Hugging Face's logo

Blackroot
/
Llama-3-8B-Abomination-LORA

Safetensors
Model card Files Community
Blackroot commited on
Commit
7141392
•
1 Parent(s): 67f53c7

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +4 -1
README.md CHANGED
@@ -1,4 +1,7 @@
1
- This is a model trained in four stages:
 
 
 
2
  Base Model -- 1 Gig of semi-structured pretraining data:
3
  ![image/png](https://cdn-uploads.huggingface.co/production/uploads/637f3b03932a61b89aefbf5c/hpdbVRrM1yt65-gNtRIfT.png)
4
  - Base pretraining phase 1 (Constant LR, text completion -- 20,000 steps 2/3 epoch)
 
1
+ This is a model trained in four stages (Use with Llama-8B-Instruct or Llama-8B-Instruct abliterations)
2
+
3
+
4
+
5
  Base Model -- 1 Gig of semi-structured pretraining data:
6
  ![image/png](https://cdn-uploads.huggingface.co/production/uploads/637f3b03932a61b89aefbf5c/hpdbVRrM1yt65-gNtRIfT.png)
7
  - Base pretraining phase 1 (Constant LR, text completion -- 20,000 steps 2/3 epoch)