Update README.md
Browse files
README.md
CHANGED
@@ -8,7 +8,7 @@ datasets:
|
|
8 |
|
9 |
# Platypus2-7B
|
10 |
|
11 |
-
**NOTE**: There is some issue with LLaMa-2 7B and fine-tuning only works if you use `fp16=False` and `bf16=True` in the HF trainer.
|
12 |
|
13 |
Platypus-7B is an instruction fine-tuned model based on the LLaMA2-7B transformer architecture.
|
14 |
|
|
|
8 |
|
9 |
# Platypus2-7B
|
10 |
|
11 |
+
**NOTE**: There is some issue with LLaMa-2 7B and fine-tuning only works if you use `fp16=False` and `bf16=True` in the HF trainer. Gathering more intel on this but if you have any thoughts about this issue or performance, please let us know!
|
12 |
|
13 |
Platypus-7B is an instruction fine-tuned model based on the LLaMA2-7B transformer architecture.
|
14 |
|