changed from vision to text model

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

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",

View file

@ -143,7 +143,7 @@
"\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",

View file

@ -154,7 +154,7 @@
"outputs": [],
"source": [
"response = client.inference.chat_completion(\n",
" messages=few_shot_examples, model='Llama3.2-11B-Vision-Instruct'\n",
" messages=few_shot_examples, model='Llama3.1-8B-Instruct'\n",
")"
]
},

View file

@ -1,6 +1,6 @@
# Llama Stack Quickstart Guide
This guide will walk you through setting up an end-to-end workflow with Llama Stack, enabling you to perform text generation using the `Llama3.2-11B-Vision-Instruct` model. Follow these steps to get started quickly.
This guide will walk you through setting up an end-to-end workflow with Llama Stack, enabling you to perform text generation using the `Llama3.1-8B-Instruct` model. Follow these steps to get started quickly.
If you're looking for more specific topics like tool calling or agent setup, we have a [Zero to Hero Guide](#next-steps) that covers everything from Tool Calling to Agents in detail. Feel free to skip to the end to explore the advanced topics you're interested in.
@ -42,7 +42,7 @@ pip install llama-stack
Download the necessary Llama model checkpoints using the `llama` CLI:
```bash
llama download --model-id Llama3.2-11B-Vision-Instruct
llama download --model-id Llama3.1-8B-Instruct
```
*Follow the CLI prompts to complete the download. You may need to accept a license agreement. Obtain an instant license [here](https://www.llama.com/llama-downloads/).*