Extract evaluation results from README
Browse filesThis commit adds structured evaluation results to the model card. The results are formatted using the model-index specification and will be displayed in the model card's evaluation widget.
README.md
CHANGED
|
@@ -3,12 +3,35 @@ library_name: vllm
|
|
| 3 |
inference: false
|
| 4 |
base_model:
|
| 5 |
- mistralai/Mistral-Small-3.1-24B-Base-2503
|
| 6 |
-
extra_gated_description:
|
| 7 |
-
|
| 8 |
-
our <a href="https://mistral.ai/terms/">Privacy Policy</a>.
|
| 9 |
tags:
|
| 10 |
- mistral-common
|
| 11 |
license: apache-2.0
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12 |
---
|
| 13 |
|
| 14 |
# Devstral Small 2 24B Instruct 2512
|
|
|
|
| 3 |
inference: false
|
| 4 |
base_model:
|
| 5 |
- mistralai/Mistral-Small-3.1-24B-Base-2503
|
| 6 |
+
extra_gated_description: If you want to learn more about how we process your personal
|
| 7 |
+
data, please read our <a href="https://mistral.ai/terms/">Privacy Policy</a>.
|
|
|
|
| 8 |
tags:
|
| 9 |
- mistral-common
|
| 10 |
license: apache-2.0
|
| 11 |
+
model-index:
|
| 12 |
+
- name: Devstral-Small-2-24B-Instruct-2512
|
| 13 |
+
results:
|
| 14 |
+
- task:
|
| 15 |
+
type: text-generation
|
| 16 |
+
dataset:
|
| 17 |
+
name: Benchmarks
|
| 18 |
+
type: benchmark
|
| 19 |
+
metrics:
|
| 20 |
+
- name: Size (B Parameters)
|
| 21 |
+
type: size_(b_parameters)
|
| 22 |
+
value: 24.0
|
| 23 |
+
- name: SWE Bench Verified
|
| 24 |
+
type: swe_bench_verified
|
| 25 |
+
value: 68.0
|
| 26 |
+
- name: SWE Bench Multilingual
|
| 27 |
+
type: swe_bench_multilingual
|
| 28 |
+
value: 55.7
|
| 29 |
+
- name: Terminal Bench 2
|
| 30 |
+
type: terminal_bench_2
|
| 31 |
+
value: 22.5
|
| 32 |
+
source:
|
| 33 |
+
name: Model README
|
| 34 |
+
url: https://huggingface.co/mistralai/Devstral-Small-2-24B-Instruct-2512
|
| 35 |
---
|
| 36 |
|
| 37 |
# Devstral Small 2 24B Instruct 2512
|