Updating model files

README.md

@@ -9,6 +9,17 @@ library_name: transformers
 pipeline_tag: text-generation
 license: other
 ---
+<div style="width: 100%;">
+    <img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
+</div>
+<div style="display: flex; justify-content: space-between; width: 100%;">
+    <div style="display: flex; flex-direction: column; align-items: flex-start;">
+        <p><a href="https://discord.gg/UBgz4VXf">Chat & support: my new Discord server</a></p>
+    </div>
+    <div style="display: flex; flex-direction: column; align-items: flex-end;">
+        <p><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? Patreon coming soon!</a></p>
+    </div>
+</div>
 
 # Wizard Mega 13B GPTQ
 
@@ -56,6 +67,17 @@ It was created without `--act-order` to ensure compatibility with all UIs out th
     ```
 
 
+## Want to support my work?
+
+I've had a lot of people ask if they can contribute. I love providing models and helping people, but it is starting to rack up pretty big cloud computing bills.
+
+So if you're able and willing to contribute, it'd be most gratefully received and will help me to keep providing models, and work on various AI projects.
+
+Donaters will get priority support on any and all AI/LLM/model questions, and I'll gladly quantise any model you'd like to try.
+
+* Patreon: coming soon! (just awaiting approval)
+* Ko-Fi: https://ko-fi.com/TheBlokeAI
+* Discord: https://discord.gg/UBgz4VXf
 # Original Wizard Mega 13B model card
 
 Wizard Mega is a Llama 13B model fine-tuned on the [ShareGPT](https://huggingface.co/datasets/anon8231489123/ShareGPT_Vicuna_unfiltered), [WizardLM](https://huggingface.co/datasets/ehartford/WizardLM_alpaca_evol_instruct_70k_unfiltered), and [Wizard-Vicuna](https://huggingface.co/datasets/ehartford/wizard_vicuna_70k_unfiltered) datasets. These particular datasets have all been filtered to remove responses where the model responds with "As an AI language model...", etc or when the model refuses to respond.
@@ -73,7 +95,7 @@ Wizard Mega was built with [Axolotl](https://github.com/OpenAccess-AI-Collective
 ````
 ### Instruction: write Python code that returns the first n numbers of the Fibonacci sequence using memoization.
 
-### Assistant: 
+### Assistant:
 ```python
 def fib(n):
     if n < 2:
@@ -86,17 +108,17 @@ def fib(n):
             cache[i] = a
             a, b = b, a + b
         return cache[n]
-    
+
 def first_n(n):
     fib_list = [fib(i) for i in range(n+1)]
     return fib_list[:n]
 ```
-This function uses memoization to store the values of previous Fibonacci numbers in a cache. This way, if the same number is requested again, it can be returned immediately without recalculating it. 
+This function uses memoization to store the values of previous Fibonacci numbers in a cache. This way, if the same number is requested again, it can be returned immediately without recalculating it.
 The `first_n` function takes an integer `n` as input, and calculates the first n numbers of the Fibonacci sequence using memoization. It returns a list of those numbers.
 ````
 
 ```
-### Instruction: Finish the joke, a mechanic and a car salesman walk into a bar...  
+### Instruction: Finish the joke, a mechanic and a car salesman walk into a bar...
 
 ### Assistant:  ...and the bartender says "Hey guys, what can I get for you?" The mechanic replies, "I'll have a beer, but make it a quick one. I have to fix this guy's car before he finds out I
  fiddled with his brakes." The salesman quips, "And I'll have a martini, shaken not stirred. After all, I have to sell this guy a car that doesn't break down on him within the first year of ownership."