appvoid commited on
Commit
4836fa5
·
verified ·
1 Parent(s): 4011f8b

Create README.md

Browse files
Files changed (1) hide show
  1. README.md +41 -0
README.md ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ language:
4
+ - en
5
+ - es
6
+ - fr
7
+ tags:
8
+ - merge
9
+ ---
10
+ ![palmer-003 logo](https://huggingface.co/appvoid/palmer-002.5/resolve/main/003.png)
11
+
12
+ Creative writing has never been so accesible, palmer goes beyond what it was thought about small language models. This model is a "MErging of Experts" (MEoE) using an internal model `palmer-003` as base, biased as an assistant, using dpo technique, without using any prompts—as a result of these efforts—palmer is better than most 1b language models on most benchmarks, despite being sometimes 40% smaller than its counterparts.
13
+
14
+ ```
15
+ MMLU ARC-C OBQA HellaSwag PIQA Winogrande Average Parameters
16
+ tinyllama | 0.2577 | 0.3029 | 0.3600 | 0.5935 | 0.7329 | 0.5959 | 0.4738 | 1.1B |
17
+ zyte | 0.2397 | 0.3353 | 0.3700 | 0.6086 | 0.7541 | 0.5998 | 0.4845 | 1.1B |
18
+ palmer | 0.2523 | 0.3439 | 0.3740 | 0.6208 | 0.7524 | 0.6590 | 0.5004 | 1.1B |
19
+ qwen | 0.4536 | 0.3490 | 0.3320 | 0.5876 | 0.7307 | 0.5896 | 0.5070 | 1.8B |
20
+ ```
21
+
22
+ This work constitutes, given its compactness, an advancement towards SMLs, easily empowering edge devices such as mobile phones, raspberry pis and automated software/robots. Aditionally, palmer-002.5 deviates its main philosophy from palmer-family to become a more powerful model with more data instead of less.
23
+
24
+ ```
25
+ prompt: Reality is but
26
+ output: a dream,
27
+ And the dreams we make are our reality.
28
+
29
+ The world is a canvas, painted by our minds,
30
+ And we can make it a masterpiece.
31
+
32
+ So let us create, let us dream,
33
+ And let our imagination run wild.
34
+
35
+ For in our imagination lies our power,
36
+ To create a world that is truly our own.
37
+ ```
38
+
39
+ You can support me [through kofi](https://ko-fi.com/appvoid)
40
+
41
+ Note that since this model uses a transformer architecture as any popular language model, its output sometimes contains hallucinations (make mistakes or false statements), and as such, it must be used with caution on sensitive scenarios.