timpal0l
/

Llama-3-8B-flashback-v1

Text Generation

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

timpal0l commited on Apr 22

Commit

5b07b5c

•

1 Parent(s): c028d91

Update README.md

Files changed (1) hide show

README.md +4 -0

README.md CHANGED Viewed

@@ -24,6 +24,10 @@ widget:
 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.
 It is a full finetune for one epoch.
 ## How to use:
 ```python
 import torch

 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.
 It is a full finetune for one epoch.
+```html
+* tokens: 8_271_170_155
+* checkpoint 4/5
+```
 ## How to use:
 ```python
 import torch