Update 2024-08-15-LLM.md

_posts/2024-08-15-LLM.md

@@ -361,6 +361,15 @@ Grok-2 & Grok-2 mini, achieve performance levels competitive to other frontier m
 ![](https://cdn.prod.website-files.com/6557a2b6957fcb7aeb0efcf0/66f6f79029bbf7e233406c45_Desktop.avif)
 **[Try Liquid](https://playground.liquid.ai/chat?model=cm1ooqdqo000208jx67z86ftk)** <br>
 
+---
+### Aria
+**model:** [rhymes-ai/Aria](https://huggingface.co/rhymes-ai/Aria)<br>
+
+---
+### Llama 3.3
+**model:** [meta-llama/Llama-3.3-70B-Instruct](https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct)<br>
+**Blog:** [Meta公布輕巧版多語言模型Llama 3.3](https://www.ithome.com.tw/news/166407)<br>
+
 ---
 ## safe AI
 
@@ -404,8 +413,12 @@ It is now the RLHAF (Reinforcement Learning from AI feedback)
 ![](https://github.com/rkuo2000/AI-course/raw/main/images/LM_Studio_0.3.3_Llama-3.2-3B-Instruct.png)
 
 ---
-### PrivateGPT
-**Code:** [https://github.com/zylon-ai/private-gpt](https://github.com/zylon-ai/private-gpt)<br>
+### [Jan](https://jan.ai/)
+**Github:** [https://github.com/janhq/jan](https://github.com/janhq/jan)<br>
+
+---
+### [PrivateGPT](https://github.com/zylon-ai/private-gpt)
+**Code:** [https://github.com/zylon-ai/private-gpt/tree/primordial](https://github.com/zylon-ai/private-gpt/tree/primordial)<br>
 ![](https://github.com/zylon-ai/private-gpt/raw/main/fern/docs/assets/ui.png?raw=true)
 
 ---
@@ -422,6 +435,8 @@ cd ~/gpt4all
 ### [GPT4FREE](https://github.com/xtekky/gpt4free)
 `pip install g4f`<br>
 
+---
+### [llama.cpp](https://github.com/ggerganov/llama.cpp)
 
 ---
 ## Reasoning