Update README.md
Browse files
README.md
CHANGED
|
@@ -12,7 +12,18 @@ tags:
|
|
| 12 |
base_model: unsloth/llama-3-8b-bnb-4bit
|
| 13 |
datasets:
|
| 14 |
- mpasila/LimaRP-PIPPA-Mix-8K-Context
|
|
|
|
|
|
|
| 15 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 16 |
|
| 17 |
# Uploaded model
|
| 18 |
|
|
|
|
| 12 |
base_model: unsloth/llama-3-8b-bnb-4bit
|
| 13 |
datasets:
|
| 14 |
- mpasila/LimaRP-PIPPA-Mix-8K-Context
|
| 15 |
+
- grimulkan/LimaRP-augmented
|
| 16 |
+
- KaraKaraWitch/PIPPA-ShareGPT-formatted
|
| 17 |
---
|
| 18 |
+
This was made using the Llama 3 Instruct prompt formatting so that it should be easier to be merged with other models using that format.
|
| 19 |
+
|
| 20 |
+
LoRA trained in 4-bit with 8k context using [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B/) as the base model for 1 epoch.
|
| 21 |
+
|
| 22 |
+
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).
|
| 23 |
+
|
| 24 |
+
### Prompt format: Llama 3 Instruct
|
| 25 |
+
|
| 26 |
+
Unsloth changed assistant to gpt and user to human.
|
| 27 |
|
| 28 |
# Uploaded model
|
| 29 |
|