Downloads · 30 days
37
8% of all-time downloads
granite-34b-code-instruct-8bit
mlx-community/granite-34b-code-instruct-8bit
granite-34b-code-instruct-8bit is a text generation model from mlx-community. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as apache-2.0.
The Model mlx-community/granite-34b-code-instruct-8bit was converted to MLX format from ibm-granite/granite-34b-code-instruct using mlx-lm version 0.13.0.
All-time downloads
467
Public
Parameters
33.7B
35.8 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors35.8 GB · 100%
Parameter types
How the weights are stored.
U3233.7B · 100%
Try a prompt
Base models
Model card
From the Hugging Face model README
mlx-community/granite-34b-code-instruct-8bit
The Model mlx-community/granite-34b-code-instruct-8bit was converted to MLX format from ibm-granite/granite-34b-code-instruct using mlx-lm version 0.13.0.
Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("mlx-community/granite-34b-code-instruct-8bit")
response = generate(model, tokenizer, prompt="hello", verbose=True)
- Task
- Text Generation
- Library
- transformers
- Type
- gpt_bigcode
- License
- apache-2.0
- Created
- May 6, 2024
- Updated
- May 14, 2024