Nicholai/jan
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

docs: update models content import and integrate remote -> model.json explanation

Browse Source
This commit is contained in:
Arista Indrajaya 2024-03-04 16:41:29 +07:00
parent 2fb99317b0
commit 217ae16d86
2 changed files with 30 additions and 50 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

24
docs/docs/guides/models/import-models.mdx
View File

@ -223,27 +223,9 @@ To update `model.json`:
}
```
#### Regarding `model.json`
- In `settings`, two crucial values are:
- `ctx_len`: Defined based on the model's context size.
- `prompt_template`: Defined based on the model's trained template (e.g., ChatML, Alpaca).
- To set up the `prompt_template`:
1. Visit [Hugging Face](https://huggingface.co/), an open-source machine learning platform.
2. Find the current model that you're using (e.g., [Gemma 7b it](https://huggingface.co/google/gemma-7b-it)).
3. Review the text and identify the template.
- In `parameters`, consider the following options. The fields in `parameters` are typically general and can be the same across models. An example is provided below:
```json
"parameters":{
"temperature": 0.7,
"top_p": 0.95,
"stream": true,
"max_tokens": 4096,
"frequency_penalty": 0,
"presence_penalty": 0
}
```
:::note
For more details regarding the `model.json` settings and parameters fields, please see [here](/docs/guides/models/integrate-remote.mdx#modeljson).
:::
### 3. Download the Model

56
docs/docs/guides/models/integrate-remote.mdx
View File

@ -53,17 +53,32 @@ This guide will show you how to configure Jan as a client and point it to any re
}
```
#### Regarding `model.json`
### `model.json`
- In `settings`, two crucial values are:
- `ctx_len`: Defined based on the model's context size.
- `prompt_template`: Defined based on the model's trained template (e.g., ChatML, Alpaca).
- To set up the `prompt_template`:
The `model.json` file is used to set up your local models.
:::note
- If you've set up your model's configuration in `nitro.json`, please note that `model.json` can overwrite the settings.
- When using OpenAI models like GPT-3.5 and GPT-4, you can use the default settings in `model.json` file.
:::
There are two important fields in model.json that you need to setup:
#### Settings
This is the field where to set your engine configurations, there are two imporant field that you need to define for your local models:
| Term | Description |
|-------------------|---------------------------------------------------------|
| `ctx_len` | Defined based on the model's context size. |
| `prompt_template` | Defined based on the model's trained template (e.g., ChatML, Alpaca). |
To set up the `prompt_template` based on your model, follow the steps below:
1. Visit [Hugging Face](https://huggingface.co/), an open-source machine learning platform.
2. Find the current model that you're using (e.g., [Gemma 7b it](https://huggingface.co/google/gemma-7b-it)).
3. Review the text and identify the template.
- In `parameters`, consider the following options. The fields in `parameters` are typically general and can be the same across models. An example is provided below:
#### Parameters
`parameters` is the adjustable settings that affect how your model operates or processes the data.
The fields in `parameters` are typically general and can be the same across models. An example is provided below:
```json
"parameters":{
@ -76,6 +91,7 @@ This guide will show you how to configure Jan as a client and point it to any re
}
```
:::tip
- You can find the list of available models in the [OpenAI Platform](https://platform.openai.com/docs/models/overview).
@ -136,7 +152,11 @@ Please note that currently, the code that supports any OpenAI-compatible endpoin
1. In `~/jan/models`, create a folder named `mistral-ins-7b-q4`.
2. In this folder, add a `model.json` file with Filename as `model.json`, `id` matching folder name, `Format` as `api`, `Engine` as `openai`, and `State` as `ready`.
2. In this folder, add a `model.json` file with Filename as `model.json`, ensure the following configurations:
- `id` matching folder name.
- `Format` set to `api`.
- `Engine` set to `openai`
- `State` set to `ready`.
```json title="~/jan/models/mistral-ins-7b-q4/model.json"
@ -163,28 +183,6 @@ Please note that currently, the code that supports any OpenAI-compatible endpoin
}
```
### Regarding `model.json`
- In `settings`, two crucial values are:
- `ctx_len`: Defined based on the model's context size.
- `prompt_template`: Defined based on the model's trained template (e.g., ChatML, Alpaca).
- To set up the `prompt_template`:
1. Visit [Hugging Face](https://huggingface.co/), an open-source machine learning platform.
2. Find the current model that you're using (e.g., [Gemma 7b it](https://huggingface.co/google/gemma-7b-it)).
3. Review the text and identify the template.
- In `parameters`, consider the following options. The fields in `parameters` are typically general and can be the same across models. An example is provided below:
```json
"parameters":{
"temperature": 0.7,
"top_p": 0.95,
"stream": true,
"max_tokens": 4096,
"frequency_penalty": 0,
"presence_penalty": 0
}
```
### 3. Start the Model
1. Restart Jan and navigate to the **Hub**.