books/LLMs-from-scratch
1
0
Fork 0
mirror of https://github.com/rasbt/LLMs-from-scratch.git synced 2026-04-10 12:33:42 +00:00
Code Issues Packages Projects Releases Wiki Activity

Add standalone finetuning and evaluation scripts for chapter 7 (#234)

Browse Source 
* add finetuning and eval scripts

* update link

* update links

* fix link
This commit is contained in:
Sebastian Raschka
2024-06-21 05:23:24 -05:00
committed by GitHub
parent e1046746e8
commit 87deec0f5f
10 changed files with 153 additions and 10 deletions
Download Patch File Download Diff File Expand all files Collapse all files

19
ch07/01_main-chapter-code/README.md
View File

@@ -10,12 +10,12 @@
- [load-finetuned-model.ipynb](load-finetuned-model.ipynb) is a standalone Jupyter notebook to load the instruction finetuned model we created in this chapter
- [gpt-instruction-finetuning.py](gpt-instruction-finetuning.py) is a standalone Python script to instruction finetune the model as described in the main chapter
- [gpt_instruction_finetuning.py](gpt_instruction_finetuning.py) is a standalone Python script to instruction finetune the model as described in the main chapter (think of it as a chapter summary focused on the finetuning parts)
Usage:
```bash
python gpt-instruction-finetuning.py
python gpt_instruction_finetuning.py
```
```
@@ -55,3 +55,18 @@ Responses saved as instruction-data-with-response-standalone.json
Model saved as gpt2-medium355M-sft-standalone.pth
```
- [ollama_evaluate.py](ollama_evaluate.py) is a standalone Python script to evaluate the responses of the finetuned model as described in the main chapter (think of it as a chapter summary focused on the evaluation parts)
Usage:
```bash
python ollama_evaluate.py --file_path instruction-data-with-response-standalone.json
```
```
Ollama running: True
Scoring entries: 100%|███████████████████████████████████████| 110/110 [01:08<00:00, 1.62it/s]
Number of scores: 110 of 110
Average score: 51.75
```