Add library name, pipeline tag
#1
by
nielsr
HF staff
- opened
README.md
CHANGED
|
@@ -73,7 +73,10 @@ model-index:
|
|
| 73 |
value: 0.4093251329787234
|
| 74 |
stderr: 0.004482884901882547
|
| 75 |
verified: false
|
|
|
|
|
|
|
| 76 |
---
|
|
|
|
| 77 |
# Control-LLM-Llama3.1-8B-Math16
|
| 78 |
This is a fine-tuned model of Llama-3.1-8B-Instruct for mathematical tasks on OpenCoder SFT dataset.
|
| 79 |
|
|
@@ -114,4 +117,4 @@ The table below summarizes evaluation results across coding tasks and original c
|
|
| 114 |
- **MLU**: MMLU (Massive Multitask Language Understanding)
|
| 115 |
- **MLUP**: MMLU Pro
|
| 116 |
- **O-Avg**: Original Capability - Size Weighted Average across ARC, GPQA, MMLU, and MMLU Pro
|
| 117 |
-
- **Overall**: Combined average across all tasks
|
|
|
|
| 73 |
value: 0.4093251329787234
|
| 74 |
stderr: 0.004482884901882547
|
| 75 |
verified: false
|
| 76 |
+
library_name: transformers
|
| 77 |
+
pipeline_tag: text-generation
|
| 78 |
---
|
| 79 |
+
|
| 80 |
# Control-LLM-Llama3.1-8B-Math16
|
| 81 |
This is a fine-tuned model of Llama-3.1-8B-Instruct for mathematical tasks on OpenCoder SFT dataset.
|
| 82 |
|
|
|
|
| 117 |
- **MLU**: MMLU (Massive Multitask Language Understanding)
|
| 118 |
- **MLUP**: MMLU Pro
|
| 119 |
- **O-Avg**: Original Capability - Size Weighted Average across ARC, GPQA, MMLU, and MMLU Pro
|
| 120 |
+
- **Overall**: Combined average across all tasks
|