Update README.md
Browse files
README.md
CHANGED
|
@@ -14,13 +14,11 @@ Code: [https://github.com/TIGER-AI-Lab/MAmmoTH2](https://github.com/TIGER-AI-Lab
|
|
| 14 |
|
| 15 |
## Introduction
|
| 16 |
Introducing 🦣 MAmmoTH2, a game-changer in improving the reasoning abilities of large language models (LLMs) through innovative instruction tuning. By efficiently harvesting 10 million instruction-response pairs from the pre-training web corpus, we've developed MAmmoTH2 models that significantly boost performance on reasoning benchmarks. For instance, MAmmoTH2-7B (Mistral) sees its performance soar from 11% to 34% on MATH and from 36% to 67% on GSM8K, all without training on any domain-specific data. Further training on public instruction tuning datasets yields MAmmoTH2-Plus, setting new standards in reasoning and chatbot benchmarks. Our work presents a cost-effective approach to acquiring large-scale, high-quality instruction data, offering a fresh perspective on enhancing LLM reasoning abilities.
|
| 17 |
-
|
|
| 18 |
-
|
| 19 |
-
| 7B | Mistral
|
| 20 |
-
| 8B | Llama-3
|
| 21 |
-
| 8x7B | Mixtral
|
| 22 |
-
|
| 23 |
-
|
| 24 |
## Training Data
|
| 25 |
(WEBINSTRUCT) Coming soon...
|
| 26 |
|
|
|
|
| 14 |
|
| 15 |
## Introduction
|
| 16 |
Introducing 🦣 MAmmoTH2, a game-changer in improving the reasoning abilities of large language models (LLMs) through innovative instruction tuning. By efficiently harvesting 10 million instruction-response pairs from the pre-training web corpus, we've developed MAmmoTH2 models that significantly boost performance on reasoning benchmarks. For instance, MAmmoTH2-7B (Mistral) sees its performance soar from 11% to 34% on MATH and from 36% to 67% on GSM8K, all without training on any domain-specific data. Further training on public instruction tuning datasets yields MAmmoTH2-Plus, setting new standards in reasoning and chatbot benchmarks. Our work presents a cost-effective approach to acquiring large-scale, high-quality instruction data, offering a fresh perspective on enhancing LLM reasoning abilities.
|
| 17 |
+
| | **Base Model** | **MAmmoTH2** | **MAmmoTH2-Plus** |
|
| 18 |
+
|------|------------------|-------------------------------------------------------------------|------------------------------------------------------------------|
|
| 19 |
+
| 7B | Mistral | 🦣 [MAmmoTH2-7B](https://huggingface.co/TIGER-Lab/MAmmoTH2-7B) | 🦣 [MAmmoTH2-7B-Plus](https://huggingface.co/TIGER-Lab/MAmmoTH2-7B-Plus) |
|
| 20 |
+
| 8B | Llama-3 | 🦣 [MAmmoTH2-8B](https://huggingface.co/TIGER-Lab/MAmmoTH2-8B) | 🦣 [MAmmoTH2-8B-Plus](https://huggingface.co/TIGER-Lab/MAmmoTH2-8B-Plus) |
|
| 21 |
+
| 8x7B | Mixtral | 🦣 [MAmmoTH2-8x7B](https://huggingface.co/TIGER-Lab/MAmmoTH2-8x7B) | 🦣 [MAmmoTH2-8x7B-Plus](https://huggingface.co/TIGER-Lab/MAmmoTH2-8x7B-Plus) |
|
|
|
|
|
|
|
| 22 |
## Training Data
|
| 23 |
(WEBINSTRUCT) Coming soon...
|
| 24 |
|