mlx-community/starcoder2-3b-4bit
This model was converted to MLX format from bigcode/starcoder2-3b
.
Refer to the original model card for more details on the model.
Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("mlx-community/starcoder2-3b-4bit")
response = generate(model, tokenizer, prompt="hello", verbose=True)
- Downloads last month
- 15
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
the model is not deployed on the HF Inference API.
Dataset used to train mlx-community/starcoder2-3b-4bit
Evaluation results
- pass@1 on CruxEval-Iself-reported32.700
- pass@1 on DS-1000self-reported25.000
- accuracy on GSM8K (PAL)self-reported27.700
- pass@1 on HumanEval+self-reported27.400
- pass@1 on HumanEvalself-reported31.700
- edit-smiliarity on RepoBench-v1.1self-reported71.190