Merge pull request #36 from jbusche/jbusche-granite4

Removing all granite3 references

Author: jjasghar

docs/lab-1.5/README.md

@@ -13,8 +13,6 @@ First, if you haven't already, download the Granite 4 model. Make sure that `oll
 ```bash
 ollama pull granite4:micro
 ```
-!!! note
-    If the granite4:micro model isn't available yet, you can choose granite3.3:2b or granite3.3:8b
 
 !!! note
     The download may take a few minutes depending on your internet connection. In the meantime, you can check out information about model we're using [here](https://ollama.com/library/granite4). Check out how many languages it supports and take note of its capabilities. It'll help you decide what tasks you might want to use it for in the future.

docs/lab-1/README.md

@@ -13,11 +13,9 @@ First, if you haven't already, download the Granite 4 model. Make sure that `oll
 ```bash
 ollama pull granite4:micro
 ```
-!!! note
-    If the granite4:micro model isn't available yet, you can choose granite3.3:2b or granite3.3:8b
 
 !!! note
-    The download may take a few minutes depending on your internet connection. In the meantime, you can check out information about model we're using [here](https://ollama.com/library/granite3.3). Check out how many languages it supports and take note of its capabilities. It'll help you decide what tasks you might want to use it for in the future.
+    The download may take a few minutes depending on your internet connection. In the meantime, you can check out information about model we're using [here](https://ollama.com/library/granite4). Check out how many languages it supports and take note of its capabilities. It'll help you decide what tasks you might want to use it for in the future.
 
 Open the AnythingLLM desktop application and either click on the *Get Started* button or open up settings (the 🔧 button). For now, we are going to configure the global settings for `ollama` but you can always change it in the future.
 

docs/lab-2/README.md

@@ -33,9 +33,7 @@ And you'll see a list similar to the following:
 ```
 ollama list
 NAME                         ID              SIZE      MODIFIED           
-granite3.3:2b                07bd1f170855    1.5 GB    About a minute ago    
-granite3.3:8b                fd429f23b909    4.9 GB    2 minutes ago         
-granite4:micro               b99795f77687    2.1 GB    23 hours ago 
+granite4:micro               4235724a127c    2.1 GB    23 hours ago 
 ```
 Next, use Ollama to run one of the models:
 

docs/lab-5/README.md

@@ -18,8 +18,6 @@ model downloaded in `ollama`. This may take a bit, but we should have a way to c
 ```bash
 ollama pull granite4:micro
 ```
-!!! note
-    If the granite4:micro model isn't available yet, you can use granite3.3:2b or granite3.3:8b
 
 If you didn't know, the supported languages with `granite4` now include:
 

docs/lab-6/README.md

@@ -21,20 +21,19 @@ Open up [Open-WebUI](http://localhost:8080/), and you should see something like
 If you see this that means Open-WebUI is installed correctly, and we can continue configuration, if not, please find a workshop TA or
 raise your hand we'll be there to help you ASAP.
 
-Next as a sanity check, run the following command to confirm you have the [granite3.3:2b](https://ollama.com/library/granite3.3:2b)
+Next as a sanity check, run the following command to confirm you have the [granite4:micro](https://ollama.com/library/granite4:micro)
 model downloaded in `ollama`. This may take a bit, but we should have a way to copy it directly on your laptop.
 
 ```bash
-ollama pull granite3.3:2b
+ollama pull granite4:micro
 ```
 
-If you didn't know, the supported languages with `granite3.3:2b` now include:
+If you didn't know, the supported languages with `granite4:micro` now include:
 
 - English, German, Spanish, French, Japanese, Portuguese, Arabic, Czech, Italian, Korean, Dutch, and Chinese. However, users may fine-tune this Granite model for languages beyond these 12 languages.
 
 And the Capabilities also include:
 
-- Thinking
 - Summarization
 - Text classification
 - Text extraction
@@ -43,11 +42,10 @@ And the Capabilities also include:
 - Code related tasks
 - Function-calling tasks
 - Multilingual dialog use cases
-- Fill-in-the-middle
-- Long-context tasks including long document/meeting summarization, long document QA, etc.
+- Fill-In-the-Middle (FIM) code completions
 
 
-Next click on the down arrow at the top and select the "granite3.3:2b" if it's not already selected.
+Next click on the down arrow at the top and select the "granite4:micro" if it's not already selected.
 
 ![model selection](../images/openwebui_model_selection.png)
 
@@ -58,9 +56,7 @@ List all the past and current CEOs of the IBM corporation in order of their term
 For example:
 ![Small LLM CEO list](../images/small_llm_ceo_list.png)
 
-At first glance, the list looks pretty good. But if you know your IBM CEOs, you'll notice that it misses a few of them, and sometimes adds new names that weren't ever IBM CEOs!
-(Note: the larger granite3.3:8b does a much better job on the IBM CEOs, you can try it later)
-But we can provide the small LLM with a RAG document that supplements the model's missing information with a correct list, so it will generate a better answer.
+At first glance, the list looks pretty good. But if you know your IBM CEOs, you'll notice that it misses a few of them, and sometimes adds new names that weren't ever IBM CEOs! Retrieval Augmented Generation (RAG) allows us to provide the small LLM with a RAG document that supplements the model's missing information with a correct list, so it will generate a better answer.
 
 Click on the "New Chat" icon to clear the context.  Then download a small text file with the correct list of IBM CEOs to your Downloads folder:
 

docs/lab-7/README.md

@@ -236,8 +236,7 @@ def write_email(m: mellea.MelleaSession, name: str, notes: str) -> str:
         return str(email_candidate.result)
     else:
         return email_candidate.sample_generations[0].value
-
-
+        
 m = mellea.start_session()
 print(
     write_email(
@@ -255,6 +254,7 @@ We create 3 requirements:
 - First requirement (r1) will be validated by LLM-as-a-judge on the output of the instruction. This is the default behavior.
 - Second requirement (r2) uses a function that takes the output of a sampling step and returns a boolean value indicating successful or unsuccessful validation. While the validation_fn parameter requires to run validation on the full session context, Mellea provides a wrapper for simpler validation functions (simple_validate(fn: Callable[[str], bool])) that take the output string and return a boolean as seen in this case.
 - Third requirement is a check(). Checks are only used for validation, not for generation. Checks aim to avoid the "do not think about B" effect that often primes models (and humans) to do the opposite and "think" about B.
+- We also demonstrate in the m = mellea.start_session() how you can specify a different Ollama model, in case you want to try something other than Mellea's ibm/granite4:micro default.
 
 Run this in your local instance, and you'll see it working, and ideally no purple elephants! :)