Text Generation
Transformers
English
Inference Endpoints
TheBloke commited on
Commit
66fafe4
1 Parent(s): 8aa1f0f

Updating model files

Browse files
Files changed (1) hide show
  1. README.md +27 -4
README.md CHANGED
@@ -9,6 +9,17 @@ library_name: transformers
9
  pipeline_tag: text-generation
10
  license: other
11
  ---
 
 
 
 
 
 
 
 
 
 
 
12
 
13
  # Wizard Mega 13B GGML
14
 
@@ -57,6 +68,18 @@ Further instructions here: [text-generation-webui/docs/llama.cpp-models.md](http
57
 
58
  Note: at this time text-generation-webui may not support the new May 19th llama.cpp quantisation methods for q4_0, q4_1 and q8_0 files.
59
 
 
 
 
 
 
 
 
 
 
 
 
 
60
  # Original Wizard Mega 13B model card
61
 
62
  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.
@@ -74,7 +97,7 @@ Wizard Mega was built with [Axolotl](https://github.com/OpenAccess-AI-Collective
74
  ````
75
  ### Instruction: write Python code that returns the first n numbers of the Fibonacci sequence using memoization.
76
 
77
- ### Assistant:
78
  ```python
79
  def fib(n):
80
  if n < 2:
@@ -87,17 +110,17 @@ def fib(n):
87
  cache[i] = a
88
  a, b = b, a + b
89
  return cache[n]
90
-
91
  def first_n(n):
92
  fib_list = [fib(i) for i in range(n+1)]
93
  return fib_list[:n]
94
  ```
95
- 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.
96
  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.
97
  ````
98
 
99
  ```
100
- ### Instruction: Finish the joke, a mechanic and a car salesman walk into a bar...
101
 
102
  ### 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
103
  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."
 
9
  pipeline_tag: text-generation
10
  license: other
11
  ---
12
+ <div style="width: 100%;">
13
+ <img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
14
+ </div>
15
+ <div style="display: flex; justify-content: space-between; width: 100%;">
16
+ <div style="display: flex; flex-direction: column; align-items: flex-start;">
17
+ <p><a href="https://discord.gg/UBgz4VXf">Chat & support: my new Discord server</a></p>
18
+ </div>
19
+ <div style="display: flex; flex-direction: column; align-items: flex-end;">
20
+ <p><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? Patreon coming soon!</a></p>
21
+ </div>
22
+ </div>
23
 
24
  # Wizard Mega 13B GGML
25
 
 
68
 
69
  Note: at this time text-generation-webui may not support the new May 19th llama.cpp quantisation methods for q4_0, q4_1 and q8_0 files.
70
 
71
+ ## Want to support my work?
72
+
73
+ 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.
74
+
75
+ 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.
76
+
77
+ 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.
78
+
79
+ * Patreon: coming soon! (just awaiting approval)
80
+ * Ko-Fi: https://ko-fi.com/TheBlokeAI
81
+ * Discord: https://discord.gg/UBgz4VXf
82
+
83
  # Original Wizard Mega 13B model card
84
 
85
  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.
 
97
  ````
98
  ### Instruction: write Python code that returns the first n numbers of the Fibonacci sequence using memoization.
99
 
100
+ ### Assistant:
101
  ```python
102
  def fib(n):
103
  if n < 2:
 
110
  cache[i] = a
111
  a, b = b, a + b
112
  return cache[n]
113
+
114
  def first_n(n):
115
  fib_list = [fib(i) for i in range(n+1)]
116
  return fib_list[:n]
117
  ```
118
+ 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.
119
  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.
120
  ````
121
 
122
  ```
123
+ ### Instruction: Finish the joke, a mechanic and a car salesman walk into a bar...
124
 
125
  ### 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
126
  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."