RichardErkhov's picture
uploaded readme
dc8f453 verified

Quantization made by Richard Erkhov.

Github

Discord

Request more models

starcoder2-3b-instruct-v0.1 - GGUF

Original model description:

license: bigcode-openrail-m datasets: - bigcode/self-oss-instruct-sc2-exec-filter-50k base_model: - bigcode/starcoder2-3b library_name: transformers

Starcoder2-3b finetuned the same way as https://huggingface.co/bigcode/starcoder2-15b-instruct-v0.1 using https://huggingface.co/datasets/bigcode/self-oss-instruct-sc2-exec-filter-50k

  • Epochs: 1
  • Learning Rate: 0.0001
  • Lora Rank: 8
  • Batch Size: 16
  • Evaluation Split: 0