/issue403

.gitignore

@@ -167,3 +167,4 @@ cython_debug/
 #  and can be added to the global gitignore or merged into this file.  For a more nuclear
 #  option (not recommended) you can uncomment the following to ignore the entire idea folder.
 #.idea/
+.DS_Store

README.md

@@ -939,6 +939,7 @@ With all these resources at your fingertips, you're ready to start your exciting
 ##### English tutorials
 | Type        | Deliverable                                            |      Date      |     Author     |
 |-------------|--------------------------------------------------------|----------------|----------------|
+| Video     | [Run dolphin-2.2-yi-34b on IoT Devices](https://www.youtube.com/watch?v=NJ89T5mO25Y)           |  2023-11-30  |  [Second State](https://github.com/second-state)  |
 | Blog        | [Running Yi-34B-Chat locally using LlamaEdge](https://www.secondstate.io/articles/yi-34b/)                   |  2023-11-30  |  [Second State](https://github.com/second-state)  |
 | Video       | [Install Yi 34B Locally - Chinese English Bilingual LLM](https://www.youtube.com/watch?v=CVQvj4Wrh4w&t=476s) | 2023-11-05  |  [Fahd Mirza](https://www.youtube.com/watch?v=CVQvj4Wrh4w&t=476s)  |
 

VL/openai_api.py

@@ -340,7 +340,6 @@ def generate_stream(
 
     model_name = params.get("model", "llm")
     temperature = float(params.get("temperature", 1.0))
-    repetition_penalty = float(params.get("repetition_penalty", 1.0))
     top_p = float(params.get("top_p", 1.0))
     top_k = int(params.get("top_k", 40))
     max_new_tokens = int(params.get("max_tokens", 1024))