nRuaif
commited on
Commit
·
9e2c203
1
Parent(s):
14adf5e
Update README.md
Browse files
README.md
CHANGED
|
@@ -5,7 +5,7 @@ tags:
|
|
| 5 |
- generated_from_trainer
|
| 6 |
base_model: tavtav/Rose-20B
|
| 7 |
model-index:
|
| 8 |
-
- name:
|
| 9 |
results: []
|
| 10 |
---
|
| 11 |
|
|
@@ -15,15 +15,15 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
[<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
|
| 16 |
# qlora-out
|
| 17 |
|
| 18 |
-
This model is a fine-tuned version of [tavtav/Rose-20B](https://huggingface.co/tavtav/Rose-20B) on the
|
| 19 |
|
| 20 |
## Model description
|
| 21 |
|
| 22 |
-
|
| 23 |
|
| 24 |
## Intended uses & limitations
|
| 25 |
|
| 26 |
-
|
| 27 |
|
| 28 |
## Training and evaluation data
|
| 29 |
|
|
|
|
| 5 |
- generated_from_trainer
|
| 6 |
base_model: tavtav/Rose-20B
|
| 7 |
model-index:
|
| 8 |
+
- name: Rose-Kimiko
|
| 9 |
results: []
|
| 10 |
---
|
| 11 |
|
|
|
|
| 15 |
[<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
|
| 16 |
# qlora-out
|
| 17 |
|
| 18 |
+
This model is a fine-tuned version of [tavtav/Rose-20B](https://huggingface.co/tavtav/Rose-20B) on the Kimiko dataset.
|
| 19 |
|
| 20 |
## Model description
|
| 21 |
|
| 22 |
+
The prompt formats used is ShareGPT/Vicuna format.
|
| 23 |
|
| 24 |
## Intended uses & limitations
|
| 25 |
|
| 26 |
+
Per many people requests, this LoRA is intended to fix spelling from Rose 20B.
|
| 27 |
|
| 28 |
## Training and evaluation data
|
| 29 |
|