|
|
--- |
|
|
base_model: unsloth/deepseek-r1-distill-llama-8b-unsloth-bnb-4bit |
|
|
tags: |
|
|
- text-generation-inference |
|
|
- transformers |
|
|
- unsloth |
|
|
- llama |
|
|
- trl |
|
|
license: apache-2.0 |
|
|
language: |
|
|
- en |
|
|
--- |
|
|
|
|
|
# Tutorial |
|
|
|
|
|
https://medium.com/ai-simplified-in-plain-english/fine-tuning-deepseek-r1-for-text-to-sql-generation-083d480e7eff |
|
|
|
|
|
|
|
|
# Model Evaluation |
|
|
|
|
|
The overall evaluation summary for the 999 examples shows strong performance: |
|
|
|
|
|
------ Overall Evaluation Summary --- |
|
|
|
|
|
Average ROUGE-1 F-measure (over 999 examples): 0.9554 |
|
|
|
|
|
Average ROUGE-2 F-measure (over 999 examples): 0.9426 |
|
|
|
|
|
Average ROUGE-L F-measure (over 999 examples): 0.9520 |
|
|
|
|
|
Average BLEU Score (over 999 examples): 92.1817 |
|
|
|
|
|
|
|
|
# Uploaded model |
|
|
|
|
|
- **Developed by:** frankmorales2020 |
|
|
- **License:** apache-2.0 |
|
|
- **Finetuned from model :** unsloth/deepseek-r1-distill-llama-8b-unsloth-bnb-4bit |
|
|
|
|
|
This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library. |
|
|
|
|
|
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth) |
|
|
|
