mlx-community/granite-20b-code-base-8bit
The Model mlx-community/granite-20b-code-base-8bit was converted to MLX format from ibm-granite/granite-20b-code-base 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-20b-code-base-8bit")
response = generate(model, tokenizer, prompt="hello", verbose=True)
- Downloads last month
- 0
Datasets used to train mlx-community/granite-20b-code-base-8bit
Evaluation results
- pass@1 on MBPPself-reported43.800
- pass@1 on MBPP+self-reported51.600
- pass@1 on HumanEvalSynthesis(Python)self-reported48.200
- pass@1 on HumanEvalSynthesis(Python)self-reported50.000
- pass@1 on HumanEvalSynthesis(Python)self-reported59.100
- pass@1 on HumanEvalSynthesis(Python)self-reported32.300
- pass@1 on HumanEvalSynthesis(Python)self-reported40.900
- pass@1 on HumanEvalSynthesis(Python)self-reported35.400
- pass@1 on HumanEvalSynthesis(Python)self-reported17.100
- pass@1 on HumanEvalSynthesis(Python)self-reported18.300
- pass@1 on HumanEvalSynthesis(Python)self-reported23.200
- pass@1 on HumanEvalSynthesis(Python)self-reported10.400
- pass@1 on HumanEvalSynthesis(Python)self-reported25.600
- pass@1 on HumanEvalSynthesis(Python)self-reported18.300
- pass@1 on HumanEvalSynthesis(Python)self-reported23.200
- pass@1 on HumanEvalSynthesis(Python)self-reported23.800
- pass@1 on HumanEvalSynthesis(Python)self-reported14.600
- pass@1 on HumanEvalSynthesis(Python)self-reported26.200
- pass@1 on HumanEvalSynthesis(Python)self-reported15.200
- pass@1 on HumanEvalSynthesis(Python)self-reported3.000