hawei_LinkedIn
commited on
Commit
·
673afc5
1
Parent(s):
8327fc3
correct meta data of base model
Browse files
README.md
CHANGED
|
@@ -10,7 +10,7 @@ datasets:
|
|
| 10 |
language:
|
| 11 |
- zh
|
| 12 |
base_model:
|
| 13 |
-
- meta-llama/Llama-3.1-8B
|
| 14 |
model-index:
|
| 15 |
- name: Control-LLM-Llama3.1-8B-SynE-Hybrid
|
| 16 |
results:
|
|
@@ -105,4 +105,3 @@ The table below summarizes evaluation results across Chinese tasks and original
|
|
| 105 |
- **MLUP**: MMLU Pro
|
| 106 |
- **O-Avg**: Original Capability - Size Weighted Average across BBH, MLU, and MLUP
|
| 107 |
- **Overall**: Combined average across all tasks
|
| 108 |
-
|
|
|
|
| 10 |
language:
|
| 11 |
- zh
|
| 12 |
base_model:
|
| 13 |
+
- meta-llama/Llama-3.1-8B
|
| 14 |
model-index:
|
| 15 |
- name: Control-LLM-Llama3.1-8B-SynE-Hybrid
|
| 16 |
results:
|
|
|
|
| 105 |
- **MLUP**: MMLU Pro
|
| 106 |
- **O-Avg**: Original Capability - Size Weighted Average across BBH, MLU, and MLUP
|
| 107 |
- **Overall**: Combined average across all tasks
|
|
|