MLX
Safetensors
dbrx
custom_code

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

Make you you first upgrade mlx-lm and mlx to the latest.

pip install mlx --upgrade
pip install mlx-lm --upgrade

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

Remember, this is an Instruct model, so you will need to use the instruct prompt template by appending --use-default-chat-template

Example:

python -m mlx_lm.generate --model dbrx-instruct-4bit --prompt "What's the difference between PCA vs UMAP vs t-SNE?" --trust-remote-code --use-default-chat-template  --max-tokens 1000

Output:

image/png

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, add_generation_prompt=True, tokenize=False)

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

Converted and uploaded by eek

Downloads last month
25
Safetensors
Model size
21.1B params
Tensor type
FP16
·
U32
·
Inference API
Inference API (serverless) has been turned off for this model.