Update README.md

README.md

@@ -2,110 +2,59 @@
 license: cc-by-4.0
 ---
 
-# Mermaid-Llama-3-8B:
+# Mermaid-Llama-3-8B
 
----
-New Prompt Template.
-"instruction,input,output": "Mermaid-Generator-Request: %instruction%\n\n### Input:\n%input%\n\n### Mermaid:\n%output%"
-
----
+Introducing Mermaid-LLama-3-8B, a robust language model designed for Python code understanding and crafting captivating story flow maps. With 8.3 billion parameters, this model excels in programming, mathematical reasoning, and general language processing.
 
----
-license: apache-2.0
----
-
-**MermaidLLama: Unleashing the Power of Llama 3 - 8 Billion Parameters**
-
-Introducing Mermaid-LLama-3-8B, a robust language model designed for Python code understanding and crafting captivating story flow maps. 
-With a petite 8.3 billion parameters, this model builds on the success of LLama 3's ability to maintain versatility in programming, mathematical reasoning, 
-and general language processing.
 ![MermaidLlama GIF](Mermaid_ShowCase/MermaidLlama.webp)
 
-
-**Key Features:**
+## Key Features
 
 1. **Code Understanding:**
    - Masters Python intricacies with finesse.
    - Generates clear and accurate Mermaid Diagram Flow Charts.
-   - Ideal for developers seeking visual representations of their code's logic to better solve problems.
+   - Ideal for developers seeking visual representations of their code logic.
 
 2. **Storytelling Capabilities:**
    - Converts narrative inputs into captivating Mermaid Diagrams.
    - Maps character interactions, plot developments, and narrative arcs.
 
 3. **Unmatched Performance:**
-   - Surpasses GPT-4 in generating well-organized and detailed Mermaid Diagrams, its not even a competition Mermaid's do it better.🧜‍♀️
+   - Surpasses GPT-4 in generating well-organized Mermaid Diagrams.
 
 4. **Training Insights:**
-   - Trained on a diverse dataset, including 800 unique, hand curated Mermaid Graph examples utilizing 478 complete python programs (hand tested each program) rather than code snippets.
-   - Exhibits emergent properties in story-to-flow map translations and step by step instruction flow maps to which it was not trained for.
-   - Adaptable and willing to be Prompt Engineered for your specific utilization.
-
-**Collaboration:**
+   - Trained on a diverse dataset, including 800 unique, hand-curated Mermaid Graph examples utilizing 478 complete Python programs.
+   - Exhibits emergent properties in story-to-flow map translations and step-by-step instruction flow maps.
 
-Mermaid is open to collaboration to further enhance its capabilities. 
+## Collaboration
 
-If you're interested in contributing or collaborating, feel free to reach out to troydoesai@gmail.com. 
-Your expertise could play a pivotal role in refining Mermaid.
+Interested in enhancing Mermaid's capabilities? Contact troydoesai@gmail.com for collaboration opportunities.
 
-**Example Use Cases:**
+## Example Use Cases
+- **Retrieval-Augmented Generation (RAG):** Utilize Mermaid-LLama-3-8B to create condensed knowledge graphs. This model excels in generating flow diagrams that enhance the retrieval process. These knowledge graphs are stored in a vector database, which allows for quick and efficient retrieval of contextually relevant information. When a query is received, the system retrieves a pertinent knowledge graph, appending it as context to the model. This enriched context enables Mermaid-LLama-3-8B to deliver more accurate and nuanced responses. This approach is particularly beneficial in applications requiring deep, context-aware interactions, such as sophisticated Q&A systems, dynamic data analysis, and complex decision-making tasks.
+- **Code Documentation:** Automatic visual flow charts from Python code.
+- **Storyboarding:** Visually appealing diagrams for storytelling.
+- **Project Planning:** Visual project flow maps for effective team communication.
+- **Learning Python:** Helps students visually understand Python code structures.
+- **Game Design:** Visualizing game storylines for coherent narrative structure.
 
-- **Code Documentation:**
-  Developers can use Mermaid to automatically generate visual flow charts from their Python code, aiding in documentation and code understanding.
-
-- **Storyboarding:**
-  Storytellers and writers can input their narrative and receive visually appealing Mermaid Diagrams, offering a structured overview of character interactions and plot progression.
-
-- **Project Planning:**
-  Project managers can create visual project flow maps, facilitating effective communication and planning among team members.
-
-- **Learning Python:**
-  Students and beginners can visually understand Python code structures, enhancing their learning experience.
-
-- **Game Design:**
-  Game developers can utilize Mermaid for visualizing game storylines, ensuring a coherent narrative structure and character development.
-
-**Proof of Concept:**
-
-Mermaid proves that innovation thrives in compact packages, delivering exceptional performance across diverse applications. 
+## Proof of Concept
 
 Stay tuned for the release of the VSCode Extension that displays the Live Flow Map every time a user stops typing for more than 10 seconds.
 
-For best results, use full precision with one of the three different instruction types:
-
-Exciting times ahead as we delve into the MermaidLLama revolution! 🚀
-
-# Training:
-LoRA Rank
-- 2048
+## Training Specifications
 
-LoRA Alpha
-- 4096
+- **LoRA Rank:** 2048
+- **LoRA Alpha:** 4096
+- **Batch Size:** 1
+- **Micro Batch Size:** 1
+- **Cutoff Length:** 4096
+- **Save every n steps:** 1000
+- **Epochs:** 3
+- **Learning Rate:** 1e-6
+- **LR Scheduler:** Cosine
 
-Batch Size
-- 1
-
-Micro Batch Size
-- 1
-
-Cutoff Length
-- 4096
-
-Save every n steps
-- 1000
-
-Epochs
-- 3
-
-Learning Rate
-- 1e-6
-
-LR Scheduler
-- cosine
-
-
-Target Modules
-▼
+**Target Modules:**
 - Enable q_proj
 - Enable v_proj
 - Enable k_proj
@@ -114,25 +63,27 @@ Target Modules
 - Enable down_proj
 - Enable up_proj
 
-Example of what you would send to my model to get a flow graph that ends with ``` every time.
-
-https://drive.google.com/file/d/1z1QM9KZdg_VeH-tGwIY-cyxDas0ucnKc/view?usp=sharing
----
+## Getting Started
 
 Start by downloading one of my models.
+
 ![0 TroyDoesAI GIF](Mermaid_ShowCase/0_TroyDoesAI.gif)
 
 Load the model.
+
 ![1 Load Model in 4-bit Show Example Use GIF](Mermaid_ShowCase/1_LoadModel_in_4bit_Show_Example_Use.gif)
 
-Inference the model using my prompt template replacing your instruction and input to generate a Mermaid code block,
-that can be viewed in the Mermaid Live Editor or Using the Mermaid CLI tool directly creating an image of the flow map.
-More on the cli tool here: https://github.com/mermaid-js/mermaid-cli
+Use my prompt template to generate a Mermaid code block, which can be viewed in the Mermaid Live Editor or using the Mermaid CLI tool.
 
 ![2 Loaded Model in Full Precision 16-bit Show Inference and Mermaid Live Editor GIF](Mermaid_ShowCase/2_Loaded_Model_in_Full_Precision_16bit_Show_Inference_and_Mermaid_Live_editor.gif)
 
-Here We Open the additional VLLM GUI Program I wrote for the example, while still running the Mermaid-Llama-8B to compare the flow diagram to the actual program.
+Here we open the VLLM GUI Program while still running in Vram the Mermaid-Llama-8B to compare the flow diagram to the actual program and show the lightweight capabilites of small models on consumer hardware.
+
 ![3 Open The Program VLLM Program With Full Precision Mermaid-Llama-8B Running to Evaluate Flow Map GIF](Mermaid_ShowCase/3_Open_The_Program_VLLM_Program_With_Full_Precision_Mermaid-Llama-8B-Running_to_evaluate_flow_map.gif)
 
-# More on my cute VLLM Class and inference GUI.
+## More on my VLLM Class and inference GUI
+
 ![Python RtdBsaz8gy GIF](Mermaid_ShowCase/python_RtdBsaz8gy.gif)
+---
+
+Note: This model should be treated as an Auto-Complete Model, Do not try talking to it in chat you are gonna get garbage, those layers have been pruned and replaced, that is all you will hear of my secret sauce on training on small < 1000 entry datasets.