Hugging Face's logo

mlx-community
/
granite-3b-code-base-4bit

Text Generation
Transformers
Safetensors
MLX
llama
code
Eval Results
text-generation-inference
Model card Files Community
1

mlx-community/granite-3b-code-base-4bit

The Model mlx-community/granite-3b-code-base-4bit was converted to MLX format from ibm-granite/granite-3b-code-base using mlx-lm version 0.12.0.

Use with mlx 

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("mlx-community/granite-3b-code-base-4bit")
response = generate(model, tokenizer, prompt="hello", verbose=True)
Downloads last month
5
Safetensors
Model size
545M params
Tensor type
FP16
·
U32
·
Inference Providers NEW
Text Generation
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API: The model authors have turned it off explicitly.

Datasets used to train mlx-community/granite-3b-code-base-4bit

Evaluation results

View on Papers With Code