adding extra LLM info

content/docs/Debian/docker.md

@@ -75,6 +75,12 @@ And that's it, Dockge is waiting for us on: localhost:5001
 
 Podman is a **container management tool** that is similar to Docker but has some differences in its approach. It allows you to run and manage containers on your system, just like Docker, but it offers some advantages, such as being daemonless (no central server) and providing **compatibility with Docker commands and images**. 
 
+
+```sh
+flatpak install flathub io.podman_desktop.PodmanDesktop
+flatpak run io.podman_desktop.PodmanDesktop
+```
+
 ## Why Podman?
 
 Both Podman and Docker are open-source projects, and they are released under different open-source licenses. 

content/docs/Debian/useful_tools.md

@@ -32,8 +32,14 @@ sudo apt install neofetch
 #neofetch
 ```
 
+* For Open Source: https://github.com/akopytov/sysbench
 
 
+```sh
+curl -s https://packagecloud.io/install/repositories/akopytov/sysbench/script.deb.sh | sudo bash
+sudo apt -y install sysbench
+```
+
 ### Hardware Monitor
 
 #### CPU Freq

content/docs/Linux_&_Cloud.md/llms.md

@@ -39,7 +39,10 @@ You can **Get LLMs Running** in your personal computer or in big servers just fo
 
 {{< /tabs >}}
 
-Others: [LibreChat](https://www.youtube.com/watch?v=0BRnK5BGZHU), Autogen + AutogenStudio https://microsoft.github.io/autogen/blog/2023/12/01/AutoGenStudio/
+* **Others:** [LibreChat](https://www.youtube.com/watch?v=0BRnK5BGZHU), Autogen + AutogenStudio https://microsoft.github.io/autogen/blog/2023/12/01/AutoGenStudio/ or [Quivir](https://github.com/StanGirard/quivr) with great [docs](https://docs.quivr.app/home/intro) or [LocalGPT](https://github.com/PromtEngineer/localGPT).
+  * Bindings:
+    * https://github.com/abetlen/llama-cpp-python
+    *
 
 
 
@@ -103,6 +106,15 @@ You can also try Solar 10.7B to compare these MoE's:
 ollama run solar:10.7b #https://ollama.ai/library/solar/tags
 ```
 
+### Choosing the Right Model
+
+#### Quantization
+
+* GPTQ quantization, a state-of-the-art method featured in research papers, offers minimal performance loss compared to previous techniques. It's most efficient on NVIDIA GPUs when the model fits entirely in VRAM.
+* GGML, a machine learning library by Georgi Gerganov (who also developed llama.cpp for running local LLMs on Mac), performs best on Apple or Intel hardware.
+
+Thanks: https://aituts.com/local-llms/#Which_Quantization
+
 #### Which LLMs are Trending now?
 
 You can always check the LLM's Leaderboards:
@@ -111,6 +123,32 @@ You can always check the LLM's Leaderboards:
 * With **ELO** Rating: <https://huggingface.co/spaces/lmsys/chatbot-arena-leaderboard>
     * <https://chat.lmsys.org/?arena>
 
+* Examples:
+  * <https://huggingface.co/TheBloke/Llama-2-13B-Chat-fp16/tree/main>
+
+#### What about Image Generation?
+
+You can find them in [Hugging Face](https://huggingface.co/spaces):
+
+* Stable Difussion:
+  * <https://huggingface.co/runwayml/stable-diffusion-v1-5/tree/main>
+  * <https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0/tree/main>
+  * <https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0/tree/main>
+  * <https://huggingface.co/stabilityai/stable-diffusion-2-base>
+  * <https://github.com/AUTOMATIC1111/stable-diffusion-webui> or <https://github.com/vladmandic/automatic>
+    * <https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Features#stable-diffusion-20>
+
+What are other people building? https://civitai.com/
+
+#### Voice?
+
+* <https://www.futuretools.io/tools/uberduck>
+* Audiocraft - https://gist.github.com/mberman84/afd800f8d4a8764a22571c1a82187bad
+
+#### Other Interesting AI Tools
+
+* <https://www.futuretools.io/?pricing-model=open-source>
+
 ### What is a RAG?
 
 RAG, which stands for "Retrieval-Augmented Generation" is a methodology used in the development of advanced natural language processing (NLP) systems, particularly in the context of large language models (LLMs)
@@ -124,4 +162,9 @@ You dont have to be a developer to get to use LLMs.
 
 Mostly we will be using frameworks that provide a level of abstraction to the real code behind the scenes.
 
-It would be definitely beneficial if you are [familiar with Python](https://fossengineer.com/guide-python/) if you want to try [Cutting-Edge and Free AI](https://fossengineer.com/tags/gen-ai/) or at least to know [how to manage Python Dependencies](https://fossengineer.com/guide-python/).
+It would be definitely beneficial if you are [familiar with Python](https://fossengineer.com/guide-python/) if you want to try [Cutting-Edge and Free AI](https://fossengineer.com/tags/gen-ai/) or at least to know [how to manage Python Dependencies](https://fossengineer.com/guide-python/).
+
+
+### Prompting
+
+* <https://prompthero.com/prompt/ccc554cf355-stable-diffusion-1-5-renaissance-painting-of-darth-vader-in-pink-fur-as-a-fashion-model-vogue-oil-paint-on-dark-background-masked-darth>

content/docs/Linux_&_Cloud.md/ml-ops.md

@@ -9,4 +9,8 @@ draft: true
 
 ## Visualizing NNs
 
-https://github.com/lutzroeder/netron
+https://github.com/lutzroeder/netron
+
+## AI Operations
+
+https://pezzo.ai/