phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-08-12 13:00:39 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

refine

Browse source
This commit is contained in:
Botao Chen 2025-02-25 23:28:05 -08:00
parent 81aed4c1e7
commit f227045b6b
1 changed files with 2 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

4
docs/notebooks/Alpha_Llama_Stack_Post_Training.ipynb
View file

@ -15,7 +15,7 @@
"\n",
"Resource requirement:\n",
"- You can run this notebook with Llama 3.2 3B instruct model on Colab's **FREE** T4 GPU\n",
"- You can run this notebook with Llama 3.1 8B instruct model on Colab's A100 GPU or any GPU types with more than 16GB memory\n",
"- You can run this notebook with Llama 3.1 8B instruct model on Colab's A100 GPU or any GPU types with more than 22GB memory\n",
"- You need to spin up an ollama server on local host (will provider step by step instruction on this)\n",
"\n",
"> **Note**: Llama Stack post training APIs are in alpha release stage and still under heavy development\n"
@ -6360,7 +6360,7 @@
"# We limit to 50 rows from the dataset to save time\n",
"eval_rows = client.datasetio.get_rows_paginated(\n",
" dataset_id=\"eval_dataset\",\n",
" rows_in_page=50,\n",
" rows_in_page=-1,\n",
")\n",
"\n",
"from tqdm import tqdm\n",