mlx-community/granite-8b-code-instruct-8bit
The Model mlx-community/granite-8b-code-instruct-8bit was converted to MLX format from ibm-granite/granite-8b-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-8b-code-instruct-8bit")
response = generate(model, tokenizer, prompt="hello", verbose=True)
- Downloads last month
- 83
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
HF Inference API has been turned off for this model.
Model tree for mlx-community/granite-8b-code-instruct-8bit
Base model
ibm-granite/granite-8b-code-base-4kDatasets used to train mlx-community/granite-8b-code-instruct-8bit
Evaluation results
- pass@1 on HumanEvalSynthesis(Python)self-reported57.900
- pass@1 on HumanEvalSynthesis(Python)self-reported52.400
- pass@1 on HumanEvalSynthesis(Python)self-reported58.500
- pass@1 on HumanEvalSynthesis(Python)self-reported43.300
- pass@1 on HumanEvalSynthesis(Python)self-reported48.200
- pass@1 on HumanEvalSynthesis(Python)self-reported37.200
- pass@1 on HumanEvalSynthesis(Python)self-reported53.000
- pass@1 on HumanEvalSynthesis(Python)self-reported42.700
- pass@1 on HumanEvalSynthesis(Python)self-reported52.400
- pass@1 on HumanEvalSynthesis(Python)self-reported36.600