Update README.md

README.md

@@ -23,6 +23,9 @@ Why? Dunno whated to see what would happen
 
 context is maybe 16k? waiting for GGUF to upload.
 
+Chat-instruct breaks the model at the moment, not really sure why, even tho it will follow instructions.
+
+
 
 Template:
 ```
@@ -33,6 +36,13 @@ Template:
 ### Assistant:
 ```
 
+
+Settings:
+```
+Temp: 1.0
+min-p: 0.02-0.1
+```
+
 Lumosia-MoE-4x10.7 is a Mixure of Experts (MoE) made with the following models:
 * [DopeorNope/SOLARC-M-10.7B](https://huggingface.co/DopeorNope/SOLARC-M-10.7B)
 * [maywell/PiVoT-10.7B-Mistral-v0.2-RP](https://huggingface.co/maywell/PiVoT-10.7B-Mistral-v0.2-RP)
@@ -41,9 +51,64 @@ Lumosia-MoE-4x10.7 is a Mixure of Experts (MoE) made with the following models:
 
 ## Evals:
 
-
 * Pending
 
+## Examples:
+```
+Example 1:
+
+User:
+Hello lumi, what is the meaning of life
+in around 100 words.
+
+Lumosia:
+The meaning of life can vary greatly
+depending on individual beliefs,
+values, and experiences. One common
+perspective suggests that the primary
+purpose of life is to seek happiness,
+fulfillment, and personal growth
+through relationships
+accomplishments, and spiritual
+awareness. Living with integrity.
+compassion, and gratitude while
+making a positive impact on others
+and the world around us can also
+contribute to finding meaning in life
+UItimately, the meaning of life is
+subjective and unique to each
+individual, who must define it for
+themselves through exploration
+reflection, and personal choice.
+
+```
+```
+Example 2:
+
+User:
+Explain a MoE (Mixture of Experts) in
+around 100 words
+
+Lumosia:
+A MoE, short for Mixture of Experts, is
+a machine learning technique utilized
+in ensemble learning. It involves
+combining multiple specialist models
+(experts) to optimize predictive
+performance. Each expert focuses on
+a subset of the input features or data
+domains, making them specialized in
+particular areas. Through a weighting
+mechanism, like Gaussian Mixture
+Model, the predictions of experts are
+blended to produce a final result. MoE
+models demonstrate effectiveness in
+handling complex or ambiguous
+inputs where a single model might
+struggle. They are commonly used in
+natural language processing.
+computer vision, and speech synthesis.
+```
 
 ## 🧩 Configuration