Merge pull request ggerganov#1 from slaren/cmrp-fixes

slaren: Cmrp fixes
dranger003 · Apr 6, 2024 · 8b6577b · 8b6577b
2 parents 26e8f23 + 78819c0
commit 8b6577b
Show file tree

Hide file tree

Showing 7 changed files with 277 additions and 295 deletions.
diff --git a/convert-hf-to-gguf.py b/convert-hf-to-gguf.py
@@ -160,7 +160,7 @@ def write_tensors(self):
                 data = data.astype(np.float32)
 
             # TODO: Why cant we use these float16 as-is? There should be not reason to store float16 as float32
-            if self.ftype == 1 and data_dtype == np.float16 and n_dims == 1:
+            if self.ftype == 1 and data_dtype == np.float16 and (n_dims == 1 or new_name.endswith("_norm.weight")):
                 data = data.astype(np.float32)
 
             # if f16 desired, convert any float32 2-dim weight tensors to float16