Update README.md
Browse files
README.md
CHANGED
|
@@ -15,7 +15,12 @@ quantized_by: Suparious
|
|
| 15 |
- Model creator: [timpal0l](https://huggingface.co/timpal0l)
|
| 16 |
- Original model: [Llama-3-8B-flashback-v1](https://huggingface.co/timpal0l/Llama-3-8B-flashback-v1)
|
| 17 |
|
|
|
|
| 18 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 19 |
|
| 20 |
## How to use
|
| 21 |
|
|
|
|
| 15 |
- Model creator: [timpal0l](https://huggingface.co/timpal0l)
|
| 16 |
- Original model: [Llama-3-8B-flashback-v1](https://huggingface.co/timpal0l/Llama-3-8B-flashback-v1)
|
| 17 |
|
| 18 |
+
|
| 19 |
|
| 20 |
+
## Model Summary
|
| 21 |
+
|
| 22 |
+
Llama-3-8B-flashback-v1 is a continuation of the pretraining process for the base meta-llama/Meta-Llama-3-8B model, utilizing 2 251 233 forum threads from the Swedish website https://www.flashback.org/. Which is rougly 40GB of text.
|
| 23 |
+
It is a full finetune for three epochs.
|
| 24 |
|
| 25 |
## How to use
|
| 26 |
|