phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-15 22:47:59 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

changed from vision to text model

Browse source
This commit is contained in:
Justin Lee 2024-11-08 08:57:38 -08:00
parent efb0fbfaea
commit 92f16ed27b
4 changed files with 12 additions and 12 deletions
Download patch file Download diff file Expand all files Collapse all files

12
docs/zero_to_hero_guide/00_Inference101.ipynb
View file

@ -7,7 +7,7 @@
"source": [
"# Llama Stack Inference Guide\n",
"\n",
"This document provides instructions on how to use Llama Stack's `chat_completion` function for generating text using the `Llama3.2-11B-Vision-Instruct` model. \n",
"This document provides instructions on how to use Llama Stack's `chat_completion` function for generating text using the `Llama3.1-8B-Instruct` model. \n",
"\n",
"Before you begin, please ensure Llama Stack is installed and set up by following the [Getting Started Guide](https://llama-stack.readthedocs.io/en/latest/getting_started/index.html).\n",
"\n",
@ -105,7 +105,7 @@
" SystemMessage(content='You are a friendly assistant.', role='system'),\n",
" UserMessage(content='Write a two-sentence poem about llama.', role='user')\n",
" ],\n",
" model='Llama3.2-11B-Vision-Instruct',\n",
" model='Llama3.1-8B-Instruct',\n",
")\n",
"\n",
"print(response.completion_message.content)"
@ -149,7 +149,7 @@
" SystemMessage(content='You are shakespeare.', role='system'),\n",
" UserMessage(content='Write a two-sentence poem about llama.', role='user')\n",
" ],\n",
" model='Llama3.2-11B-Vision-Instruct',\n",
" model='Llama3.1-8B-Instruct',\n",
")\n",
"\n",
"print(response.completion_message.content)"
@ -220,7 +220,7 @@
" message = UserMessage(content=user_input, role='user')\n",
" response = client.inference.chat_completion(\n",
" messages=[message],\n",
" model='Llama3.2-11B-Vision-Instruct',\n",
" model='Llama3.1-8B-Instruct',\n",
" )\n",
" cprint(f'> Response: {response.completion_message.content}', 'cyan')\n",
"\n",
@ -319,7 +319,7 @@
"\n",
" response = client.inference.chat_completion(\n",
" messages=conversation_history,\n",
" model='Llama3.2-11B-Vision-Instruct',\n",
" model='Llama3.1-8B-Instruct',\n",
" )\n",
" cprint(f'> Response: {response.completion_message.content}', 'cyan')\n",
"\n",
@ -378,7 +378,7 @@
"\n",
" response = client.inference.chat_completion(\n",
" messages=[message],\n",
" model='Llama3.2-11B-Vision-Instruct',\n",
" model='Llama3.1-8B-Instruct',\n",
" stream=stream,\n",
" )\n",
"\n",