Commit
•
3b01c96
1
Parent(s):
a11ea6e
Update README.md
Browse files
README.md
CHANGED
|
@@ -9,6 +9,9 @@ datasets:
|
|
| 9 |
- Intel/orca_dpo_pairs
|
| 10 |
base_model: meta-llama/Meta-Llama-3.1-8B-Instruct
|
| 11 |
license: apache-2.0
|
|
|
|
|
|
|
|
|
|
| 12 |
---
|
| 13 |
|
| 14 |
### Finetuning Overview:
|
|
@@ -35,5 +38,4 @@ This finetuning run was performed using [MonsterAPI](https://monsterapi.ai)'s LL
|
|
| 35 |
- **Model Path:** meta-llama/Meta-Llama-3.1-8B-Instruct
|
| 36 |
- **Learning Rate:** 0.001
|
| 37 |
- **Data Split:** 90% train 10% validation
|
| 38 |
-
- **Gradient Accumulation Steps:** 16
|
| 39 |
-
|
|
|
|
| 9 |
- Intel/orca_dpo_pairs
|
| 10 |
base_model: meta-llama/Meta-Llama-3.1-8B-Instruct
|
| 11 |
license: apache-2.0
|
| 12 |
+
language:
|
| 13 |
+
- en
|
| 14 |
+
pipeline_tag: feature-extraction
|
| 15 |
---
|
| 16 |
|
| 17 |
### Finetuning Overview:
|
|
|
|
| 38 |
- **Model Path:** meta-llama/Meta-Llama-3.1-8B-Instruct
|
| 39 |
- **Learning Rate:** 0.001
|
| 40 |
- **Data Split:** 90% train 10% validation
|
| 41 |
+
- **Gradient Accumulation Steps:** 16
|
|
|