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
|
|
@@ -11,6 +11,15 @@ tags:
|
|
| 11 |
- trl
|
| 12 |
- sft
|
| 13 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 14 |
|
| 15 |
# Uploaded model
|
| 16 |
|
|
|
|
| 1 |
---
|
| 2 |
+
base_model: mistralai/Mistral-Nemo-Base-2407
|
| 3 |
language:
|
| 4 |
- en
|
| 5 |
license: apache-2.0
|
|
|
|
| 11 |
- trl
|
| 12 |
- sft
|
| 13 |
---
|
| 14 |
+
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.
|
| 15 |
+
|
| 16 |
+
Dataset used is [mpasila/LimaRP-PIPPA-Mix-8K-Context](https://huggingface.co/datasets/mpasila/LimaRP-PIPPA-Mix-8K-Context) which was made using [grimulkan/LimaRP-augmented](https://huggingface.co/datasets/grimulkan/LimaRP-augmented) and [KaraKaraWitch/PIPPA-ShareGPT-formatted](https://huggingface.co/datasets/KaraKaraWitch/PIPPA-ShareGPT-formatted).
|
| 17 |
+
|
| 18 |
+
Merged from this LoRA: [mpasila/Mistral-LiPPA-LoRA-12B](https://huggingface.co/mpasila/Mistral-LiPPA-LoRA-12B)
|
| 19 |
+
|
| 20 |
+
### Prompt format: Llama 3 Instruct
|
| 21 |
+
|
| 22 |
+
Unsloth changed assistant to gpt and user to human.
|
| 23 |
|
| 24 |
# Uploaded model
|
| 25 |
|