Qubitium commited on
Commit
026f154
1 Parent(s): 104a0b3

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -0
README.md CHANGED
@@ -22,6 +22,9 @@ Run:
22
  "checkpoint_format": "marlin"
23
  }
24
  ```
 
 
 
25
  ---
26
  inference: false
27
  license: other
 
22
  "checkpoint_format": "marlin"
23
  }
24
  ```
25
+
26
+ TODO:
27
+ * Add sharding of quantized model so there is no need to manually combine safetensor files
28
  ---
29
  inference: false
30
  license: other