Update README.md
Browse files
README.md
CHANGED
|
@@ -22,6 +22,8 @@ LoRA trained in 4-bit with 8k context using [meta-llama/Meta-Llama-3-8B](https:/
|
|
| 22 |
|
| 23 |
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).
|
| 24 |
|
|
|
|
|
|
|
| 25 |
### Prompt format: Llama 3 Instruct
|
| 26 |
|
| 27 |
Unsloth changed assistant to gpt and user to human.
|
|
|
|
| 22 |
|
| 23 |
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).
|
| 24 |
|
| 25 |
+
From quick testing it appears to work fairly well for chatting.
|
| 26 |
+
|
| 27 |
### Prompt format: Llama 3 Instruct
|
| 28 |
|
| 29 |
Unsloth changed assistant to gpt and user to human.
|