Update README.md
Browse files
README.md
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
---
|
| 2 |
-
base_model:
|
| 3 |
language:
|
| 4 |
- en
|
| 5 |
license: apache-2.0
|
|
@@ -9,7 +9,22 @@ tags:
|
|
| 9 |
- unsloth
|
| 10 |
- mistral
|
| 11 |
- trl
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 13 |
|
| 14 |
# Uploaded model
|
| 15 |
|
|
|
|
| 1 |
---
|
| 2 |
+
base_model: mistralai/Mistral-Nemo-Base-2407
|
| 3 |
language:
|
| 4 |
- en
|
| 5 |
license: apache-2.0
|
|
|
|
| 9 |
- unsloth
|
| 10 |
- mistral
|
| 11 |
- trl
|
| 12 |
+
datasets:
|
| 13 |
+
- mpasila/LimaRP-PIPPA-freedom-rp-Mix-8K
|
| 14 |
+
- grimulkan/LimaRP-augmented
|
| 15 |
+
- KaraKaraWitch/PIPPA-ShareGPT-formatted
|
| 16 |
+
- openerotica/freedom-rp
|
| 17 |
+
library_name: peft
|
| 18 |
---
|
| 19 |
+
LoRA trained in 4-bit with 8k context using [mistralai/Mistral-Nemo-Base-2407](https://huggingface.co/mistralai/Mistral-Nemo-Base-2407/) as the base model for 1 epoch.
|
| 20 |
+
|
| 21 |
+
Dataset used is [mpasila/LimaRP-PIPPA-freedom-rp-Mix-8K](https://huggingface.co/datasets/mpasila/LimaRP-PIPPA-freedom-rp-Mix-8K) which was made using [grimulkan/LimaRP-augmented](https://huggingface.co/datasets/grimulkan/LimaRP-augmented), [KaraKaraWitch/PIPPA-ShareGPT-formatted](https://huggingface.co/datasets/KaraKaraWitch/PIPPA-ShareGPT-formatted) and [openerotica/freedom-rp](https://huggingface.co/datasets/openerotica/freedom-rp).
|
| 22 |
+
|
| 23 |
+
Merged LoRA: [mpasila/Mistral-freeLiPPA-12B](https://huggingface.co/mpasila/Mistral-freeLiPPA-12B)
|
| 24 |
+
|
| 25 |
+
### Prompt format: ChatML
|
| 26 |
+
|
| 27 |
+
Changed to ChatML since it might be confusing to use Llama 3 Instruct template on a Mistral model...
|
| 28 |
|
| 29 |
# Uploaded model
|
| 30 |
|