jan.md

To use the DCLM-7B model on Jan.ai, follow these steps:

Install the Required Tools: Ensure you have the necessary tools installed. You might need packages like transformers and open_lm. You can install them using:
```
pip install git+https://github.com/mlfoundations/open_lm.git transformers
```

Download the Model: Integrate the DCLM-7B model from Hugging Face with Jan.ai:

from open_lm.hf import *
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("apple/DCLM-Baseline-7B")
model = AutoModelForCausalLM.from_pretrained("apple/DCLM-Baseline-7B")

Set Up Jan API Server:
- Enable the Jan API Server. Go to the Local API Server section on Jan.ai and set up the server, including the IP Port, CORS, and verbose server logs.
- Start the server by pressing the Start Server button.

Configure the Local Server:

Navigate to the ~/.continue directory.

Ensure the configuration file (~/.continue/config.json) includes:

{
  "models": [
    {
      "title": "Jan",
      "provider": "openai",
      "model": "dclm-7b",
      "apiKey": "EMPTY",
      "apiBase": "http://localhost:1337/v1"
    }
  ]
}

Ensure the model name and API base match the ones set up in the Jan API Server.

Activate the Model in Jan:
- Go to Settings > My Models on Jan.ai.
- Click the three dots (⋮) next to the model and select "Start Model" to activate it.

Following these steps will allow you to integrate and use the DCLM-7B model with Jan.ai, leveraging its capabilities within your local environment. For more detailed instructions, you can refer to the Jan.ai documentation and the specific integration guide for local AI models【19†source】【20†source】.

potatoqualitee/jan.md