yujunjun/LLMs-from-scratch
1
0
Fork 0
mirror of https://github.com/rasbt/LLMs-from-scratch.git synced 2025-08-31 03:50:23 +00:00
Code Issues Packages Projects Releases Wiki Activity

spelling fix

Browse Source
This commit is contained in:
rasbt 2024-06-22 12:22:15 -05:00
parent fef88072eb
commit 519bfd6dc5
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
ch07/01_main-chapter-code/exercise-solutions.ipynb
View File

@ -956,7 +956,7 @@
"\n",
"For comparison, you can run the original chapter 7 finetuning code via `python exercise_experiments.py --exercise_solution baseline`. \n",
"\n",
"Note that on an Nvidia L4 GPU, the code above, using LoRA, takes 1.30 min to run. In comparison, the Alpaca-style template takes 1.80 minutes to run. So, LoRA is approximately 28% faster.\n",
"Note that on an Nvidia L4 GPU, the code above, using LoRA, takes 1.30 min to run. In comparison, the baseline takes 1.80 minutes to run. So, LoRA is approximately 28% faster.\n",
"\n",
"\n",
"We can evaluate the performance using the Ollama Llama 3 method, which is for your convenience, also implemented in the `python exercise_experiments.py` script, which we can run as follows:\n",
@ -974,7 +974,7 @@
"Average score: 50.23\n",
"```\n",
"\n",
"The score is around 50, which is in the same ballpark as original model."
"The score is around 50, which is in the same ballpark as the original model."
]
}
],