willyninja30
commited on
Commit
•
3b97d51
1
Parent(s):
d2e765f
Update README.md
Browse files
README.md
CHANGED
@@ -2,6 +2,7 @@
|
|
2 |
library_name: peft
|
3 |
base_model: meta-llama/Llama-2-7b-chat-hf
|
4 |
inference: true
|
|
|
5 |
---
|
6 |
## Training procedure
|
7 |
|
@@ -20,4 +21,4 @@ The following `bitsandbytes` quantization config was used during training:
|
|
20 |
### Framework versions
|
21 |
|
22 |
|
23 |
-
- PEFT 0.6.0.dev0
|
|
|
2 |
library_name: peft
|
3 |
base_model: meta-llama/Llama-2-7b-chat-hf
|
4 |
inference: true
|
5 |
+
pipeline_tag: text-generation
|
6 |
---
|
7 |
## Training procedure
|
8 |
|
|
|
21 |
### Framework versions
|
22 |
|
23 |
|
24 |
+
- PEFT 0.6.0.dev0
|