Commit
·
7754b1e
1
Parent(s):
2ad39db
Update README.md
Browse files
README.md
CHANGED
|
@@ -2,6 +2,6 @@
|
|
| 2 |
|
| 3 |
This is a 8bit quanitzed fine tuned adapter merged with fp16 llama2-7b-chat-hf checkpoint.
|
| 4 |
Fine tuning has been performed on a very small/pico Guanaco dataset: manojkumarvohra/guanaco-pico-100-samples
|
| 5 |
-
|
| 6 |
with 100 training samples and 20 validation samples.
|
| 7 |
This model is created for learning purpose only and is not recommended to be used for a business purpose.
|
|
|
|
| 2 |
|
| 3 |
This is a 8bit quanitzed fine tuned adapter merged with fp16 llama2-7b-chat-hf checkpoint.
|
| 4 |
Fine tuning has been performed on a very small/pico Guanaco dataset: manojkumarvohra/guanaco-pico-100-samples
|
| 5 |
+
https://huggingface.co/datasets/manojkumarvohra/guanaco-pico-100-samples
|
| 6 |
with 100 training samples and 20 validation samples.
|
| 7 |
This model is created for learning purpose only and is not recommended to be used for a business purpose.
|