Update README.md
Browse files
README.md
CHANGED
|
@@ -5,17 +5,7 @@ license: apache-2.0
|
|
| 5 |
# Model Card for Mathstral-7B-v0.1
|
| 6 |
|
| 7 |
<Fill-me for Mathstral-7B-v0.1>
|
| 8 |
-
|
| 9 |
-
## Evaluation
|
| 10 |
-
We evaluate Mathstral 7B and models of the similar size on industry-standard benchmarks.
|
| 11 |
-
| Benchmarks | MATH | GSM8K (8-shot) | Odyssey Math | GRE Math | AMC 2023 | AIME 2024
|
| 12 |
-
| :--- | :---: | :---: | :---: | :---: | :---: | :---: |
|
| 13 |
-
| Mathstral 7B | **56.6** | 77.1 | **37.2** | 56.9 | **42.4** | **2/30** |
|
| 14 |
-
| DeepSeek Math 7B | 44.4 | **80.6** | 27.6 | 44.6 | 28.0 | 0/30 |
|
| 15 |
-
| Llama3 8B | 28.4 | 75.4 | 24.0 | 26.2 | 34.4 | 0/30 |
|
| 16 |
-
| GLM4 9B | 50.2 | 48.8 | 18.9 | 46.2 | 36.0 | 1/30 |
|
| 17 |
-
| QWen2 7B | **56.8** | 32.7 | 24.8 | **58.5** | 35.2 | **2/30** |
|
| 18 |
-
| Gemma2 9B | 48.3 | 69.5 | 18.6 | 52.3 | 31.2 | 1/30 |
|
| 19 |
|
| 20 |
## Installation
|
| 21 |
|
|
@@ -47,9 +37,19 @@ After installing `mistral_inference`, a `mistral-demo` CLI command should be ava
|
|
| 47 |
mistral-chat $HOME/mistral_models/mathstral-7B-v0.1 --instruct
|
| 48 |
```
|
| 49 |
|
| 50 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 51 |
|
| 52 |
|
| 53 |
## The Mistral AI Team
|
| 54 |
|
| 55 |
-
Albert Jiang, Alexandre Sablayrolles, Alexis Tacnet, Antoine Roux, Arthur Mensch, Audrey Herblin-Stoop, Baptiste Bout, Baudouin de Monicault, Blanche Savary,
|
|
|
|
| 5 |
# Model Card for Mathstral-7B-v0.1
|
| 6 |
|
| 7 |
<Fill-me for Mathstral-7B-v0.1>
|
| 8 |
+
Mathstral 7B is a model specializing in mathematical and scientific tasks, based on Mistral 7B.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 9 |
|
| 10 |
## Installation
|
| 11 |
|
|
|
|
| 37 |
mistral-chat $HOME/mistral_models/mathstral-7B-v0.1 --instruct
|
| 38 |
```
|
| 39 |
|
| 40 |
+
|
| 41 |
+
## Evaluation
|
| 42 |
+
We evaluate Mathstral 7B and open-weight models of the similar size on industry-standard benchmarks.
|
| 43 |
+
| Benchmarks | MATH | GSM8K (8-shot) | Odyssey Math | GRE Math | AMC 2023 | AIME 2024
|
| 44 |
+
| :--- | :---: | :---: | :---: | :---: | :---: | :---: |
|
| 45 |
+
| Mathstral 7B | **56.6** | 77.1 | **37.2** | 56.9 | **42.4** | **2/30** |
|
| 46 |
+
| DeepSeek Math 7B | 44.4 | **80.6** | 27.6 | 44.6 | 28.0 | 0/30 |
|
| 47 |
+
| Llama3 8B | 28.4 | 75.4 | 24.0 | 26.2 | 34.4 | 0/30 |
|
| 48 |
+
| GLM4 9B | 50.2 | 48.8 | 18.9 | 46.2 | 36.0 | 1/30 |
|
| 49 |
+
| QWen2 7B | **56.8** | 32.7 | 24.8 | **58.5** | 35.2 | **2/30** |
|
| 50 |
+
| Gemma2 9B | 48.3 | 69.5 | 18.6 | 52.3 | 31.2 | 1/30 |
|
| 51 |
|
| 52 |
|
| 53 |
## The Mistral AI Team
|
| 54 |
|
| 55 |
+
Albert Jiang, Alexandre Sablayrolles, Alexis Tacnet, Alok Kothari, Antoine Roux, Arthur Mensch, Audrey Herblin-Stoop, Augustin Garreau, Austin Birky, Bam4d, Baptiste Bout, Baudouin de Monicault, Blanche Savary, Carole Rambaud, Caroline Feldman, Devendra Singh Chaplot, Diego de las Casas, Eleonore Arcelin, Emma Bou Hanna, Etienne Metzger, Gaspard Blanchet, Gianna Lengyel, Guillaume Bour, Guillaume Lample, Harizo Rajaona, Henri Roussez, Hichem Sattouf, Ian Mack, Jean-Malo Delignon, Jessica Chudnovsky, Justus Murke, Kartik Khandelwal, Lawrence Stewart, Louis Martin, Louis Ternon, Lucile Saulnier, Lélio Renard Lavaud, Margaret Jennings, Marie Pellat, Marie Torelli, Marie-Anne Lachaux, Marjorie Janiewicz, Mickaël Seznec, Nicolas Schuhl, Niklas Muhs, Olivier de Garrigues, Patrick von Platen, Paul Jacob, Pauline Buche, Pavan Kumar Reddy, Perry Savas, Pierre Stock, Romain Sauvestre, Sagar Vaze, Sandeep Subramanian, Saurabh Garg, Sophia Yang, Szymon Antoniak, Teven Le Scao, Thibault Schueller, Thibaut Lavril, Thomas Wang, Théophile Gervet, Timothée Lacroix, Valera Nemychnikova, Wendy Shang, William El Sayed, William Marshall
|