Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
license: cc-by-nc-4.0
|
| 4 |
+
tags:
|
| 5 |
+
- merge
|
| 6 |
+
- automerger
|
| 7 |
+
base_model: mlabonne/UltraMerge-7B
|
| 8 |
+
pipeline_tag: text-generation
|
| 9 |
+
---
|
| 10 |
+
|
| 11 |
+
# QuantFactory/UltraMerge-7B-GGUF
|
| 12 |
+
This is quantized version of [mlabonne/UltraMerge-7B](https://huggingface.co/mlabonne/UltraMerge-7B) created using llama.cpp
|
| 13 |
+
|
| 14 |
+
# Model Description
|
| 15 |
+
|
| 16 |
+
This model is an experimental DPO fine-tune of [automerger/YamShadow-7B](https://huggingface.co/automerger/YamShadow-7B) on the following datasets:
|
| 17 |
+
|
| 18 |
+
- mlabonne/truthy-dpo-v0.1
|
| 19 |
+
- mlabonne/distilabel-intel-orca-dpo-pairs
|
| 20 |
+
- mlabonne/chatml-OpenHermes2.5-dpo-binarized-alpha
|
| 21 |
+
- mlabonne/ultrafeedback-binarized-preferences-cleaned
|
| 22 |
+
|
| 23 |
+
I have no idea about what's the best chat template. Probably Mistral-Instruct or ChatML.
|