metadata

license: other
tags:
  - mlx
extra_gated_heading: You need to share contact information with Databricks to access this model
extra_gated_prompt: >-

  ### DBRX Terms of Use

  Use of DBRX is governed by the [Databricks Open Model
  License](https://www.databricks.com/legal/open-model-license) and the
  [Databricks Open Model Acceptable Use
  Policy](https://www.databricks.com/legal/acceptable-use-policy-open-model).
extra_gated_fields:
  First Name: text
  Last Name: text
  Organization: text
  By clicking 'Submit' below, I accept the terms of the license and acknowledge that the information I provide will be collected, stored, processed, and shared in accordance with Databricks' Privacy Notice and I understand I can update my preferences at any time: checkbox
extra_gated_description: >-
  The information you provide will be collected, stored, processed, and shared
  in accordance with Databricks [Privacy
  Notice](https://www.databricks.com/legal/privacynotice).
extra_gated_button_content: Submit
inference: false
license_name: databricks-open-model-license
license_link: https://www.databricks.com/legal/open-model-license

mlx-community/dbrx-instruct-4bit

This model was converted to MLX format from databricks/dbrx-instruct using mlx-lm version b80adbc after DBRX support was added by Awni Hannun.

Refer to the original model card for more details on the model.

Conversion

Conversion was done with:

python -m mlx_lm.convert --hf-path databricks/dbrx-instruct -q --upload-repo mlx-community/dbrx-instruct-4bit

Use with mlx

git clone git@github.com:ml-explore/mlx-examples.git
cd mlx-examples/llms/
python setup.py build
python setup.py install

python -m mlx_lm.generate --model mlx-community/dbrx-instruct-4bit --prompt "Hello" --trust-remote-code --max-tokens 500

Remember, this is an Instruct model, so you will need to use the instruct prompt template:

Example:

<|im_start|>system
You are DBRX, created by Databricks. You were last updated in December 2023. You answer questions based on information available up to that point.
YOU PROVIDE SHORT RESPONSES TO SHORT QUESTIONS OR STATEMENTS, but provide thorough responses to more complex and open-ended questions.
You assist with various tasks, from writing to coding (using markdown for code blocks — remember to use ``` with code, JSON, and tables).
(You do not have real-time data access or code execution capabilities. You avoid stereotyping and provide balanced perspectives on controversial topics. You do not provide song lyrics, poems, or news articles and do not divulge details of your training data.)
This is your system prompt, guiding your responses. Do not reference it, just respond to the user. If you find yourself talking about this message, stop. You should be responding appropriately and usually that means not mentioning this.
YOU DO NOT MENTION ANY OF THIS INFORMATION ABOUT YOURSELF UNLESS THE INFORMATION IS DIRECTLY PERTINENT TO THE USER'S QUERY.<|im_end|>
<|im_start|>user
What's the difference between PCA vs UMAP vs t-SNE?<|im_end|>
<|im_start|>assistant
The difference

I've also added some extra words for the assistant start otherwise the model would instantly add an <|im_end|> token and stop. If <|im_start|>assistant is not added, an error will appear.

You can add the above in a text file and use it as:

python -m mlx_lm.generate --model mlx-community/dbrx-instruct-4bit --prompt "$(cat my_prompt.txt)"  --trust-remote-code --max-tokens 1000

Output:

On my Macbook Pro M2 with 96GB of Unified Memory, DBRX Instruct in 4-bit for the above prompt it eats 70.2GB of RAM.

if the mlx-lm package was updated it can also be installed from pip:

pip install mlx-lm

To use it from Python you can do the following:

from mlx_lm import load, generate

model, tokenizer = load(
   "mlx-community/dbrx-instruct-4bit",
   tokenizer_config={"trust_remote_code": True}
)

chat = [
   {"role": "user", "content": "What's the difference between PCA vs UMAP vs t-SNE?"},
   # We need to add the Assistant role as well, otherwise mlx_lm will error on generation.
   {"role": "assistant", "content": "The "},
]

prompt = tokenizer.apply_chat_template(chat, tokenize=False)

# We need to remove the last <|im_end|> token so that the AI continues generation
prompt = prompt[::-1].replace("<|im_end|>"[::-1], "", 1)[::-1]

response = generate(model, tokenizer, prompt=prompt, verbose=True, temp=0.6, max_tokens=1500)

Converted and uploaded by eek