rombodawg's picture
Update README.md
7741878 verified
|
raw
history blame
765 Bytes
metadata
language:
  - en
license: apache-2.0
tags:
  - text-generation-inference
  - transformers
  - unsloth
  - llama
  - trl
  - sft
base_model: NousResearch/Meta-Llama-3-8B

This is was experinment to update my training method for future finetunes.

This model was trained on the dataset bellow for 5 epochs, at a learning rate of 2e-4, with 20 warm up steps.

https://huggingface.co/datasets/Replete-AI/code_test_dataset_10k

Prompt format: Alpaca

Below is an instruction that describes a task, Write a response that appropriately completes the request.

### Instruction:

### Response:

Join the Replete-Ai discord! We are a great and Loving community!