Instructions to use leafspark/SFR-Iterative-DPO-LLaMA-3-8B-R-lora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use leafspark/SFR-Iterative-DPO-LLaMA-3-8B-R-lora with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("leafspark/SFR-Iterative-DPO-LLaMA-3-8B-R-lora", dtype="auto") - PEFT
How to use leafspark/SFR-Iterative-DPO-LLaMA-3-8B-R-lora with PEFT:
Task type is invalid.
- Notebooks
- Google Colab
- Kaggle
readme: add model card
Browse files
README.md
CHANGED
|
@@ -1,3 +1,23 @@
|
|
| 1 |
-
---
|
| 2 |
-
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: []
|
| 3 |
+
library_name: transformers
|
| 4 |
+
tags:
|
| 5 |
+
- mergekit
|
| 6 |
+
- peft
|
| 7 |
+
license: llama3
|
| 8 |
+
---
|
| 9 |
+
# SFR-Iterative-DPO-LLaMA-3-8B-R LoRA Model
|
| 10 |
+
|
| 11 |
+
This is a LoRA extracted from a language model. It was extracted using [mergekit](https://github.com/arcee-ai/mergekit).
|
| 12 |
+
|
| 13 |
+
## LoRA Details
|
| 14 |
+
|
| 15 |
+
This LoRA adapter was extracted from SFR-Iterative-DPO-LLaMA-3-8B-R and uses Meta-Llama-3-8B as a base.
|
| 16 |
+
|
| 17 |
+
### Parameters
|
| 18 |
+
|
| 19 |
+
The following command was used to extract this LoRA adapter:
|
| 20 |
+
|
| 21 |
+
```sh
|
| 22 |
+
mergekit-extract-lora Meta-Llama-3-8B SFR-Iterative-DPO-LLaMA-3-8B-R OUTPUT_PATH --rank=32
|
| 23 |
+
```
|