RELLE / README.md
bchoiced
Initial commit
0934177

RELLE

we have trained the RELLE model based on the Mistral-7B LLM model.

The initial goal is to reproduce the baseline model and check the workflow for uploading results:

  • Check the upload workflow.
  • Checkpoint
  • training
  • We plan to release a technical report in the future.

Model Information

  • Model Size: 7B
  • Embedding Dimension: 4096
  • Max Input Tokens: 32k

Requirements

transformers>=4.48.3