Text Generation
Transformers
Safetensors
MLX
llama
code
conversational
Eval Results
text-generation-inference
Edit model card

mlx-community/granite-3b-code-instruct-8bit

The Model mlx-community/granite-3b-code-instruct-8bit was converted to MLX format from ibm-granite/granite-3b-code-instruct 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-instruct-8bit")
response = generate(model, tokenizer, prompt="hello", verbose=True)
Downloads last month
1
Safetensors
Model size
980M params
Tensor type
FP16
·
U32
·
Inference API
Input a message to start chatting with mlx-community/granite-3b-code-instruct-8bit.
Inference API (serverless) has been turned off for this model.

Finetuned from

Datasets used to train mlx-community/granite-3b-code-instruct-8bit

Evaluation results