AI : New Apps! (akash-network#373)

* Add AI section

Add ai-chat-app to run self-hosted chatgpt.

* Add stable diffusion and ai-chat-app update

* Update README and deploy.yaml on ai-chat-app and sd

* Add ChatGPT screenshots

* Update README.md

* Update README.md

* Update README.md

* Update README.md

* Initial commit serge

* Add daila

* Add alpaca and gpt4all

* Fix image name

* Fix alpaca.cpp

* README updates

* Fix StableDiffusion

README.md

@@ -16,7 +16,11 @@ Also, follow [@akashnet\_](https://twitter.com/akashnet_) to stay in the loop wi
 
 ### AI
 
+- [Alpaca.cpp](alpaca-cpp)
 - [ChatGPT Self-Hosted Chat](ai-chat-app)
+- [Daila](daila)
+- [GPT4ALL](gpt4all)
+- [Serge](serge)
 - [Stable Diffusion](stable-diffusion-ui)
 
 ### Blogging

alpaca-cpp/Dockerfile

@@ -0,0 +1,26 @@
+# Use a Linux base image
+FROM ubuntu:latest
+
+# Set the working directory to /app
+WORKDIR /app
+
+# Install dependencies
+RUN apt-get update && \
+    apt-get install -y g++ git cmake wget aria2 && \
+    apt-get clean
+
+# Clone the alpaca.cpp repository
+RUN git clone https://github.com/antimatter15/alpaca.cpp && \
+    cd alpaca.cpp && \
+    make chat && \
+    cp chat ../ && \
+    cd .. && \
+    rm -rf alpaca.cpp
+
+# Download the weights
+RUN aria2c --out=ggml-alpaca-7b-q4.bin --summary-interval 15 --check-certificate=false --max-tries=99 --retry-wait=5 --always-resume=true --max-file-not-found=99 --conditional-get=true -s 16 -x 16 -k 1M -j 1 https://huggingface.co/Sosaka/Alpaca-native-4bit-ggml/resolve/main/ggml-alpaca-7b-q4.bin
+RUN aria2c --out=gotty.tar.gz https://github.com/yudai/gotty/releases/download/v2.0.0-alpha.3/gotty_2.0.0-alpha.3_linux_amd64.tar.gz
+RUN tar -zxvf gotty.tar.gz ; rm -rf gotty.tar.gz
+
+# Set the entrypoint command
+ENTRYPOINT ["./gotty", "-w", "./chat","-t","15"]

alpaca-cpp/README.md

@@ -0,0 +1,64 @@
+# Alpaca.cpp
+
+Run a fast ChatGPT-like model locally on your device. The screencast below is not sped up and running on an M2 Macbook Air with 4GB of weights.
+
+[![asciicast](screencast.gif)](https://asciinema.org/a/dfJ8QXZ4u978Ona59LPEldtKK)
+
+
+This combines the [LLaMA foundation model](https://github.com/facebookresearch/llama) with an [open reproduction](https://github.com/tloen/alpaca-lora) of [Stanford Alpaca](https://github.com/tatsu-lab/stanford_alpaca) a fine-tuning of the base model to obey instructions (akin to the [RLHF](https://huggingface.co/blog/rlhf) used to train ChatGPT) and a set of modifications to [llama.cpp](https://github.com/ggerganov/llama.cpp) to add a chat interface. 
+
+## Get Started (7B)
+
+Download the zip file corresponding to your operating system from the [latest release](https://github.com/antimatter15/alpaca.cpp/releases/latest). On Windows, download `alpaca-win.zip`, on Mac (both Intel or ARM) download `alpaca-mac.zip`, and on Linux (x64) download `alpaca-linux.zip`. 
+
+Download `ggml-alpaca-7b-q4.bin` and place it in the same folder as the `chat` executable in the zip file. There are several options: 
+
+Once you've downloaded the model weights and placed them into the same directory as the `chat` or `chat.exe` executable, run:
+
+```
+./chat
+```
+
+The weights are based on the published fine-tunes from `alpaca-lora`, converted back into a pytorch checkpoint with a [modified script](https://github.com/tloen/alpaca-lora/pull/19) and then quantized with llama.cpp the regular way. 
+
+## Building from Source (MacOS/Linux)
+
+
+```sh
+git clone https://github.com/antimatter15/alpaca.cpp
+cd alpaca.cpp
+
+make chat
+./chat
+```
+
+
+## Building from Source (Windows)
+
+- Download and install CMake: <https://cmake.org/download/>
+- Download and install `git`. If you've never used git before, consider a GUI client like <https://desktop.github.com/>
+- Clone this repo using your git client of choice (for GitHub Desktop, go to File -> Clone repository -> From URL and paste `https://github.com/antimatter15/alpaca.cpp` in as the URL)
+- Open a Windows Terminal inside the folder you cloned the repository to
+- Run the following commands one by one:
+
+```ps1
+cmake .
+cmake --build . --config Release
+```
+
+- Download the weights via any of the links in "Get started" above, and save the file as `ggml-alpaca-7b-q4.bin` in the main Alpaca directory.
+- In the terminal window, run this command:
+```ps1
+.\Release\chat.exe
+```
+- (You can add other launch options like `--n 8` as preferred onto the same line)
+- You can now type to the AI in the terminal and it will reply. Enjoy!
+
+## Credit
+
+This combines [Facebook's LLaMA](https://github.com/facebookresearch/llama), [Stanford Alpaca](https://crfm.stanford.edu/2023/03/13/alpaca.html), [alpaca-lora](https://github.com/tloen/alpaca-lora) and [corresponding weights](https://huggingface.co/tloen/alpaca-lora-7b/tree/main) by Eric Wang (which uses [Jason Phang's implementation of LLaMA](https://github.com/huggingface/transformers/pull/21955) on top of Hugging Face Transformers), and [llama.cpp](https://github.com/ggerganov/llama.cpp) by Georgi Gerganov. The chat implementation is based on Matvey Soloviev's [Interactive Mode](https://github.com/ggerganov/llama.cpp/pull/61) for llama.cpp. Inspired by [Simon Willison's](https://til.simonwillison.net/llms/llama-7b-m2) getting started guide for LLaMA. [Andy Matuschak](https://twitter.com/andy_matuschak/status/1636769182066053120)'s thread on adapting this to 13B, using fine tuning weights by [Sam Witteveen](https://huggingface.co/samwit/alpaca13B-lora). 
+
+
+## Disclaimer
+
+Note that the model weights are only to be used for research purposes, as they are derivative of LLaMA, and uses the published instruction data from the Stanford Alpaca project which is generated by OpenAI, which itself disallows the usage of its outputs to train competing models. 

alpaca-cpp/deploy.yaml

@@ -0,0 +1,45 @@
+---
+version: "2.0"
+
+services:
+  alpaca-cpp:
+    image: cryptoandcoffee/akash-alpaca-cpp:1
+    expose:
+      - port: 8080
+        as: 80
+        to:
+          - global: true
+    command:
+      - "./gotty"
+      - "-w"
+      - "./chat"
+      - "-t"
+      - "15"
+profiles:
+  compute:
+    alpaca-cpp:
+      resources:
+        cpu:
+          units: 16.0 
+        memory:
+          size: 16Gi #Need to increase for larger models
+        storage:
+          size: 8Gi #Need to increase for larger models
+  placement:
+    akash:
+      attributes:
+        host: akash
+      signedBy:
+        anyOf:
+          - "akash1365yvmc4s7awdyj3n2sav7xfx76adc6dnmlx63"
+          - "akash18qa2a2ltfyvkyj0ggj3hkvuj6twzyumuaru9s4"
+      pricing:
+        alpaca-cpp: 
+          denom: uakt
+          amount: 10000
+
+deployment:
+  alpaca-cpp:
+    akash:
+      profile: alpaca-cpp
+      count: 1

daila/Dockerfile

@@ -0,0 +1,36 @@
+FROM python:3.10-slim-buster
+
+# The dalai server runs on port 3000
+EXPOSE 3000
+
+# Install dependencies
+RUN apt-get update \
+    && apt-get install -y \
+        build-essential \
+        curl \
+        g++ \
+        git \
+        make \
+        python3-venv \
+        software-properties-common
+
+# Add NodeSource PPA to get Node.js 18.x
+RUN curl -fsSL https://deb.nodesource.com/setup_18.x | bash -
+
+# Install Node.js 18.x
+RUN apt-get update \
+    && apt-get install -y nodejs
+
+WORKDIR /root/dalai
+
+# Install dalai and its dependencies
+RUN npm install [email protected]
+
+ENV MODEL_SIZE=7B
+ENV LLAMA=false
+ENV ALPACA=true
+
+COPY startup.sh .
+
+# Run the dalai server
+CMD [ "bash", "startup.sh" ]