fix: bad dtype for full finetune (#504)

* fix: bad dtype for full finetune

* Update src/axolotl/utils/models.py

Co-authored-by: Wing Lian <wing.lian@gmail.com>

* Update models.py

---------

Co-authored-by: Wing Lian <wing.lian@gmail.com>

src/axolotl/utils/models.py

@@ -371,7 +371,7 @@ def load_model(
 
     # LlamaRMSNorm layers are in fp32 after kbit_training or full finetune, so we need to
     # convert them back to fp16/bf16 for flash-attn compatibility.
-    if needs_fa2_dtype and (cfg.flash_attention and cfg.is_llama_derived_model):
+    if needs_fa2_dtype or (cfg.flash_attention and cfg.is_llama_derived_model):
         LOG.info("converting modules to %s for flash attention", cfg.torch_dtype)
         for name, module in model.named_modules():
             if "norm" in name: