Edit model card

StarCoder2-Instruct-GGUF

Model Summary

We introduce StarCoder2-15B-Instruct-v0.1, the very first entirely self-aligned code Large Language Model (LLM) trained with a fully permissive and transparent pipeline. Our open-source pipeline uses StarCoder2-15B to generate thousands of instruction-response pairs, which are then used to fine-tune StarCoder-15B itself without any human annotations or distilled data from huge and proprietary LLMs.

self-alignment pipeline

Use

Intended use

The model is designed to respond to coding-related instructions in a single turn. Instructions in other styles may result in less accurate responses.

Bias, Risks, and Limitations

StarCoder2-15B-Instruct-v0.1 is primarily finetuned for Python code generation tasks that can be verified through execution, which may lead to certain biases and limitations. For example, the model might not adhere strictly to instructions that dictate the output format. In these situations, it's beneficial to provide a response prefix or a one-shot example to steer the model’s output. Additionally, the model may have limitations with other programming languages and out-of-domain coding tasks.

The model also inherits the bias, risks, and limitations from its base StarCoder2-15B model. For more information, please refer to the StarCoder2-15B model card.

Evaluation on EvalPlus, LiveCodeBench, and DS-1000

EvalPlus

LiveCodeBench and DS-1000

Training Details

Hyperparameters

  • Optimizer: Adafactor
  • Learning rate: 1e-5
  • Epoch: 4
  • Batch size: 64
  • Warmup ratio: 0.05
  • Scheduler: Linear
  • Sequence length: 1280
  • Dropout: Not applied

Hardware

1 x NVIDIA A100 80GB

Resources

Downloads last month
260
GGUF
Model size
16B params
Architecture
starcoder2

Quantized from

Dataset used to train QuantFactory/starcoder2-15b-instruct-v0.1-GGUF

Evaluation results