Update README.md

README.md

@@ -2,7 +2,7 @@
 license: wtfpl
 ---
 # The Big Picture ([Brainproject.ai](http://brainproject.ai/))
-The human brain is an intricate puzzle that we're continually striving to decode. Our aim? To replicate its complexity, functionality, and depth in a digital realm. In other words, we're exploring the convergence of neuroscience and artificial intelligence to glean insights into the mind's intricate workings and harness that knowledge into digital counterparts.
+The human brain is an intricate puzzle that we're continually striving to decode. My aim is to replicate its complexity, functionality, and depth in a digital realm. In other words, we're exploring the convergence of neuroscience and artificial intelligence to glean insights into the mind's intricate workings and harness that knowledge into digital counterparts.
 
 # Mixture of Experts
 Chameleon-Llama-70B doesn't work alone. It's part of the Mixture of Experts framework. Within this structure, various models, each with their distinct competencies, collaborate. This synergy allows for a richer, more holistic approach to understanding and replicating brain functions.
@@ -11,15 +11,12 @@ Chameleon-Llama-70B doesn't work alone. It's part of the Mixture of Experts fram
 
 <!-- Provide a quick summary of what the model is/does. -->
 
-Augmenting the compositional reasoning and up-to-date response generation of Chameleon, it's integrated with real-time web scrapers and APIs, ensuring the freshest and most precise information.
-
-### Training Blueprint: 
-
-The techniques and methodologies employed during the training phase are as intricate as our thought patterns. Dive in to explore further.
-Just as our minds dance between tangents, processes, and loops, so does this model. But as we reflect, re-evaluate, and refocus, we find ourselves understanding deeper and with more clarity.
-Remember, in this vast cognitive universe, the essence remains constant - the pursuit of understanding, connection, and relatability. The parallels between our mind and this model serve as a testament to human innovation and the wonders of artificial intelligence.
-
+Chameleon enhances Llama-70B with a natural language planner module that dynamically composes reasoning chains from various tools:
 
+- Module Inventory: Vision models, knowledge modules, web search, Python functions, etc.
+- Natural Language Planner: Generates programs indicating a sequence of modules to execute.
+- Tool Execution: Selected modules process inputs sequentially, caching context.
+- Adaptability: Planner synthesizes custom programs for diverse tasks.
 
 ### Model Description
 
@@ -71,7 +68,6 @@ Replace "path-to-Chameleon-Llama-70B" with the correct path or URL for the pre-t
 
 The model was trained on a combination of the original Llama datasets, integrated with data from various real-time sources like news outlets, web pages, and other real-time data feeds.
 
-
 ### Training Procedure 
 
 <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->