diff --git a/docs/docs/quickstart/install.mdx b/docs/docs/quickstart/install.mdx
index 53c0a7a1c..d96246a53 100644
--- a/docs/docs/quickstart/install.mdx
+++ b/docs/docs/quickstart/install.mdx
@@ -1,22 +1,30 @@
---
+title: Installation
sidebar_position: 2
hide_table_of_contents: true
+description: Jan is a ChatGPT-alternative that runs on your own computer, with a local API server.
+keywords:
+ [
+ Jan AI,
+ Jan,
+ ChatGPT alternative,
+ local AI,
+ private AI,
+ conversational AI,
+ no-subscription fee,
+ large language model,
+ ]
---
import Tabs from '@theme/Tabs';
import TabItem from '@theme/TabItem';
import installImageURL from './assets/jan-ai-download.png';
-# Installation
-
-:::warning
-
-Ensure that your MacOS version is 13 or higher to run Jan.
-
-:::
+ ### Pre-requisites
+ Ensure that your MacOS version is 13 or higher to run Jan.
### Stable Releases
@@ -43,16 +51,13 @@ If you are stuck in a broken build, go to the [Broken Build](/docs/common-error/
-:::warning
-
-Ensure that your system meets the following requirements:
- - Windows 10 or higher is required to run Jan.
-
-To enable GPU support, you will need:
- - NVIDIA GPU with CUDA Toolkit 11.7 or higher
- - NVIDIA driver 470.63.01 or higher
-
-:::
+ ### Pre-requisites
+ Ensure that your system meets the following requirements:
+ - Windows 10 or higher is required to run Jan.
+
+ To enable GPU support, you will need:
+ - NVIDIA GPU with CUDA Toolkit 11.7 or higher
+ - NVIDIA driver 470.63.01 or higher
### Stable Releases
@@ -88,15 +93,14 @@ If you are stuck in a broken build, go to the [Broken Build](/docs/common-error/
-:::warning
-Ensure that your system meets the following requirements:
- - glibc 2.27 or higher (check with `ldd --version`)
- - gcc 11, g++ 11, cpp 11, or higher, refer to this link for more information.
+ ### Pre-requisites
+ Ensure that your system meets the following requirements:
+ - glibc 2.27 or higher (check with `ldd --version`)
+ - gcc 11, g++ 11, cpp 11, or higher, refer to this link for more information.
-To enable GPU support, you will need:
- - NVIDIA GPU with CUDA Toolkit 11.7 or higher
- - NVIDIA driver 470.63.01 or higher
-:::
+ To enable GPU support, you will need:
+ - NVIDIA GPU with CUDA Toolkit 11.7 or higher
+ - NVIDIA driver 470.63.01 or higher
### Stable Releases
@@ -154,4 +158,117 @@ If you are stuck in a broken build, go to the [Broken Build](/docs/common-error/
:::
+
+
+ ### Pre-requisites
+ Ensure that your system meets the following requirements:
+ - Linux or WSL2 Docker
+ - Latest Docker Engine and Docker Compose
+
+ To enable GPU support, you will need:
+ - `nvidia-driver`
+ - `nvidia-docker2`
+
+:::note
+- If you have not installed Docker, follow the instructions [here](https://docs.docker.com/engine/install/ubuntu/).
+- If you have not installed the required file for GPU support, follow the instructions [here](https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/latest/install-guide.html).
+:::
+
+ ### Docker Compose Profile and Environment
+ Before dive in into the steps to run Jan in Docker, ensure that you have understand the following docker compose profile and the environment variable listed below:
+
+ #### Docker Compose Profile
+
+ | Profile | Description |
+ |-----------|-------------------------------------------|
+ | cpu-fs | Run Jan in CPU mode with default file system |
+ | cpu-s3fs | Run Jan in CPU mode with S3 file system |
+ | gpu-fs | Run Jan in GPU mode with default file system |
+ | gpu-s3fs | Run Jan in GPU mode with S3 file system |
+
+ #### Environment Variables
+
+ | Environment Variable | Description |
+ |--------------------------|------------------------------------------------------------|
+ | S3_BUCKET_NAME | S3 bucket name - leave blank for default file system |
+ | AWS_ACCESS_KEY_ID | AWS access key ID - leave blank for default file system |
+ | AWS_SECRET_ACCESS_KEY | AWS secret access key - leave blank for default file system|
+ | AWS_ENDPOINT | AWS endpoint URL - leave blank for default file system |
+ | AWS_REGION | AWS region - leave blank for default file system |
+ | API_BASE_URL | Jan Server URL, please modify it as your public ip address or domain name default http://localhost:1377 |
+
+ ### Run Jan in Docker
+ You can run Jan in Docker with two methods:
+ 1. Run Jan in CPU mode
+ 2. Run Jan in GPU mode
+
+
+
+ To run Jan in Docker CPU mode, by using the following code:
+
+ ```bash
+ # cpu mode with default file system
+ docker compose --profile cpu-fs up -d
+
+ # cpu mode with S3 file system
+ docker compose --profile cpu-s3fs up -d
+ ```
+
+
+
+
+ To run Jan in Docker CPU mode, follow the steps below:
+ 1. Check CUDA compatibility with your NVIDIA driver by running nvidia-smi and check the CUDA version in the output as shown below:
+ ```sh
+ nvidia-smi
+
+ # Output
+ +---------------------------------------------------------------------------------------+
+ | NVIDIA-SMI 531.18 Driver Version: 531.18 CUDA Version: 12.1 |
+ |-----------------------------------------+----------------------+----------------------+
+ | GPU Name TCC/WDDM | Bus-Id Disp.A | Volatile Uncorr. ECC |
+ | Fan Temp Perf Pwr:Usage/Cap| Memory-Usage | GPU-Util Compute M. |
+ | | | MIG M. |
+ |=========================================+======================+======================|
+ | 0 NVIDIA GeForce RTX 4070 Ti WDDM | 00000000:01:00.0 On | N/A |
+ | 0% 44C P8 16W / 285W| 1481MiB / 12282MiB | 2% Default |
+ | | | N/A |
+ +-----------------------------------------+----------------------+----------------------+
+ | 1 NVIDIA GeForce GTX 1660 Ti WDDM | 00000000:02:00.0 Off | N/A |
+ | 0% 49C P8 14W / 120W| 0MiB / 6144MiB | 0% Default |
+ | | | N/A |
+ +-----------------------------------------+----------------------+----------------------+
+ | 2 NVIDIA GeForce GTX 1660 Ti WDDM | 00000000:05:00.0 Off | N/A |
+ | 29% 38C P8 11W / 120W| 0MiB / 6144MiB | 0% Default |
+ | | | N/A |
+ +-----------------------------------------+----------------------+----------------------+
+
+ +---------------------------------------------------------------------------------------+
+ | Processes: |
+ | GPU GI CI PID Type Process name GPU Memory |
+ | ID ID Usage |
+ |=======================================================================================|
+ ```
+ 2. Visit [NVIDIA NGC Catalog](https://catalog.ngc.nvidia.com/orgs/nvidia/containers/cuda/tags) and find the smallest minor version of image tag that matches your CUDA version (e.g., 12.1 -> 12.1.0)
+ 3. Update the `Dockerfile.gpu` line number 5 with the latest minor version of the image tag from step 2 (e.g. change `FROM nvidia/cuda:12.2.0-runtime-ubuntu22.04 AS base` to `FROM nvidia/cuda:12.1.0-runtime-ubuntu22.04 AS base`)
+ 4. Run Jan in GPU mode by using the following command:
+
+ ```bash
+ # GPU mode with default file system
+ docker compose --profile gpu-fs up -d
+
+ # GPU mode with S3 file system
+ docker compose --profile gpu-s3fs up -d
+ ```
+
+
+
+
+:::warning
+
+If you are stuck in a broken build, go to the [Broken Build](/docs/common-error/broken-build) section of Common Errors.
+
+:::
+
+
\ No newline at end of file
diff --git a/docs/docs/quickstart/models-list.mdx b/docs/docs/quickstart/models-list.mdx
index a939b0248..cd7107a92 100644
--- a/docs/docs/quickstart/models-list.mdx
+++ b/docs/docs/quickstart/models-list.mdx
@@ -1,9 +1,8 @@
---
+title: Pre-configured Models
sidebar_position: 3
---
-# Pre-configured Models
-
## Overview
Jan provides various pre-configured AI models with different capabilities. Please see the following list for details.
@@ -14,18 +13,18 @@ Jan provides various pre-configured AI models with different capabilities. Pleas
| OpenHermes Neural 7B Q4 | A merged model using the TIES method. It performs well in various benchmarks |
| Stealth 7B Q4 | This is a new experimental family designed to enhance Mathematical and Logical abilities |
| Trinity-v1.2 7B Q4 | An experimental model merge using the Slerp method |
-| Openchat-3.5 7B Q4 | An open-source model that has the performance that surpasses that of ChatGPT-3.5 and Grok-1 across various benchmarks |
+| Openchat-3.5 7B Q4 | An open-source model that has a performance that surpasses that of ChatGPT-3.5 and Grok-1 across various benchmarks |
| Wizard Coder Python 13B Q5 | A Python coding model that demonstrates high proficiency in specific domains like coding and mathematics |
-| OpenAI GPT 3.5 Turbo | The latest GPT-3.5 Turbo model with higher accuracy at responding in requested formats and a fix for a bug which caused a text encoding issue for non-English language function calls |
+| OpenAI GPT 3.5 Turbo | The latest GPT-3.5 Turbo model with higher accuracy at responding in requested formats and a fix for a bug that caused a text encoding issue for non-English language function calls |
| OpenAI GPT 3.5 Turbo 16k 0613 | A Snapshot model of gpt-3.5-16k-turbo from June 13th 2023 |
| OpenAI GPT 4 | The latest GPT-4 model intended to reduce cases of “laziness” where the model doesn't complete a task |
| TinyLlama Chat 1.1B Q4 | A tiny model with only 1.1B. It's a good model for less powerful computers |
| Deepseek Coder 1.3B Q8 | A model that excelled in project-level code completion with advanced capabilities across multiple programming languages |
| Phi-2 3B Q8 | a 2.7B model, excelling in common sense and logical reasoning benchmarks, trained with synthetic texts and filtered websites |
| Llama 2 Chat 7B Q4 | A model that is specifically designed for a comprehensive understanding through training on extensive internet data |
-| CodeNinja 7B Q4 | A model that is is good for coding tasks and can handle various languages including Python, C, C++, Rust, Java, JavaScript, and more |
-| Noromaid 7B Q5 | A model that is designed for role-playing with human-like behavior. |
-| Starling alpha 7B Q4 | An upgrade of Openchat 3.5 using RLAIF, is really good at various benchmarks, especially with GPT-4 judging its performance |
+| CodeNinja 7B Q4 | A model that is good for coding tasks and can handle various languages, including Python, C, C++, Rust, Java, JavaScript, and more |
+| Noromaid 7B Q5 | A model designed for role-playing with human-like behavior. |
+| Starling alpha 7B Q4 | An upgrade of Openchat 3.5 using RLAIF, is good at various benchmarks, especially with GPT-4 judging its performance |
| Yarn Mistral 7B Q4 | A language model for long context and supports a 128k token context window |
| LlaVa 1.5 7B Q5 K | A model can bring vision understanding to Jan |
| BakLlava 1 | A model can bring vision understanding to Jan |
@@ -33,16 +32,16 @@ Jan provides various pre-configured AI models with different capabilities. Pleas
| LlaVa 1.5 13B Q5 K | A model can bring vision understanding to Jan |
| Deepseek Coder 33B Q5 | A model that excelled in project-level code completion with advanced capabilities across multiple programming languages |
| Phind 34B Q5 | A multi-lingual model that is fine-tuned on 1.5B tokens of high-quality programming data, excels in various programming languages, and is designed to be steerable and user-friendly |
-| Yi 34B Q5 | A specialized chat model, is known for its diverse and creative responses and excels across various NLP tasks and benchmarks |
+| Yi 34B Q5 | A specialized chat model is known for its diverse and creative responses and excels across various NLP tasks and benchmarks |
| Capybara 200k 34B Q5 | A long context length model that supports 200K tokens |
| Dolphin 8x7B Q4 | An uncensored model built on Mixtral-8x7b and it is good at programming tasks |
-| Mixtral 8x7B Instruct Q4 | A pretrained generative Sparse Mixture of Experts, which outperforms 70B models on most benchmarks |
+| Mixtral 8x7B Instruct Q4 | A pre-trained generative Sparse Mixture of Experts, which outperforms 70B models on most benchmarks |
| Tulu 2 70B Q4 | A strong model alternative to Llama 2 70b Chat to act as helpful assistants |
| Llama 2 Chat 70B Q4 | A model that is specifically designed for a comprehensive understanding through training on extensive internet data |
:::note
-OpenAI GPT models requires a subscription in order to use them further. To learn more, [click here](https://openai.com/pricing).
+OpenAI GPT models require a subscription to use them further. To learn more, [click here](https://openai.com/pricing).
:::
@@ -69,13 +68,3 @@ OpenAI GPT models requires a subscription in order to use them further. To learn
| Yarn Mistral 7B Q4 | NousResearch, The Bloke | `yarn-mistral-7b` | **GGUF** | 4.07GB |
| LlaVa 1.5 7B Q5 K | Mys | `llava-1.5-7b-q5` | **GGUF** | 5.03GB |
| BakLlava 1 | Mys | `bakllava-1` | **GGUF** | 5.36GB |
-| Solar Slerp 10.7B Q4 | Jan | `solar-10.7b-slerp` | **GGUF** | 5.92GB |
-| LlaVa 1.5 13B Q5 K | Mys | `llava-1.5-13b-q5` | **GGUF** | 9.17GB |
-| Deepseek Coder 33B Q5 | Deepseek, The Bloke | `deepseek-coder-34b` | **GGUF** | 18.57GB |
-| Phind 34B Q5 | Phind, The Bloke | `phind-34b` | **GGUF** | 18.83GB |
-| Yi 34B Q5 | 01-ai, The Bloke | `yi-34b` | **GGUF** | 19.24GB |
-| Capybara 200k 34B Q5 | NousResearch, The Bloke | `capybara-34b` | **GGUF** | 22.65GB |
-| Dolphin 8x7B Q4 | Cognitive Computations, TheBloke | `dolphin-2.7-mixtral-8x7b` | **GGUF** | 24.62GB |
-| Mixtral 8x7B Instruct Q4 | MistralAI, TheBloke | `mixtral-8x7b-instruct` | **GGUF** | 24.62GB |
-| Tulu 2 70B Q4 | Lizpreciatior, The Bloke | `tulu-2-70b` | **GGUF** | 38.56GB |
-| Llama 2 Chat 70B Q4 | MetaAI, The Bloke | `llama2-chat-70b-q4` | **GGUF** | 40.90GB |
\ No newline at end of file
diff --git a/docs/docs/quickstart/quickstart.mdx b/docs/docs/quickstart/quickstart.mdx
index c84e21d54..c00fbfd5c 100644
--- a/docs/docs/quickstart/quickstart.mdx
+++ b/docs/docs/quickstart/quickstart.mdx
@@ -4,6 +4,7 @@ hide_table_of_contents: true
---
import installImageURL from './assets/jan-ai-quickstart.png';
+import flow from './assets/quick.png';
# Quickstart
@@ -28,12 +29,19 @@ import installImageURL from './assets/jan-ai-quickstart.png';
3. Go to the **Hub** under the **Thread** section and select the AI model that you want to use. For more info, go to the [Using Models](category/using-models) section.
4. A new thread will be added. You can use Jan in the thread with the AI model that you selected before. */}
+
+
+