Update README.md
Browse files
README.md
CHANGED
|
@@ -19,20 +19,22 @@ tags:
|
|
| 19 |
**The V2 version performs better in multiple benchmarks than the V1 version, and even outmatches both 1211 and V1 in mathematics: https://huggingface.co/MultivexAI/Gladiator-Mini-Exp-1221-3B-Instruct**
|
| 20 |
|
| 21 |
**Examples:**
|
| 22 |
-
|
| 23 |
**MATH**
|
| 24 |
**1211: 13.44 %**
|
| 25 |
**V1: 13.07 %**
|
| 26 |
**V2: 13.75 %**
|
| 27 |
-
|
|
|
|
| 28 |
**IFEval**
|
| 29 |
**V1: 60.79 %**
|
| 30 |
**V2: 62.15 %**
|
| 31 |
-
|
|
|
|
| 32 |
**BBH**
|
| 33 |
**V1: 20.40 %**
|
| 34 |
**V2: 20.65 %**
|
| 35 |
-
|
| 36 |
# Gladiator-Mini-exp-1221-Instruct
|
| 37 |
|
| 38 |
**Gladiator-Mini-exp-1221** is a 3-billion parameter language model focused on **complex reasoning**. Built upon the foundation of [meta-llama/Llama-3.2-3B-Instruct](https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct), this experimental model is designed to explore what's achievable with smaller models in analytical thinking. It's all about pushing boundaries and learning what's possible in resource-efficient AI. We believe small models represent the future of open source language models, making AI more accessible and adaptable for a wider range of users and applications.
|
|
|
|
| 19 |
**The V2 version performs better in multiple benchmarks than the V1 version, and even outmatches both 1211 and V1 in mathematics: https://huggingface.co/MultivexAI/Gladiator-Mini-Exp-1221-3B-Instruct**
|
| 20 |
|
| 21 |
**Examples:**
|
| 22 |
+
----------------
|
| 23 |
**MATH**
|
| 24 |
**1211: 13.44 %**
|
| 25 |
**V1: 13.07 %**
|
| 26 |
**V2: 13.75 %**
|
| 27 |
+
----------------
|
| 28 |
+
----------------
|
| 29 |
**IFEval**
|
| 30 |
**V1: 60.79 %**
|
| 31 |
**V2: 62.15 %**
|
| 32 |
+
----------------
|
| 33 |
+
----------------
|
| 34 |
**BBH**
|
| 35 |
**V1: 20.40 %**
|
| 36 |
**V2: 20.65 %**
|
| 37 |
+
----------------
|
| 38 |
# Gladiator-Mini-exp-1221-Instruct
|
| 39 |
|
| 40 |
**Gladiator-Mini-exp-1221** is a 3-billion parameter language model focused on **complex reasoning**. Built upon the foundation of [meta-llama/Llama-3.2-3B-Instruct](https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct), this experimental model is designed to explore what's achievable with smaller models in analytical thinking. It's all about pushing boundaries and learning what's possible in resource-efficient AI. We believe small models represent the future of open source language models, making AI more accessible and adaptable for a wider range of users and applications.
|