Update README.md
Browse files
README.md
CHANGED
|
@@ -9,8 +9,24 @@ tags:
|
|
| 9 |
- smoltalk
|
| 10 |
datasets:
|
| 11 |
- HuggingFaceTB/smoltalk
|
|
|
|
|
|
|
| 12 |
language:
|
| 13 |
- en
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 14 |
---
|
| 15 |
|
| 16 |
# Model Card for DeepSeek-R1-SmolTalk
|
|
|
|
| 9 |
- smoltalk
|
| 10 |
datasets:
|
| 11 |
- HuggingFaceTB/smoltalk
|
| 12 |
+
metrics:
|
| 13 |
+
- MMLU
|
| 14 |
language:
|
| 15 |
- en
|
| 16 |
+
|
| 17 |
+
model-index:
|
| 18 |
+
- name: DeepSeek-R1-Distill-Qwen-1.5B-finetuned-smoltalk-everyday-conversations
|
| 19 |
+
results:
|
| 20 |
+
- task:
|
| 21 |
+
name: Text Generation
|
| 22 |
+
type: text-generation
|
| 23 |
+
dataset:
|
| 24 |
+
name: HuggingFaceTB/smoltalk
|
| 25 |
+
type: HuggingFaceTB/smoltalk
|
| 26 |
+
metrics:
|
| 27 |
+
- name: MMLU (0-shot)
|
| 28 |
+
type: MMLU-PEM (0-shot)
|
| 29 |
+
value: 0.2749
|
| 30 |
---
|
| 31 |
|
| 32 |
# Model Card for DeepSeek-R1-SmolTalk
|