mlx-community/granite-3b-code-instruct-4bit
The Model mlx-community/granite-3b-code-instruct-4bit 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-4bit")
response = generate(model, tokenizer, prompt="hello", verbose=True)
- Downloads last month
- 18
Model tree for mlx-community/granite-3b-code-instruct-4bit
Base model
ibm-granite/granite-3b-code-base-2kDatasets used to train mlx-community/granite-3b-code-instruct-4bit
Evaluation results
- pass@1 on HumanEvalSynthesis(Python)self-reported51.200
- pass@1 on HumanEvalSynthesis(Python)self-reported43.900
- pass@1 on HumanEvalSynthesis(Python)self-reported41.500
- pass@1 on HumanEvalSynthesis(Python)self-reported31.700
- pass@1 on HumanEvalSynthesis(Python)self-reported40.200
- pass@1 on HumanEvalSynthesis(Python)self-reported29.300
- pass@1 on HumanEvalSynthesis(Python)self-reported39.600
- pass@1 on HumanEvalSynthesis(Python)self-reported26.800
- pass@1 on HumanEvalSynthesis(Python)self-reported39.000
- pass@1 on HumanEvalSynthesis(Python)self-reported14.000