Initialize SFT adapter repo
Browse files
README.md
ADDED
|
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model: Qwen/Qwen2.5-1.5B-Instruct
|
| 4 |
+
datasets:
|
| 5 |
+
- krystv/nomen-ai-sft
|
| 6 |
+
tags:
|
| 7 |
+
- peft
|
| 8 |
+
- lora
|
| 9 |
+
- sft
|
| 10 |
+
- nomen-ai
|
| 11 |
+
pipeline_tag: text-generation
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
+
# Nomen-AI SFT LoRA Adapter
|
| 15 |
+
|
| 16 |
+
Target output repo for the SFT phase of Nomen-AI.
|
| 17 |
+
|
| 18 |
+
Training command:
|
| 19 |
+
|
| 20 |
+
```bash
|
| 21 |
+
export HUB_MODEL_ID=krystv/nomen-ai-sft-lora
|
| 22 |
+
python scripts/train_sft.py
|
| 23 |
+
```
|
| 24 |
+
|
| 25 |
+
Main pipeline repo: https://huggingface.co/krystv/nomen-ai
|