Update README.md
Browse files
README.md
CHANGED
@@ -12,11 +12,11 @@ tags:
|
|
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 |
-
|
16 |
-
tinyllama
|
17 |
-
zyte
|
18 |
-
palmer
|
19 |
-
qwen
|
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-003 follows the same philosophy as palmer-002.5 to become a more powerful model with more data instead of less.
|
|
|
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 |
+
Model MMLU ARC-C OBQA HellaSwag PIQA Winogrande Average Params
|
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-003 follows the same philosophy as palmer-002.5 to become a more powerful model with more data instead of less.
|