|
|
--- |
|
|
library_name: transformers |
|
|
license: apache-2.0 |
|
|
datasets: |
|
|
- TokenBender/code_instructions_122k_alpaca_style |
|
|
--- |
|
|
|
|
|
# Model Card for Model ID |
|
|
|
|
|
<!-- Provide a quick summary of what the model is/does. --> |
|
|
|
|
|
This is a LoRA adapter for Mistral-Instruct-v0.2 |
|
|
|
|
|
Base Model: [Mistral-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) |
|
|
Dataset: [TokenBender/code_instructions_122k_alpaca_style](https://huggingface.co/datasets/TokenBender/code_instructions_122k_alpaca_style) |
|
|
|
|
|
Test run, trained on subsample of 5k examples for 1 epoch using QLoRa technique. |
|
|
|
|
|
Final loss: 0.394200 |
