TroyDoesAI/Mermaid-Llama-3-7B-Pruned

Update README.md

Removed Layer 11. this layer shared responsibility with layer 25

Update README.md

Update README.md

https://www.linkedin.com/posts/troyandrewschultz_i-just-wanna-thank-eric-hartford-fernando-activity-7187654884362457089-tKOt?utm_source=share&utm_medium=member_desktop

Might have did something cool, its a secret. Lets see if it improved because I think so.

Rename Mermaid_ShowCase/Mermaid_ShowCase_python_RtdBsaz8gy.gif to Mermaid_ShowCase/python_RtdBsaz8gy.gif

Rename Mermaid_ShowCase/Mermaid_ShowCase_MermaidLlama.webp to Mermaid_ShowCase/MermaidLlama.webp

Rename Mermaid_ShowCase/Mermaid_ShowCase_3_Open_The_Program_VLLM_Program_With_Full_Precision_Mermaid-Llama-8B-Running_to_evaluate_flow_map.gif to Mermaid_ShowCase/3_Open_The_Program_VLLM_Program_With_Full_Precision_Mermaid-Llama-8B-Running_to_evaluate_flow_map.gif

Showcase Example of how to use my model.

Update README.md

Found 4 Bunk Layers, Removed 3 without training yields a perfectly send-able Model with less requirements and more speed.

29 Layers: Removed from the 32 layer Foundation Model with no loss of output without fine tuning.

initial commit