Commit
•
fec208d
1
Parent(s):
093800e
Update README.md
Browse files
README.md
CHANGED
@@ -12,6 +12,8 @@ datasets:
|
|
12 |
|
13 |
# shisa-v2 Base Model ablation
|
14 |
|
|
|
|
|
15 |
This is a fine-tune Llama 3 70B Instruct with the primary `shisa-v1` dataset to improve Japanese language capabilities.
|
16 |
|
17 |
This model uses a LR of 8e-6 that slightly improves performance vs the original 2e-5 tune (based on and validating predictive power of the the
|
|
|
12 |
|
13 |
# shisa-v2 Base Model ablation
|
14 |
|
15 |
+
*Per the Llama 3 Community License Agreement, the official name of this model is "LLama 3 shisa-v1-llama3-70b"*
|
16 |
+
|
17 |
This is a fine-tune Llama 3 70B Instruct with the primary `shisa-v1` dataset to improve Japanese language capabilities.
|
18 |
|
19 |
This model uses a LR of 8e-6 that slightly improves performance vs the original 2e-5 tune (based on and validating predictive power of the the
|