mirror of
https://github.com/microsoft/generative-ai-for-beginners.git
synced 2026-06-05 21:07:14 +08:00
fix: repair broken markdown links in Lessons 14, 17, and 18
Lesson 14: - Fix 10 truncated tracking IDs where `koreyst` was misspelled as `koreys` (missing trailing `t`) across all URLs and image paths Lesson 17: - Fix malformed JARVIS URL with double `?` query delimiter (`?tab=readme-ov-file?WT.mc_id=` → `?tab=readme-ov-file&WT.mc_id=`) Lesson 18: - Fix malformed Azure fine-tuning tutorial URL with double `?` (`?tabs=python-new%2Ccommand-line?WT.mc_id=` → `&WT.mc_id=`) - Remove stray `]` bracket inside TRL documentation URL that broke the markdown link rendering
This commit is contained in:
Vikrant Singh
parent
ca334a0cb6
commit
ba79c023a8
@ -21,7 +21,7 @@ LLMs are a new tool in the Artificial Intelligence arsenal, they are incredibly
|
||||
|
||||
With this, we need a new Paradigm to adapt this tool in a dynamic, with the correct incentives. We can categorize older AI apps as "ML Apps" and newer AI Apps as "GenAI Apps" or just "AI Apps", reflecting the mainstream technology and techniques used at the time. This shifts our narrative in multiple ways, look at the following comparison.
|
||||
|
||||
|
||||
|
||||
|
||||
Notice that in LLMOps, we are more focused on the App Developers, using integrations as a key point, using "Models-as-a-Service" and thinking in the following points for metrics.
|
||||
|
||||
@ -35,7 +35,7 @@ Notice that in LLMOps, we are more focused on the App Developers, using integrat
|
||||
|
||||
First, to understand the lifecycle and the modifications, let's note the next infographic.
|
||||
|
||||
|
||||
|
||||
|
||||
As you may note, this is different from the usual Lifecycles from MLOps. LLMs have many new requirements, as Prompting, different techniques to improve quality (Fine-Tuning, RAG, Meta-Prompts), different assessment and responsibility with responsible AI, lastly, new evaluation metrics (Quality, Harm, Honesty, Cost and Latency).
|
||||
|
||||
@ -45,7 +45,7 @@ Note that this is not linear, but integrated loops, iterative and with an overar
|
||||
|
||||
How could we explore those steps? Let's step into detail in how could we build a lifecycle.
|
||||
|
||||
|
||||
|
||||
|
||||
This may look a bit complicated, lets focus on the three big steps first.
|
||||
|
||||
@ -55,21 +55,21 @@ This may look a bit complicated, lets focus on the three big steps first.
|
||||
|
||||
Then, we have the overarching cycle of Management, focusing on security, compliance and governance.
|
||||
|
||||
Congratulations, now you have your AI App ready to go and operational. For a hands on experience, take a look on the [Contoso Chat Demo.](https://nitya.github.io/contoso-chat/?WT.mc_id=academic-105485-koreys)
|
||||
Congratulations, now you have your AI App ready to go and operational. For a hands on experience, take a look on the [Contoso Chat Demo.](https://nitya.github.io/contoso-chat/?WT.mc_id=academic-105485-koreyst)
|
||||
|
||||
Now, what tools could we use?
|
||||
|
||||
## Lifecycle Tooling
|
||||
|
||||
For Tooling, Microsoft provides the [Azure AI Platform](https://azure.microsoft.com/solutions/ai/?WT.mc_id=academic-105485-koreys) and [PromptFlow](https://microsoft.github.io/promptflow/index.html?WT.mc_id=academic-105485-koreyst) facilitate and make your cycle easy to implement and ready to go.
|
||||
For Tooling, Microsoft provides the [Azure AI Platform](https://azure.microsoft.com/solutions/ai/?WT.mc_id=academic-105485-koreyst) and [PromptFlow](https://microsoft.github.io/promptflow/index.html?WT.mc_id=academic-105485-koreyst) facilitate and make your cycle easy to implement and ready to go.
|
||||
|
||||
The [Azure AI Platform](https://azure.microsoft.com/solutions/ai/?WT.mc_id=academic-105485-koreys), allows you to use [AI Studio](https://ai.azure.com/?WT.mc_id=academic-105485-koreys). AI Studio is a web portal allows you to Explore models, samples and tools. Managing your resources, UI development flows and SDK/CLI options for Code-First development.
|
||||
The [Azure AI Platform](https://azure.microsoft.com/solutions/ai/?WT.mc_id=academic-105485-koreyst), allows you to use [AI Studio](https://ai.azure.com/?WT.mc_id=academic-105485-koreyst). AI Studio is a web portal allows you to Explore models, samples and tools. Managing your resources, UI development flows and SDK/CLI options for Code-First development.
|
||||
|
||||
|
||||
|
||||
|
||||
Azure AI, allows you to use multiple resources, to manage your operations, services, projects, vector search and databases needs.
|
||||
|
||||
|
||||
|
||||
|
||||
Construct, from Proof-of-Concept(POC) until large scale applications with PromptFlow:
|
||||
|
||||
@ -77,7 +77,7 @@ Construct, from Proof-of-Concept(POC) until large scale applications with Prompt
|
||||
- Test and fine-tune your apps for quality AI, with ease.
|
||||
- Use Azure AI Studio to Integrate and Iterate with cloud, Push and Deploy for quick integration.
|
||||
|
||||
|
||||
|
||||
|
||||
## Great! Continue your Learning!
|
||||
|
||||
|
||||
@ -132,7 +132,7 @@ The code is verified before executing. Another feature to manage context in Task
|
||||
|
||||
## JARVIS
|
||||
|
||||
The last agent framework we will explore is [JARVIS](https://github.com/microsoft/JARVIS?tab=readme-ov-file?WT.mc_id=academic-105485-koreyst). What makes JARVIS unique is that it uses an LLM to manage the `state` of the conversation and the `tools`are other AI models. Each of the AI models are specialized models that perform certain tasks such as object detection, transcription or image captioning.
|
||||
The last agent framework we will explore is [JARVIS](https://github.com/microsoft/JARVIS?tab=readme-ov-file&WT.mc_id=academic-105485-koreyst). What makes JARVIS unique is that it uses an LLM to manage the `state` of the conversation and the `tools`are other AI models. Each of the AI models are specialized models that perform certain tasks such as object detection, transcription or image captioning.
|
||||
|
||||
|
||||
|
||||
|
||||
@ -78,8 +78,8 @@ The following resources provide step-by-step tutorials to walk you through a rea
|
||||
| Provider | Tutorial | Description |
|
||||
| ------------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
|
||||
| OpenAI | [How to fine-tune chat models](https://github.com/openai/openai-cookbook/blob/main/examples/How_to_finetune_chat_models.ipynb?WT.mc_id=academic-105485-koreyst) | Learn to fine-tune a `gpt-35-turbo` for a specific domain ("recipe assistant") by preparing training data, running the fine-tuning job, and using the fine-tuned model for inference. |
|
||||
| Azure OpenAI | [GPT 3.5 Turbo fine-tuning tutorial](https://learn.microsoft.com/azure/ai-services/openai/tutorials/fine-tune?tabs=python-new%2Ccommand-line?WT.mc_id=academic-105485-koreyst) | Learn to fine-tune a `gpt-35-turbo-0613` model **on Azure** by taking steps to create & upload training data, run the fine-tuning job. Deploy & use the new model. |
|
||||
| Hugging Face | [Fine-tuning LLMs with Hugging Face](https://www.philschmid.de/fine-tune-llms-in-2024-with-trl?WT.mc_id=academic-105485-koreyst) | This blog post walks you fine-tuning an _open LLM_ (ex: `CodeLlama 7B`) using the [transformers](https://huggingface.co/docs/transformers/index?WT.mc_id=academic-105485-koreyst) library & [Transformer Reinforcement Learning (TRL)](https://huggingface.co/docs/trl/index?WT.mc_id=academic-105485-koreyst]) with open [datasets](https://huggingface.co/docs/datasets/index?WT.mc_id=academic-105485-koreyst) on Hugging Face. |
|
||||
| Azure OpenAI | [GPT 3.5 Turbo fine-tuning tutorial](https://learn.microsoft.com/azure/ai-services/openai/tutorials/fine-tune?tabs=python-new%2Ccommand-line&WT.mc_id=academic-105485-koreyst) | Learn to fine-tune a `gpt-35-turbo-0613` model **on Azure** by taking steps to create & upload training data, run the fine-tuning job. Deploy & use the new model. |
|
||||
| Hugging Face | [Fine-tuning LLMs with Hugging Face](https://www.philschmid.de/fine-tune-llms-in-2024-with-trl?WT.mc_id=academic-105485-koreyst) | This blog post walks you fine-tuning an _open LLM_ (ex: `CodeLlama 7B`) using the [transformers](https://huggingface.co/docs/transformers/index?WT.mc_id=academic-105485-koreyst) library & [Transformer Reinforcement Learning (TRL)](https://huggingface.co/docs/trl/index?WT.mc_id=academic-105485-koreyst) with open [datasets](https://huggingface.co/docs/datasets/index?WT.mc_id=academic-105485-koreyst) on Hugging Face. |
|
||||
| | | |
|
||||
| 🤗 AutoTrain | [Fine-tuning LLMs with AutoTrain](https://github.com/huggingface/autotrain-advanced/?WT.mc_id=academic-105485-koreyst) | AutoTrain (or AutoTrain Advanced) is a python library developed by Hugging Face that allows finetuning for many different tasks including LLM finetuning. AutoTrain is a no-code solution and finetuning can be done in your own cloud, on Hugging Face Spaces or locally. It supports both a web-based GUI, CLI and training via yaml config files. |
|
||||
| | | |
|
||||
|
||||
Loading…
Reference in New Issue
Block a user