Commit
•
97c3b34
1
Parent(s):
165792a
Upload folder using huggingface_hub
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- ndarray-cache-b16.json +1446 -0
- ndarray-cache.json +1446 -0
- params_shard_0.bin +3 -0
- params_shard_1.bin +3 -0
- params_shard_10.bin +3 -0
- params_shard_11.bin +3 -0
- params_shard_12.bin +3 -0
- params_shard_13.bin +3 -0
- params_shard_14.bin +3 -0
- params_shard_15.bin +3 -0
- params_shard_16.bin +3 -0
- params_shard_17.bin +3 -0
- params_shard_18.bin +3 -0
- params_shard_19.bin +3 -0
- params_shard_2.bin +3 -0
- params_shard_20.bin +3 -0
- params_shard_21.bin +3 -0
- params_shard_22.bin +3 -0
- params_shard_23.bin +3 -0
- params_shard_24.bin +3 -0
- params_shard_25.bin +3 -0
- params_shard_26.bin +3 -0
- params_shard_27.bin +3 -0
- params_shard_28.bin +3 -0
- params_shard_29.bin +3 -0
- params_shard_3.bin +3 -0
- params_shard_30.bin +3 -0
- params_shard_31.bin +3 -0
- params_shard_32.bin +3 -0
- params_shard_33.bin +3 -0
- params_shard_34.bin +3 -0
- params_shard_35.bin +3 -0
- params_shard_36.bin +3 -0
- params_shard_37.bin +3 -0
- params_shard_38.bin +3 -0
- params_shard_39.bin +3 -0
- params_shard_4.bin +3 -0
- params_shard_40.bin +3 -0
- params_shard_41.bin +3 -0
- params_shard_42.bin +3 -0
- params_shard_43.bin +3 -0
- params_shard_44.bin +3 -0
- params_shard_45.bin +3 -0
- params_shard_46.bin +3 -0
- params_shard_47.bin +3 -0
- params_shard_48.bin +3 -0
- params_shard_5.bin +3 -0
- params_shard_6.bin +3 -0
- params_shard_7.bin +3 -0
- params_shard_8.bin +3 -0
ndarray-cache-b16.json
ADDED
|
@@ -0,0 +1,1446 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"ParamSize": 98,
|
| 4 |
+
"ParamBytes": 4943257600.0,
|
| 5 |
+
"BitsPerParam": 32.0
|
| 6 |
+
},
|
| 7 |
+
"records": [
|
| 8 |
+
{
|
| 9 |
+
"dataPath": "params_shard_0.bin",
|
| 10 |
+
"format": "raw-shard",
|
| 11 |
+
"nbytes": 525336576,
|
| 12 |
+
"records": [
|
| 13 |
+
{
|
| 14 |
+
"name": "model.embed_tokens.weight",
|
| 15 |
+
"shape": [
|
| 16 |
+
128256,
|
| 17 |
+
2048
|
| 18 |
+
],
|
| 19 |
+
"dtype": "bfloat16",
|
| 20 |
+
"format": "raw",
|
| 21 |
+
"nbytes": 525336576,
|
| 22 |
+
"byteOffset": 0
|
| 23 |
+
}
|
| 24 |
+
],
|
| 25 |
+
"md5sum": "2097305f352cca56c3dc0ad1edb5bcbf"
|
| 26 |
+
},
|
| 27 |
+
{
|
| 28 |
+
"dataPath": "params_shard_1.bin",
|
| 29 |
+
"format": "raw-shard",
|
| 30 |
+
"nbytes": 33554432,
|
| 31 |
+
"records": [
|
| 32 |
+
{
|
| 33 |
+
"name": "model.layers.0.mlp.down_proj.weight",
|
| 34 |
+
"shape": [
|
| 35 |
+
2048,
|
| 36 |
+
8192
|
| 37 |
+
],
|
| 38 |
+
"dtype": "bfloat16",
|
| 39 |
+
"format": "raw",
|
| 40 |
+
"nbytes": 33554432,
|
| 41 |
+
"byteOffset": 0
|
| 42 |
+
}
|
| 43 |
+
],
|
| 44 |
+
"md5sum": "800df08c617c74598d4ca6af76553de0"
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"dataPath": "params_shard_2.bin",
|
| 48 |
+
"format": "raw-shard",
|
| 49 |
+
"nbytes": 67108864,
|
| 50 |
+
"records": [
|
| 51 |
+
{
|
| 52 |
+
"name": "model.layers.0.mlp.gate_up_proj.weight",
|
| 53 |
+
"shape": [
|
| 54 |
+
16384,
|
| 55 |
+
2048
|
| 56 |
+
],
|
| 57 |
+
"dtype": "bfloat16",
|
| 58 |
+
"format": "raw",
|
| 59 |
+
"nbytes": 67108864,
|
| 60 |
+
"byteOffset": 0
|
| 61 |
+
}
|
| 62 |
+
],
|
| 63 |
+
"md5sum": "eb3b214c8e085725718f03cf804164ae"
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"dataPath": "params_shard_3.bin",
|
| 67 |
+
"format": "raw-shard",
|
| 68 |
+
"nbytes": 33554432,
|
| 69 |
+
"records": [
|
| 70 |
+
{
|
| 71 |
+
"name": "model.layers.1.mlp.down_proj.weight",
|
| 72 |
+
"shape": [
|
| 73 |
+
2048,
|
| 74 |
+
8192
|
| 75 |
+
],
|
| 76 |
+
"dtype": "bfloat16",
|
| 77 |
+
"format": "raw",
|
| 78 |
+
"nbytes": 33554432,
|
| 79 |
+
"byteOffset": 0
|
| 80 |
+
}
|
| 81 |
+
],
|
| 82 |
+
"md5sum": "6a9a2411562a216b805451d914163a8c"
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"dataPath": "params_shard_4.bin",
|
| 86 |
+
"format": "raw-shard",
|
| 87 |
+
"nbytes": 67108864,
|
| 88 |
+
"records": [
|
| 89 |
+
{
|
| 90 |
+
"name": "model.layers.1.mlp.gate_up_proj.weight",
|
| 91 |
+
"shape": [
|
| 92 |
+
16384,
|
| 93 |
+
2048
|
| 94 |
+
],
|
| 95 |
+
"dtype": "bfloat16",
|
| 96 |
+
"format": "raw",
|
| 97 |
+
"nbytes": 67108864,
|
| 98 |
+
"byteOffset": 0
|
| 99 |
+
}
|
| 100 |
+
],
|
| 101 |
+
"md5sum": "32b4b83389df3b212ef853f8f19fc2d1"
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"dataPath": "params_shard_5.bin",
|
| 105 |
+
"format": "raw-shard",
|
| 106 |
+
"nbytes": 20987904,
|
| 107 |
+
"records": [
|
| 108 |
+
{
|
| 109 |
+
"name": "model.layers.0.input_layernorm.weight",
|
| 110 |
+
"shape": [
|
| 111 |
+
2048
|
| 112 |
+
],
|
| 113 |
+
"dtype": "bfloat16",
|
| 114 |
+
"format": "raw",
|
| 115 |
+
"nbytes": 4096,
|
| 116 |
+
"byteOffset": 0
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"name": "model.layers.0.post_attention_layernorm.weight",
|
| 120 |
+
"shape": [
|
| 121 |
+
2048
|
| 122 |
+
],
|
| 123 |
+
"dtype": "bfloat16",
|
| 124 |
+
"format": "raw",
|
| 125 |
+
"nbytes": 4096,
|
| 126 |
+
"byteOffset": 4096
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"name": "model.layers.0.self_attn.qkv_proj.weight",
|
| 130 |
+
"shape": [
|
| 131 |
+
3072,
|
| 132 |
+
2048
|
| 133 |
+
],
|
| 134 |
+
"dtype": "bfloat16",
|
| 135 |
+
"format": "raw",
|
| 136 |
+
"nbytes": 12582912,
|
| 137 |
+
"byteOffset": 8192
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"name": "model.layers.0.self_attn.o_proj.weight",
|
| 141 |
+
"shape": [
|
| 142 |
+
2048,
|
| 143 |
+
2048
|
| 144 |
+
],
|
| 145 |
+
"dtype": "bfloat16",
|
| 146 |
+
"format": "raw",
|
| 147 |
+
"nbytes": 8388608,
|
| 148 |
+
"byteOffset": 12591104
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"name": "model.layers.1.input_layernorm.weight",
|
| 152 |
+
"shape": [
|
| 153 |
+
2048
|
| 154 |
+
],
|
| 155 |
+
"dtype": "bfloat16",
|
| 156 |
+
"format": "raw",
|
| 157 |
+
"nbytes": 4096,
|
| 158 |
+
"byteOffset": 20979712
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"name": "model.layers.1.post_attention_layernorm.weight",
|
| 162 |
+
"shape": [
|
| 163 |
+
2048
|
| 164 |
+
],
|
| 165 |
+
"dtype": "bfloat16",
|
| 166 |
+
"format": "raw",
|
| 167 |
+
"nbytes": 4096,
|
| 168 |
+
"byteOffset": 20983808
|
| 169 |
+
}
|
| 170 |
+
],
|
| 171 |
+
"md5sum": "35b8ff220ef5e2e6627dcfb621fb832d"
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"dataPath": "params_shard_6.bin",
|
| 175 |
+
"format": "raw-shard",
|
| 176 |
+
"nbytes": 33554432,
|
| 177 |
+
"records": [
|
| 178 |
+
{
|
| 179 |
+
"name": "model.layers.10.mlp.down_proj.weight",
|
| 180 |
+
"shape": [
|
| 181 |
+
2048,
|
| 182 |
+
8192
|
| 183 |
+
],
|
| 184 |
+
"dtype": "bfloat16",
|
| 185 |
+
"format": "raw",
|
| 186 |
+
"nbytes": 33554432,
|
| 187 |
+
"byteOffset": 0
|
| 188 |
+
}
|
| 189 |
+
],
|
| 190 |
+
"md5sum": "9d8db30764216ea077a052dcd20fb2c4"
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"dataPath": "params_shard_7.bin",
|
| 194 |
+
"format": "raw-shard",
|
| 195 |
+
"nbytes": 67108864,
|
| 196 |
+
"records": [
|
| 197 |
+
{
|
| 198 |
+
"name": "model.layers.10.mlp.gate_up_proj.weight",
|
| 199 |
+
"shape": [
|
| 200 |
+
16384,
|
| 201 |
+
2048
|
| 202 |
+
],
|
| 203 |
+
"dtype": "bfloat16",
|
| 204 |
+
"format": "raw",
|
| 205 |
+
"nbytes": 67108864,
|
| 206 |
+
"byteOffset": 0
|
| 207 |
+
}
|
| 208 |
+
],
|
| 209 |
+
"md5sum": "0856245486dd0d049581359e670f33e0"
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"dataPath": "params_shard_8.bin",
|
| 213 |
+
"format": "raw-shard",
|
| 214 |
+
"nbytes": 20979712,
|
| 215 |
+
"records": [
|
| 216 |
+
{
|
| 217 |
+
"name": "model.layers.1.self_attn.qkv_proj.weight",
|
| 218 |
+
"shape": [
|
| 219 |
+
3072,
|
| 220 |
+
2048
|
| 221 |
+
],
|
| 222 |
+
"dtype": "bfloat16",
|
| 223 |
+
"format": "raw",
|
| 224 |
+
"nbytes": 12582912,
|
| 225 |
+
"byteOffset": 0
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"name": "model.layers.1.self_attn.o_proj.weight",
|
| 229 |
+
"shape": [
|
| 230 |
+
2048,
|
| 231 |
+
2048
|
| 232 |
+
],
|
| 233 |
+
"dtype": "bfloat16",
|
| 234 |
+
"format": "raw",
|
| 235 |
+
"nbytes": 8388608,
|
| 236 |
+
"byteOffset": 12582912
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"name": "model.layers.10.input_layernorm.weight",
|
| 240 |
+
"shape": [
|
| 241 |
+
2048
|
| 242 |
+
],
|
| 243 |
+
"dtype": "bfloat16",
|
| 244 |
+
"format": "raw",
|
| 245 |
+
"nbytes": 4096,
|
| 246 |
+
"byteOffset": 20971520
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"name": "model.layers.10.post_attention_layernorm.weight",
|
| 250 |
+
"shape": [
|
| 251 |
+
2048
|
| 252 |
+
],
|
| 253 |
+
"dtype": "bfloat16",
|
| 254 |
+
"format": "raw",
|
| 255 |
+
"nbytes": 4096,
|
| 256 |
+
"byteOffset": 20975616
|
| 257 |
+
}
|
| 258 |
+
],
|
| 259 |
+
"md5sum": "af71427b909126ccc9a9635a8279e0a9"
|
| 260 |
+
},
|
| 261 |
+
{
|
| 262 |
+
"dataPath": "params_shard_9.bin",
|
| 263 |
+
"format": "raw-shard",
|
| 264 |
+
"nbytes": 33554432,
|
| 265 |
+
"records": [
|
| 266 |
+
{
|
| 267 |
+
"name": "model.layers.11.mlp.down_proj.weight",
|
| 268 |
+
"shape": [
|
| 269 |
+
2048,
|
| 270 |
+
8192
|
| 271 |
+
],
|
| 272 |
+
"dtype": "bfloat16",
|
| 273 |
+
"format": "raw",
|
| 274 |
+
"nbytes": 33554432,
|
| 275 |
+
"byteOffset": 0
|
| 276 |
+
}
|
| 277 |
+
],
|
| 278 |
+
"md5sum": "795af0ca2c531da387572abece860a7e"
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"dataPath": "params_shard_10.bin",
|
| 282 |
+
"format": "raw-shard",
|
| 283 |
+
"nbytes": 67108864,
|
| 284 |
+
"records": [
|
| 285 |
+
{
|
| 286 |
+
"name": "model.layers.11.mlp.gate_up_proj.weight",
|
| 287 |
+
"shape": [
|
| 288 |
+
16384,
|
| 289 |
+
2048
|
| 290 |
+
],
|
| 291 |
+
"dtype": "bfloat16",
|
| 292 |
+
"format": "raw",
|
| 293 |
+
"nbytes": 67108864,
|
| 294 |
+
"byteOffset": 0
|
| 295 |
+
}
|
| 296 |
+
],
|
| 297 |
+
"md5sum": "4c8d8ed56e53eb99608130db0c1de05d"
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"dataPath": "params_shard_11.bin",
|
| 301 |
+
"format": "raw-shard",
|
| 302 |
+
"nbytes": 20979712,
|
| 303 |
+
"records": [
|
| 304 |
+
{
|
| 305 |
+
"name": "model.layers.10.self_attn.qkv_proj.weight",
|
| 306 |
+
"shape": [
|
| 307 |
+
3072,
|
| 308 |
+
2048
|
| 309 |
+
],
|
| 310 |
+
"dtype": "bfloat16",
|
| 311 |
+
"format": "raw",
|
| 312 |
+
"nbytes": 12582912,
|
| 313 |
+
"byteOffset": 0
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"name": "model.layers.10.self_attn.o_proj.weight",
|
| 317 |
+
"shape": [
|
| 318 |
+
2048,
|
| 319 |
+
2048
|
| 320 |
+
],
|
| 321 |
+
"dtype": "bfloat16",
|
| 322 |
+
"format": "raw",
|
| 323 |
+
"nbytes": 8388608,
|
| 324 |
+
"byteOffset": 12582912
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"name": "model.layers.11.input_layernorm.weight",
|
| 328 |
+
"shape": [
|
| 329 |
+
2048
|
| 330 |
+
],
|
| 331 |
+
"dtype": "bfloat16",
|
| 332 |
+
"format": "raw",
|
| 333 |
+
"nbytes": 4096,
|
| 334 |
+
"byteOffset": 20971520
|
| 335 |
+
},
|
| 336 |
+
{
|
| 337 |
+
"name": "model.layers.11.post_attention_layernorm.weight",
|
| 338 |
+
"shape": [
|
| 339 |
+
2048
|
| 340 |
+
],
|
| 341 |
+
"dtype": "bfloat16",
|
| 342 |
+
"format": "raw",
|
| 343 |
+
"nbytes": 4096,
|
| 344 |
+
"byteOffset": 20975616
|
| 345 |
+
}
|
| 346 |
+
],
|
| 347 |
+
"md5sum": "f7628a591cb04c54546aaaa4f9398a68"
|
| 348 |
+
},
|
| 349 |
+
{
|
| 350 |
+
"dataPath": "params_shard_12.bin",
|
| 351 |
+
"format": "raw-shard",
|
| 352 |
+
"nbytes": 33554432,
|
| 353 |
+
"records": [
|
| 354 |
+
{
|
| 355 |
+
"name": "model.layers.12.mlp.down_proj.weight",
|
| 356 |
+
"shape": [
|
| 357 |
+
2048,
|
| 358 |
+
8192
|
| 359 |
+
],
|
| 360 |
+
"dtype": "bfloat16",
|
| 361 |
+
"format": "raw",
|
| 362 |
+
"nbytes": 33554432,
|
| 363 |
+
"byteOffset": 0
|
| 364 |
+
}
|
| 365 |
+
],
|
| 366 |
+
"md5sum": "64f4c86756397349e929cd1f2f849e5c"
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"dataPath": "params_shard_13.bin",
|
| 370 |
+
"format": "raw-shard",
|
| 371 |
+
"nbytes": 67108864,
|
| 372 |
+
"records": [
|
| 373 |
+
{
|
| 374 |
+
"name": "model.layers.12.mlp.gate_up_proj.weight",
|
| 375 |
+
"shape": [
|
| 376 |
+
16384,
|
| 377 |
+
2048
|
| 378 |
+
],
|
| 379 |
+
"dtype": "bfloat16",
|
| 380 |
+
"format": "raw",
|
| 381 |
+
"nbytes": 67108864,
|
| 382 |
+
"byteOffset": 0
|
| 383 |
+
}
|
| 384 |
+
],
|
| 385 |
+
"md5sum": "ea4ff7cec9e3c5ec3c805a6586bdd2ee"
|
| 386 |
+
},
|
| 387 |
+
{
|
| 388 |
+
"dataPath": "params_shard_14.bin",
|
| 389 |
+
"format": "raw-shard",
|
| 390 |
+
"nbytes": 20979712,
|
| 391 |
+
"records": [
|
| 392 |
+
{
|
| 393 |
+
"name": "model.layers.11.self_attn.qkv_proj.weight",
|
| 394 |
+
"shape": [
|
| 395 |
+
3072,
|
| 396 |
+
2048
|
| 397 |
+
],
|
| 398 |
+
"dtype": "bfloat16",
|
| 399 |
+
"format": "raw",
|
| 400 |
+
"nbytes": 12582912,
|
| 401 |
+
"byteOffset": 0
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"name": "model.layers.11.self_attn.o_proj.weight",
|
| 405 |
+
"shape": [
|
| 406 |
+
2048,
|
| 407 |
+
2048
|
| 408 |
+
],
|
| 409 |
+
"dtype": "bfloat16",
|
| 410 |
+
"format": "raw",
|
| 411 |
+
"nbytes": 8388608,
|
| 412 |
+
"byteOffset": 12582912
|
| 413 |
+
},
|
| 414 |
+
{
|
| 415 |
+
"name": "model.layers.12.input_layernorm.weight",
|
| 416 |
+
"shape": [
|
| 417 |
+
2048
|
| 418 |
+
],
|
| 419 |
+
"dtype": "bfloat16",
|
| 420 |
+
"format": "raw",
|
| 421 |
+
"nbytes": 4096,
|
| 422 |
+
"byteOffset": 20971520
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"name": "model.layers.12.post_attention_layernorm.weight",
|
| 426 |
+
"shape": [
|
| 427 |
+
2048
|
| 428 |
+
],
|
| 429 |
+
"dtype": "bfloat16",
|
| 430 |
+
"format": "raw",
|
| 431 |
+
"nbytes": 4096,
|
| 432 |
+
"byteOffset": 20975616
|
| 433 |
+
}
|
| 434 |
+
],
|
| 435 |
+
"md5sum": "90f829661b428a1095ad0216de8f525e"
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"dataPath": "params_shard_15.bin",
|
| 439 |
+
"format": "raw-shard",
|
| 440 |
+
"nbytes": 33554432,
|
| 441 |
+
"records": [
|
| 442 |
+
{
|
| 443 |
+
"name": "model.layers.13.mlp.down_proj.weight",
|
| 444 |
+
"shape": [
|
| 445 |
+
2048,
|
| 446 |
+
8192
|
| 447 |
+
],
|
| 448 |
+
"dtype": "bfloat16",
|
| 449 |
+
"format": "raw",
|
| 450 |
+
"nbytes": 33554432,
|
| 451 |
+
"byteOffset": 0
|
| 452 |
+
}
|
| 453 |
+
],
|
| 454 |
+
"md5sum": "fb6f9e666f95e8149da896c79bbb730c"
|
| 455 |
+
},
|
| 456 |
+
{
|
| 457 |
+
"dataPath": "params_shard_16.bin",
|
| 458 |
+
"format": "raw-shard",
|
| 459 |
+
"nbytes": 67108864,
|
| 460 |
+
"records": [
|
| 461 |
+
{
|
| 462 |
+
"name": "model.layers.13.mlp.gate_up_proj.weight",
|
| 463 |
+
"shape": [
|
| 464 |
+
16384,
|
| 465 |
+
2048
|
| 466 |
+
],
|
| 467 |
+
"dtype": "bfloat16",
|
| 468 |
+
"format": "raw",
|
| 469 |
+
"nbytes": 67108864,
|
| 470 |
+
"byteOffset": 0
|
| 471 |
+
}
|
| 472 |
+
],
|
| 473 |
+
"md5sum": "097a18cf907839e45e7bceedcfeee09c"
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"dataPath": "params_shard_17.bin",
|
| 477 |
+
"format": "raw-shard",
|
| 478 |
+
"nbytes": 20979712,
|
| 479 |
+
"records": [
|
| 480 |
+
{
|
| 481 |
+
"name": "model.layers.12.self_attn.qkv_proj.weight",
|
| 482 |
+
"shape": [
|
| 483 |
+
3072,
|
| 484 |
+
2048
|
| 485 |
+
],
|
| 486 |
+
"dtype": "bfloat16",
|
| 487 |
+
"format": "raw",
|
| 488 |
+
"nbytes": 12582912,
|
| 489 |
+
"byteOffset": 0
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"name": "model.layers.12.self_attn.o_proj.weight",
|
| 493 |
+
"shape": [
|
| 494 |
+
2048,
|
| 495 |
+
2048
|
| 496 |
+
],
|
| 497 |
+
"dtype": "bfloat16",
|
| 498 |
+
"format": "raw",
|
| 499 |
+
"nbytes": 8388608,
|
| 500 |
+
"byteOffset": 12582912
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"name": "model.layers.13.input_layernorm.weight",
|
| 504 |
+
"shape": [
|
| 505 |
+
2048
|
| 506 |
+
],
|
| 507 |
+
"dtype": "bfloat16",
|
| 508 |
+
"format": "raw",
|
| 509 |
+
"nbytes": 4096,
|
| 510 |
+
"byteOffset": 20971520
|
| 511 |
+
},
|
| 512 |
+
{
|
| 513 |
+
"name": "model.layers.13.post_attention_layernorm.weight",
|
| 514 |
+
"shape": [
|
| 515 |
+
2048
|
| 516 |
+
],
|
| 517 |
+
"dtype": "bfloat16",
|
| 518 |
+
"format": "raw",
|
| 519 |
+
"nbytes": 4096,
|
| 520 |
+
"byteOffset": 20975616
|
| 521 |
+
}
|
| 522 |
+
],
|
| 523 |
+
"md5sum": "8c3f48c9a1fb32d02410baeb954f1bb6"
|
| 524 |
+
},
|
| 525 |
+
{
|
| 526 |
+
"dataPath": "params_shard_18.bin",
|
| 527 |
+
"format": "raw-shard",
|
| 528 |
+
"nbytes": 33554432,
|
| 529 |
+
"records": [
|
| 530 |
+
{
|
| 531 |
+
"name": "model.layers.14.mlp.down_proj.weight",
|
| 532 |
+
"shape": [
|
| 533 |
+
2048,
|
| 534 |
+
8192
|
| 535 |
+
],
|
| 536 |
+
"dtype": "bfloat16",
|
| 537 |
+
"format": "raw",
|
| 538 |
+
"nbytes": 33554432,
|
| 539 |
+
"byteOffset": 0
|
| 540 |
+
}
|
| 541 |
+
],
|
| 542 |
+
"md5sum": "ab16992964f5135c087f55a6c96eaf30"
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"dataPath": "params_shard_19.bin",
|
| 546 |
+
"format": "raw-shard",
|
| 547 |
+
"nbytes": 67108864,
|
| 548 |
+
"records": [
|
| 549 |
+
{
|
| 550 |
+
"name": "model.layers.14.mlp.gate_up_proj.weight",
|
| 551 |
+
"shape": [
|
| 552 |
+
16384,
|
| 553 |
+
2048
|
| 554 |
+
],
|
| 555 |
+
"dtype": "bfloat16",
|
| 556 |
+
"format": "raw",
|
| 557 |
+
"nbytes": 67108864,
|
| 558 |
+
"byteOffset": 0
|
| 559 |
+
}
|
| 560 |
+
],
|
| 561 |
+
"md5sum": "75e6fc44ba742deec3aea8e1bd310f22"
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"dataPath": "params_shard_20.bin",
|
| 565 |
+
"format": "raw-shard",
|
| 566 |
+
"nbytes": 20979712,
|
| 567 |
+
"records": [
|
| 568 |
+
{
|
| 569 |
+
"name": "model.layers.13.self_attn.qkv_proj.weight",
|
| 570 |
+
"shape": [
|
| 571 |
+
3072,
|
| 572 |
+
2048
|
| 573 |
+
],
|
| 574 |
+
"dtype": "bfloat16",
|
| 575 |
+
"format": "raw",
|
| 576 |
+
"nbytes": 12582912,
|
| 577 |
+
"byteOffset": 0
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"name": "model.layers.13.self_attn.o_proj.weight",
|
| 581 |
+
"shape": [
|
| 582 |
+
2048,
|
| 583 |
+
2048
|
| 584 |
+
],
|
| 585 |
+
"dtype": "bfloat16",
|
| 586 |
+
"format": "raw",
|
| 587 |
+
"nbytes": 8388608,
|
| 588 |
+
"byteOffset": 12582912
|
| 589 |
+
},
|
| 590 |
+
{
|
| 591 |
+
"name": "model.layers.14.input_layernorm.weight",
|
| 592 |
+
"shape": [
|
| 593 |
+
2048
|
| 594 |
+
],
|
| 595 |
+
"dtype": "bfloat16",
|
| 596 |
+
"format": "raw",
|
| 597 |
+
"nbytes": 4096,
|
| 598 |
+
"byteOffset": 20971520
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"name": "model.layers.14.post_attention_layernorm.weight",
|
| 602 |
+
"shape": [
|
| 603 |
+
2048
|
| 604 |
+
],
|
| 605 |
+
"dtype": "bfloat16",
|
| 606 |
+
"format": "raw",
|
| 607 |
+
"nbytes": 4096,
|
| 608 |
+
"byteOffset": 20975616
|
| 609 |
+
}
|
| 610 |
+
],
|
| 611 |
+
"md5sum": "a2c7db5bc8440c57f50b3c38a403c9f8"
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"dataPath": "params_shard_21.bin",
|
| 615 |
+
"format": "raw-shard",
|
| 616 |
+
"nbytes": 33554432,
|
| 617 |
+
"records": [
|
| 618 |
+
{
|
| 619 |
+
"name": "model.layers.15.mlp.down_proj.weight",
|
| 620 |
+
"shape": [
|
| 621 |
+
2048,
|
| 622 |
+
8192
|
| 623 |
+
],
|
| 624 |
+
"dtype": "bfloat16",
|
| 625 |
+
"format": "raw",
|
| 626 |
+
"nbytes": 33554432,
|
| 627 |
+
"byteOffset": 0
|
| 628 |
+
}
|
| 629 |
+
],
|
| 630 |
+
"md5sum": "3fe8a1e2c9e49e659f3411c7e138cd9f"
|
| 631 |
+
},
|
| 632 |
+
{
|
| 633 |
+
"dataPath": "params_shard_22.bin",
|
| 634 |
+
"format": "raw-shard",
|
| 635 |
+
"nbytes": 67108864,
|
| 636 |
+
"records": [
|
| 637 |
+
{
|
| 638 |
+
"name": "model.layers.15.mlp.gate_up_proj.weight",
|
| 639 |
+
"shape": [
|
| 640 |
+
16384,
|
| 641 |
+
2048
|
| 642 |
+
],
|
| 643 |
+
"dtype": "bfloat16",
|
| 644 |
+
"format": "raw",
|
| 645 |
+
"nbytes": 67108864,
|
| 646 |
+
"byteOffset": 0
|
| 647 |
+
}
|
| 648 |
+
],
|
| 649 |
+
"md5sum": "6929ff78c04aaf58088e2b0fd33c61c4"
|
| 650 |
+
},
|
| 651 |
+
{
|
| 652 |
+
"dataPath": "params_shard_23.bin",
|
| 653 |
+
"format": "raw-shard",
|
| 654 |
+
"nbytes": 20979712,
|
| 655 |
+
"records": [
|
| 656 |
+
{
|
| 657 |
+
"name": "model.layers.14.self_attn.qkv_proj.weight",
|
| 658 |
+
"shape": [
|
| 659 |
+
3072,
|
| 660 |
+
2048
|
| 661 |
+
],
|
| 662 |
+
"dtype": "bfloat16",
|
| 663 |
+
"format": "raw",
|
| 664 |
+
"nbytes": 12582912,
|
| 665 |
+
"byteOffset": 0
|
| 666 |
+
},
|
| 667 |
+
{
|
| 668 |
+
"name": "model.layers.14.self_attn.o_proj.weight",
|
| 669 |
+
"shape": [
|
| 670 |
+
2048,
|
| 671 |
+
2048
|
| 672 |
+
],
|
| 673 |
+
"dtype": "bfloat16",
|
| 674 |
+
"format": "raw",
|
| 675 |
+
"nbytes": 8388608,
|
| 676 |
+
"byteOffset": 12582912
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"name": "model.layers.15.input_layernorm.weight",
|
| 680 |
+
"shape": [
|
| 681 |
+
2048
|
| 682 |
+
],
|
| 683 |
+
"dtype": "bfloat16",
|
| 684 |
+
"format": "raw",
|
| 685 |
+
"nbytes": 4096,
|
| 686 |
+
"byteOffset": 20971520
|
| 687 |
+
},
|
| 688 |
+
{
|
| 689 |
+
"name": "model.layers.15.post_attention_layernorm.weight",
|
| 690 |
+
"shape": [
|
| 691 |
+
2048
|
| 692 |
+
],
|
| 693 |
+
"dtype": "bfloat16",
|
| 694 |
+
"format": "raw",
|
| 695 |
+
"nbytes": 4096,
|
| 696 |
+
"byteOffset": 20975616
|
| 697 |
+
}
|
| 698 |
+
],
|
| 699 |
+
"md5sum": "50aa881a0f07e3bf087ec22fd3c2c7f7"
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"dataPath": "params_shard_24.bin",
|
| 703 |
+
"format": "raw-shard",
|
| 704 |
+
"nbytes": 33554432,
|
| 705 |
+
"records": [
|
| 706 |
+
{
|
| 707 |
+
"name": "model.layers.2.mlp.down_proj.weight",
|
| 708 |
+
"shape": [
|
| 709 |
+
2048,
|
| 710 |
+
8192
|
| 711 |
+
],
|
| 712 |
+
"dtype": "bfloat16",
|
| 713 |
+
"format": "raw",
|
| 714 |
+
"nbytes": 33554432,
|
| 715 |
+
"byteOffset": 0
|
| 716 |
+
}
|
| 717 |
+
],
|
| 718 |
+
"md5sum": "5814d5a86c183a63f441e473b96eac9f"
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"dataPath": "params_shard_25.bin",
|
| 722 |
+
"format": "raw-shard",
|
| 723 |
+
"nbytes": 67108864,
|
| 724 |
+
"records": [
|
| 725 |
+
{
|
| 726 |
+
"name": "model.layers.2.mlp.gate_up_proj.weight",
|
| 727 |
+
"shape": [
|
| 728 |
+
16384,
|
| 729 |
+
2048
|
| 730 |
+
],
|
| 731 |
+
"dtype": "bfloat16",
|
| 732 |
+
"format": "raw",
|
| 733 |
+
"nbytes": 67108864,
|
| 734 |
+
"byteOffset": 0
|
| 735 |
+
}
|
| 736 |
+
],
|
| 737 |
+
"md5sum": "66938847fe03b3b7beb0c34e0ea3d146"
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"dataPath": "params_shard_26.bin",
|
| 741 |
+
"format": "raw-shard",
|
| 742 |
+
"nbytes": 20979712,
|
| 743 |
+
"records": [
|
| 744 |
+
{
|
| 745 |
+
"name": "model.layers.15.self_attn.qkv_proj.weight",
|
| 746 |
+
"shape": [
|
| 747 |
+
3072,
|
| 748 |
+
2048
|
| 749 |
+
],
|
| 750 |
+
"dtype": "bfloat16",
|
| 751 |
+
"format": "raw",
|
| 752 |
+
"nbytes": 12582912,
|
| 753 |
+
"byteOffset": 0
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"name": "model.layers.15.self_attn.o_proj.weight",
|
| 757 |
+
"shape": [
|
| 758 |
+
2048,
|
| 759 |
+
2048
|
| 760 |
+
],
|
| 761 |
+
"dtype": "bfloat16",
|
| 762 |
+
"format": "raw",
|
| 763 |
+
"nbytes": 8388608,
|
| 764 |
+
"byteOffset": 12582912
|
| 765 |
+
},
|
| 766 |
+
{
|
| 767 |
+
"name": "model.layers.2.input_layernorm.weight",
|
| 768 |
+
"shape": [
|
| 769 |
+
2048
|
| 770 |
+
],
|
| 771 |
+
"dtype": "bfloat16",
|
| 772 |
+
"format": "raw",
|
| 773 |
+
"nbytes": 4096,
|
| 774 |
+
"byteOffset": 20971520
|
| 775 |
+
},
|
| 776 |
+
{
|
| 777 |
+
"name": "model.layers.2.post_attention_layernorm.weight",
|
| 778 |
+
"shape": [
|
| 779 |
+
2048
|
| 780 |
+
],
|
| 781 |
+
"dtype": "bfloat16",
|
| 782 |
+
"format": "raw",
|
| 783 |
+
"nbytes": 4096,
|
| 784 |
+
"byteOffset": 20975616
|
| 785 |
+
}
|
| 786 |
+
],
|
| 787 |
+
"md5sum": "60e2dec95a7f652b11879a58814a0b72"
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"dataPath": "params_shard_27.bin",
|
| 791 |
+
"format": "raw-shard",
|
| 792 |
+
"nbytes": 33554432,
|
| 793 |
+
"records": [
|
| 794 |
+
{
|
| 795 |
+
"name": "model.layers.3.mlp.down_proj.weight",
|
| 796 |
+
"shape": [
|
| 797 |
+
2048,
|
| 798 |
+
8192
|
| 799 |
+
],
|
| 800 |
+
"dtype": "bfloat16",
|
| 801 |
+
"format": "raw",
|
| 802 |
+
"nbytes": 33554432,
|
| 803 |
+
"byteOffset": 0
|
| 804 |
+
}
|
| 805 |
+
],
|
| 806 |
+
"md5sum": "daca4f0d1145ceba60aba195b6e4b717"
|
| 807 |
+
},
|
| 808 |
+
{
|
| 809 |
+
"dataPath": "params_shard_28.bin",
|
| 810 |
+
"format": "raw-shard",
|
| 811 |
+
"nbytes": 67108864,
|
| 812 |
+
"records": [
|
| 813 |
+
{
|
| 814 |
+
"name": "model.layers.3.mlp.gate_up_proj.weight",
|
| 815 |
+
"shape": [
|
| 816 |
+
16384,
|
| 817 |
+
2048
|
| 818 |
+
],
|
| 819 |
+
"dtype": "bfloat16",
|
| 820 |
+
"format": "raw",
|
| 821 |
+
"nbytes": 67108864,
|
| 822 |
+
"byteOffset": 0
|
| 823 |
+
}
|
| 824 |
+
],
|
| 825 |
+
"md5sum": "a7d140e2aa8117b4e0251ab7d4f1e894"
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"dataPath": "params_shard_29.bin",
|
| 829 |
+
"format": "raw-shard",
|
| 830 |
+
"nbytes": 20979712,
|
| 831 |
+
"records": [
|
| 832 |
+
{
|
| 833 |
+
"name": "model.layers.2.self_attn.qkv_proj.weight",
|
| 834 |
+
"shape": [
|
| 835 |
+
3072,
|
| 836 |
+
2048
|
| 837 |
+
],
|
| 838 |
+
"dtype": "bfloat16",
|
| 839 |
+
"format": "raw",
|
| 840 |
+
"nbytes": 12582912,
|
| 841 |
+
"byteOffset": 0
|
| 842 |
+
},
|
| 843 |
+
{
|
| 844 |
+
"name": "model.layers.2.self_attn.o_proj.weight",
|
| 845 |
+
"shape": [
|
| 846 |
+
2048,
|
| 847 |
+
2048
|
| 848 |
+
],
|
| 849 |
+
"dtype": "bfloat16",
|
| 850 |
+
"format": "raw",
|
| 851 |
+
"nbytes": 8388608,
|
| 852 |
+
"byteOffset": 12582912
|
| 853 |
+
},
|
| 854 |
+
{
|
| 855 |
+
"name": "model.layers.3.input_layernorm.weight",
|
| 856 |
+
"shape": [
|
| 857 |
+
2048
|
| 858 |
+
],
|
| 859 |
+
"dtype": "bfloat16",
|
| 860 |
+
"format": "raw",
|
| 861 |
+
"nbytes": 4096,
|
| 862 |
+
"byteOffset": 20971520
|
| 863 |
+
},
|
| 864 |
+
{
|
| 865 |
+
"name": "model.layers.3.post_attention_layernorm.weight",
|
| 866 |
+
"shape": [
|
| 867 |
+
2048
|
| 868 |
+
],
|
| 869 |
+
"dtype": "bfloat16",
|
| 870 |
+
"format": "raw",
|
| 871 |
+
"nbytes": 4096,
|
| 872 |
+
"byteOffset": 20975616
|
| 873 |
+
}
|
| 874 |
+
],
|
| 875 |
+
"md5sum": "aa3290f5cbda1c5d43f00d0846fb3c5d"
|
| 876 |
+
},
|
| 877 |
+
{
|
| 878 |
+
"dataPath": "params_shard_30.bin",
|
| 879 |
+
"format": "raw-shard",
|
| 880 |
+
"nbytes": 33554432,
|
| 881 |
+
"records": [
|
| 882 |
+
{
|
| 883 |
+
"name": "model.layers.4.mlp.down_proj.weight",
|
| 884 |
+
"shape": [
|
| 885 |
+
2048,
|
| 886 |
+
8192
|
| 887 |
+
],
|
| 888 |
+
"dtype": "bfloat16",
|
| 889 |
+
"format": "raw",
|
| 890 |
+
"nbytes": 33554432,
|
| 891 |
+
"byteOffset": 0
|
| 892 |
+
}
|
| 893 |
+
],
|
| 894 |
+
"md5sum": "6f6f0eafe2557a8793292023a93fc44d"
|
| 895 |
+
},
|
| 896 |
+
{
|
| 897 |
+
"dataPath": "params_shard_31.bin",
|
| 898 |
+
"format": "raw-shard",
|
| 899 |
+
"nbytes": 67108864,
|
| 900 |
+
"records": [
|
| 901 |
+
{
|
| 902 |
+
"name": "model.layers.4.mlp.gate_up_proj.weight",
|
| 903 |
+
"shape": [
|
| 904 |
+
16384,
|
| 905 |
+
2048
|
| 906 |
+
],
|
| 907 |
+
"dtype": "bfloat16",
|
| 908 |
+
"format": "raw",
|
| 909 |
+
"nbytes": 67108864,
|
| 910 |
+
"byteOffset": 0
|
| 911 |
+
}
|
| 912 |
+
],
|
| 913 |
+
"md5sum": "ac207948c6dd9f8c618249b5c8370101"
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"dataPath": "params_shard_32.bin",
|
| 917 |
+
"format": "raw-shard",
|
| 918 |
+
"nbytes": 20979712,
|
| 919 |
+
"records": [
|
| 920 |
+
{
|
| 921 |
+
"name": "model.layers.3.self_attn.qkv_proj.weight",
|
| 922 |
+
"shape": [
|
| 923 |
+
3072,
|
| 924 |
+
2048
|
| 925 |
+
],
|
| 926 |
+
"dtype": "bfloat16",
|
| 927 |
+
"format": "raw",
|
| 928 |
+
"nbytes": 12582912,
|
| 929 |
+
"byteOffset": 0
|
| 930 |
+
},
|
| 931 |
+
{
|
| 932 |
+
"name": "model.layers.3.self_attn.o_proj.weight",
|
| 933 |
+
"shape": [
|
| 934 |
+
2048,
|
| 935 |
+
2048
|
| 936 |
+
],
|
| 937 |
+
"dtype": "bfloat16",
|
| 938 |
+
"format": "raw",
|
| 939 |
+
"nbytes": 8388608,
|
| 940 |
+
"byteOffset": 12582912
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"name": "model.layers.4.input_layernorm.weight",
|
| 944 |
+
"shape": [
|
| 945 |
+
2048
|
| 946 |
+
],
|
| 947 |
+
"dtype": "bfloat16",
|
| 948 |
+
"format": "raw",
|
| 949 |
+
"nbytes": 4096,
|
| 950 |
+
"byteOffset": 20971520
|
| 951 |
+
},
|
| 952 |
+
{
|
| 953 |
+
"name": "model.layers.4.post_attention_layernorm.weight",
|
| 954 |
+
"shape": [
|
| 955 |
+
2048
|
| 956 |
+
],
|
| 957 |
+
"dtype": "bfloat16",
|
| 958 |
+
"format": "raw",
|
| 959 |
+
"nbytes": 4096,
|
| 960 |
+
"byteOffset": 20975616
|
| 961 |
+
}
|
| 962 |
+
],
|
| 963 |
+
"md5sum": "5fd4c85aebd5f940fb7cb90a06bc0e3d"
|
| 964 |
+
},
|
| 965 |
+
{
|
| 966 |
+
"dataPath": "params_shard_33.bin",
|
| 967 |
+
"format": "raw-shard",
|
| 968 |
+
"nbytes": 33554432,
|
| 969 |
+
"records": [
|
| 970 |
+
{
|
| 971 |
+
"name": "model.layers.5.mlp.down_proj.weight",
|
| 972 |
+
"shape": [
|
| 973 |
+
2048,
|
| 974 |
+
8192
|
| 975 |
+
],
|
| 976 |
+
"dtype": "bfloat16",
|
| 977 |
+
"format": "raw",
|
| 978 |
+
"nbytes": 33554432,
|
| 979 |
+
"byteOffset": 0
|
| 980 |
+
}
|
| 981 |
+
],
|
| 982 |
+
"md5sum": "385fbfd45620a6a7c7d555b8cf7d35ff"
|
| 983 |
+
},
|
| 984 |
+
{
|
| 985 |
+
"dataPath": "params_shard_34.bin",
|
| 986 |
+
"format": "raw-shard",
|
| 987 |
+
"nbytes": 67108864,
|
| 988 |
+
"records": [
|
| 989 |
+
{
|
| 990 |
+
"name": "model.layers.5.mlp.gate_up_proj.weight",
|
| 991 |
+
"shape": [
|
| 992 |
+
16384,
|
| 993 |
+
2048
|
| 994 |
+
],
|
| 995 |
+
"dtype": "bfloat16",
|
| 996 |
+
"format": "raw",
|
| 997 |
+
"nbytes": 67108864,
|
| 998 |
+
"byteOffset": 0
|
| 999 |
+
}
|
| 1000 |
+
],
|
| 1001 |
+
"md5sum": "9d34ce6dc3d3bcecc868378358d66bcb"
|
| 1002 |
+
},
|
| 1003 |
+
{
|
| 1004 |
+
"dataPath": "params_shard_35.bin",
|
| 1005 |
+
"format": "raw-shard",
|
| 1006 |
+
"nbytes": 20979712,
|
| 1007 |
+
"records": [
|
| 1008 |
+
{
|
| 1009 |
+
"name": "model.layers.4.self_attn.qkv_proj.weight",
|
| 1010 |
+
"shape": [
|
| 1011 |
+
3072,
|
| 1012 |
+
2048
|
| 1013 |
+
],
|
| 1014 |
+
"dtype": "bfloat16",
|
| 1015 |
+
"format": "raw",
|
| 1016 |
+
"nbytes": 12582912,
|
| 1017 |
+
"byteOffset": 0
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"name": "model.layers.4.self_attn.o_proj.weight",
|
| 1021 |
+
"shape": [
|
| 1022 |
+
2048,
|
| 1023 |
+
2048
|
| 1024 |
+
],
|
| 1025 |
+
"dtype": "bfloat16",
|
| 1026 |
+
"format": "raw",
|
| 1027 |
+
"nbytes": 8388608,
|
| 1028 |
+
"byteOffset": 12582912
|
| 1029 |
+
},
|
| 1030 |
+
{
|
| 1031 |
+
"name": "model.layers.5.input_layernorm.weight",
|
| 1032 |
+
"shape": [
|
| 1033 |
+
2048
|
| 1034 |
+
],
|
| 1035 |
+
"dtype": "bfloat16",
|
| 1036 |
+
"format": "raw",
|
| 1037 |
+
"nbytes": 4096,
|
| 1038 |
+
"byteOffset": 20971520
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"name": "model.layers.5.post_attention_layernorm.weight",
|
| 1042 |
+
"shape": [
|
| 1043 |
+
2048
|
| 1044 |
+
],
|
| 1045 |
+
"dtype": "bfloat16",
|
| 1046 |
+
"format": "raw",
|
| 1047 |
+
"nbytes": 4096,
|
| 1048 |
+
"byteOffset": 20975616
|
| 1049 |
+
}
|
| 1050 |
+
],
|
| 1051 |
+
"md5sum": "24b869dad75eb377412439976e3ae012"
|
| 1052 |
+
},
|
| 1053 |
+
{
|
| 1054 |
+
"dataPath": "params_shard_36.bin",
|
| 1055 |
+
"format": "raw-shard",
|
| 1056 |
+
"nbytes": 33554432,
|
| 1057 |
+
"records": [
|
| 1058 |
+
{
|
| 1059 |
+
"name": "model.layers.6.mlp.down_proj.weight",
|
| 1060 |
+
"shape": [
|
| 1061 |
+
2048,
|
| 1062 |
+
8192
|
| 1063 |
+
],
|
| 1064 |
+
"dtype": "bfloat16",
|
| 1065 |
+
"format": "raw",
|
| 1066 |
+
"nbytes": 33554432,
|
| 1067 |
+
"byteOffset": 0
|
| 1068 |
+
}
|
| 1069 |
+
],
|
| 1070 |
+
"md5sum": "0168cb04de60c94a82da930ef69dfc79"
|
| 1071 |
+
},
|
| 1072 |
+
{
|
| 1073 |
+
"dataPath": "params_shard_37.bin",
|
| 1074 |
+
"format": "raw-shard",
|
| 1075 |
+
"nbytes": 67108864,
|
| 1076 |
+
"records": [
|
| 1077 |
+
{
|
| 1078 |
+
"name": "model.layers.6.mlp.gate_up_proj.weight",
|
| 1079 |
+
"shape": [
|
| 1080 |
+
16384,
|
| 1081 |
+
2048
|
| 1082 |
+
],
|
| 1083 |
+
"dtype": "bfloat16",
|
| 1084 |
+
"format": "raw",
|
| 1085 |
+
"nbytes": 67108864,
|
| 1086 |
+
"byteOffset": 0
|
| 1087 |
+
}
|
| 1088 |
+
],
|
| 1089 |
+
"md5sum": "f38fe5a46d483f933a79ce6577bd5236"
|
| 1090 |
+
},
|
| 1091 |
+
{
|
| 1092 |
+
"dataPath": "params_shard_38.bin",
|
| 1093 |
+
"format": "raw-shard",
|
| 1094 |
+
"nbytes": 20979712,
|
| 1095 |
+
"records": [
|
| 1096 |
+
{
|
| 1097 |
+
"name": "model.layers.5.self_attn.qkv_proj.weight",
|
| 1098 |
+
"shape": [
|
| 1099 |
+
3072,
|
| 1100 |
+
2048
|
| 1101 |
+
],
|
| 1102 |
+
"dtype": "bfloat16",
|
| 1103 |
+
"format": "raw",
|
| 1104 |
+
"nbytes": 12582912,
|
| 1105 |
+
"byteOffset": 0
|
| 1106 |
+
},
|
| 1107 |
+
{
|
| 1108 |
+
"name": "model.layers.5.self_attn.o_proj.weight",
|
| 1109 |
+
"shape": [
|
| 1110 |
+
2048,
|
| 1111 |
+
2048
|
| 1112 |
+
],
|
| 1113 |
+
"dtype": "bfloat16",
|
| 1114 |
+
"format": "raw",
|
| 1115 |
+
"nbytes": 8388608,
|
| 1116 |
+
"byteOffset": 12582912
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"name": "model.layers.6.input_layernorm.weight",
|
| 1120 |
+
"shape": [
|
| 1121 |
+
2048
|
| 1122 |
+
],
|
| 1123 |
+
"dtype": "bfloat16",
|
| 1124 |
+
"format": "raw",
|
| 1125 |
+
"nbytes": 4096,
|
| 1126 |
+
"byteOffset": 20971520
|
| 1127 |
+
},
|
| 1128 |
+
{
|
| 1129 |
+
"name": "model.layers.6.post_attention_layernorm.weight",
|
| 1130 |
+
"shape": [
|
| 1131 |
+
2048
|
| 1132 |
+
],
|
| 1133 |
+
"dtype": "bfloat16",
|
| 1134 |
+
"format": "raw",
|
| 1135 |
+
"nbytes": 4096,
|
| 1136 |
+
"byteOffset": 20975616
|
| 1137 |
+
}
|
| 1138 |
+
],
|
| 1139 |
+
"md5sum": "49401c003986778a26ab6e1d17dea5a9"
|
| 1140 |
+
},
|
| 1141 |
+
{
|
| 1142 |
+
"dataPath": "params_shard_39.bin",
|
| 1143 |
+
"format": "raw-shard",
|
| 1144 |
+
"nbytes": 33554432,
|
| 1145 |
+
"records": [
|
| 1146 |
+
{
|
| 1147 |
+
"name": "model.layers.7.mlp.down_proj.weight",
|
| 1148 |
+
"shape": [
|
| 1149 |
+
2048,
|
| 1150 |
+
8192
|
| 1151 |
+
],
|
| 1152 |
+
"dtype": "bfloat16",
|
| 1153 |
+
"format": "raw",
|
| 1154 |
+
"nbytes": 33554432,
|
| 1155 |
+
"byteOffset": 0
|
| 1156 |
+
}
|
| 1157 |
+
],
|
| 1158 |
+
"md5sum": "c9edef3101ccb32cf23b9342315b1a38"
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"dataPath": "params_shard_40.bin",
|
| 1162 |
+
"format": "raw-shard",
|
| 1163 |
+
"nbytes": 67108864,
|
| 1164 |
+
"records": [
|
| 1165 |
+
{
|
| 1166 |
+
"name": "model.layers.7.mlp.gate_up_proj.weight",
|
| 1167 |
+
"shape": [
|
| 1168 |
+
16384,
|
| 1169 |
+
2048
|
| 1170 |
+
],
|
| 1171 |
+
"dtype": "bfloat16",
|
| 1172 |
+
"format": "raw",
|
| 1173 |
+
"nbytes": 67108864,
|
| 1174 |
+
"byteOffset": 0
|
| 1175 |
+
}
|
| 1176 |
+
],
|
| 1177 |
+
"md5sum": "c7b95c82540aad932bca9ebac8caa96e"
|
| 1178 |
+
},
|
| 1179 |
+
{
|
| 1180 |
+
"dataPath": "params_shard_41.bin",
|
| 1181 |
+
"format": "raw-shard",
|
| 1182 |
+
"nbytes": 20979712,
|
| 1183 |
+
"records": [
|
| 1184 |
+
{
|
| 1185 |
+
"name": "model.layers.6.self_attn.qkv_proj.weight",
|
| 1186 |
+
"shape": [
|
| 1187 |
+
3072,
|
| 1188 |
+
2048
|
| 1189 |
+
],
|
| 1190 |
+
"dtype": "bfloat16",
|
| 1191 |
+
"format": "raw",
|
| 1192 |
+
"nbytes": 12582912,
|
| 1193 |
+
"byteOffset": 0
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"name": "model.layers.6.self_attn.o_proj.weight",
|
| 1197 |
+
"shape": [
|
| 1198 |
+
2048,
|
| 1199 |
+
2048
|
| 1200 |
+
],
|
| 1201 |
+
"dtype": "bfloat16",
|
| 1202 |
+
"format": "raw",
|
| 1203 |
+
"nbytes": 8388608,
|
| 1204 |
+
"byteOffset": 12582912
|
| 1205 |
+
},
|
| 1206 |
+
{
|
| 1207 |
+
"name": "model.layers.7.input_layernorm.weight",
|
| 1208 |
+
"shape": [
|
| 1209 |
+
2048
|
| 1210 |
+
],
|
| 1211 |
+
"dtype": "bfloat16",
|
| 1212 |
+
"format": "raw",
|
| 1213 |
+
"nbytes": 4096,
|
| 1214 |
+
"byteOffset": 20971520
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"name": "model.layers.7.post_attention_layernorm.weight",
|
| 1218 |
+
"shape": [
|
| 1219 |
+
2048
|
| 1220 |
+
],
|
| 1221 |
+
"dtype": "bfloat16",
|
| 1222 |
+
"format": "raw",
|
| 1223 |
+
"nbytes": 4096,
|
| 1224 |
+
"byteOffset": 20975616
|
| 1225 |
+
}
|
| 1226 |
+
],
|
| 1227 |
+
"md5sum": "e44904f0c432ad45b9919a22b590ae9a"
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"dataPath": "params_shard_42.bin",
|
| 1231 |
+
"format": "raw-shard",
|
| 1232 |
+
"nbytes": 33554432,
|
| 1233 |
+
"records": [
|
| 1234 |
+
{
|
| 1235 |
+
"name": "model.layers.8.mlp.down_proj.weight",
|
| 1236 |
+
"shape": [
|
| 1237 |
+
2048,
|
| 1238 |
+
8192
|
| 1239 |
+
],
|
| 1240 |
+
"dtype": "bfloat16",
|
| 1241 |
+
"format": "raw",
|
| 1242 |
+
"nbytes": 33554432,
|
| 1243 |
+
"byteOffset": 0
|
| 1244 |
+
}
|
| 1245 |
+
],
|
| 1246 |
+
"md5sum": "3e337579a791f65389f4a5a93dc95633"
|
| 1247 |
+
},
|
| 1248 |
+
{
|
| 1249 |
+
"dataPath": "params_shard_43.bin",
|
| 1250 |
+
"format": "raw-shard",
|
| 1251 |
+
"nbytes": 67108864,
|
| 1252 |
+
"records": [
|
| 1253 |
+
{
|
| 1254 |
+
"name": "model.layers.8.mlp.gate_up_proj.weight",
|
| 1255 |
+
"shape": [
|
| 1256 |
+
16384,
|
| 1257 |
+
2048
|
| 1258 |
+
],
|
| 1259 |
+
"dtype": "bfloat16",
|
| 1260 |
+
"format": "raw",
|
| 1261 |
+
"nbytes": 67108864,
|
| 1262 |
+
"byteOffset": 0
|
| 1263 |
+
}
|
| 1264 |
+
],
|
| 1265 |
+
"md5sum": "79c0f7d1fa6519b778d30ef952522121"
|
| 1266 |
+
},
|
| 1267 |
+
{
|
| 1268 |
+
"dataPath": "params_shard_44.bin",
|
| 1269 |
+
"format": "raw-shard",
|
| 1270 |
+
"nbytes": 20979712,
|
| 1271 |
+
"records": [
|
| 1272 |
+
{
|
| 1273 |
+
"name": "model.layers.7.self_attn.qkv_proj.weight",
|
| 1274 |
+
"shape": [
|
| 1275 |
+
3072,
|
| 1276 |
+
2048
|
| 1277 |
+
],
|
| 1278 |
+
"dtype": "bfloat16",
|
| 1279 |
+
"format": "raw",
|
| 1280 |
+
"nbytes": 12582912,
|
| 1281 |
+
"byteOffset": 0
|
| 1282 |
+
},
|
| 1283 |
+
{
|
| 1284 |
+
"name": "model.layers.7.self_attn.o_proj.weight",
|
| 1285 |
+
"shape": [
|
| 1286 |
+
2048,
|
| 1287 |
+
2048
|
| 1288 |
+
],
|
| 1289 |
+
"dtype": "bfloat16",
|
| 1290 |
+
"format": "raw",
|
| 1291 |
+
"nbytes": 8388608,
|
| 1292 |
+
"byteOffset": 12582912
|
| 1293 |
+
},
|
| 1294 |
+
{
|
| 1295 |
+
"name": "model.layers.8.input_layernorm.weight",
|
| 1296 |
+
"shape": [
|
| 1297 |
+
2048
|
| 1298 |
+
],
|
| 1299 |
+
"dtype": "bfloat16",
|
| 1300 |
+
"format": "raw",
|
| 1301 |
+
"nbytes": 4096,
|
| 1302 |
+
"byteOffset": 20971520
|
| 1303 |
+
},
|
| 1304 |
+
{
|
| 1305 |
+
"name": "model.layers.8.post_attention_layernorm.weight",
|
| 1306 |
+
"shape": [
|
| 1307 |
+
2048
|
| 1308 |
+
],
|
| 1309 |
+
"dtype": "bfloat16",
|
| 1310 |
+
"format": "raw",
|
| 1311 |
+
"nbytes": 4096,
|
| 1312 |
+
"byteOffset": 20975616
|
| 1313 |
+
}
|
| 1314 |
+
],
|
| 1315 |
+
"md5sum": "5a57388997fefe29f3788be628569150"
|
| 1316 |
+
},
|
| 1317 |
+
{
|
| 1318 |
+
"dataPath": "params_shard_45.bin",
|
| 1319 |
+
"format": "raw-shard",
|
| 1320 |
+
"nbytes": 33554432,
|
| 1321 |
+
"records": [
|
| 1322 |
+
{
|
| 1323 |
+
"name": "model.layers.9.mlp.down_proj.weight",
|
| 1324 |
+
"shape": [
|
| 1325 |
+
2048,
|
| 1326 |
+
8192
|
| 1327 |
+
],
|
| 1328 |
+
"dtype": "bfloat16",
|
| 1329 |
+
"format": "raw",
|
| 1330 |
+
"nbytes": 33554432,
|
| 1331 |
+
"byteOffset": 0
|
| 1332 |
+
}
|
| 1333 |
+
],
|
| 1334 |
+
"md5sum": "e2d663fbf063a76d8845a1117834610f"
|
| 1335 |
+
},
|
| 1336 |
+
{
|
| 1337 |
+
"dataPath": "params_shard_46.bin",
|
| 1338 |
+
"format": "raw-shard",
|
| 1339 |
+
"nbytes": 67108864,
|
| 1340 |
+
"records": [
|
| 1341 |
+
{
|
| 1342 |
+
"name": "model.layers.9.mlp.gate_up_proj.weight",
|
| 1343 |
+
"shape": [
|
| 1344 |
+
16384,
|
| 1345 |
+
2048
|
| 1346 |
+
],
|
| 1347 |
+
"dtype": "bfloat16",
|
| 1348 |
+
"format": "raw",
|
| 1349 |
+
"nbytes": 67108864,
|
| 1350 |
+
"byteOffset": 0
|
| 1351 |
+
}
|
| 1352 |
+
],
|
| 1353 |
+
"md5sum": "50e4119a748b23e67bfa10d1ec8e1f00"
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"dataPath": "params_shard_47.bin",
|
| 1357 |
+
"format": "raw-shard",
|
| 1358 |
+
"nbytes": 20979712,
|
| 1359 |
+
"records": [
|
| 1360 |
+
{
|
| 1361 |
+
"name": "model.layers.8.self_attn.qkv_proj.weight",
|
| 1362 |
+
"shape": [
|
| 1363 |
+
3072,
|
| 1364 |
+
2048
|
| 1365 |
+
],
|
| 1366 |
+
"dtype": "bfloat16",
|
| 1367 |
+
"format": "raw",
|
| 1368 |
+
"nbytes": 12582912,
|
| 1369 |
+
"byteOffset": 0
|
| 1370 |
+
},
|
| 1371 |
+
{
|
| 1372 |
+
"name": "model.layers.8.self_attn.o_proj.weight",
|
| 1373 |
+
"shape": [
|
| 1374 |
+
2048,
|
| 1375 |
+
2048
|
| 1376 |
+
],
|
| 1377 |
+
"dtype": "bfloat16",
|
| 1378 |
+
"format": "raw",
|
| 1379 |
+
"nbytes": 8388608,
|
| 1380 |
+
"byteOffset": 12582912
|
| 1381 |
+
},
|
| 1382 |
+
{
|
| 1383 |
+
"name": "model.layers.9.input_layernorm.weight",
|
| 1384 |
+
"shape": [
|
| 1385 |
+
2048
|
| 1386 |
+
],
|
| 1387 |
+
"dtype": "bfloat16",
|
| 1388 |
+
"format": "raw",
|
| 1389 |
+
"nbytes": 4096,
|
| 1390 |
+
"byteOffset": 20971520
|
| 1391 |
+
},
|
| 1392 |
+
{
|
| 1393 |
+
"name": "model.layers.9.post_attention_layernorm.weight",
|
| 1394 |
+
"shape": [
|
| 1395 |
+
2048
|
| 1396 |
+
],
|
| 1397 |
+
"dtype": "bfloat16",
|
| 1398 |
+
"format": "raw",
|
| 1399 |
+
"nbytes": 4096,
|
| 1400 |
+
"byteOffset": 20975616
|
| 1401 |
+
}
|
| 1402 |
+
],
|
| 1403 |
+
"md5sum": "c7f736b657c13231c2c106aab8827f06"
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"dataPath": "params_shard_48.bin",
|
| 1407 |
+
"format": "raw-shard",
|
| 1408 |
+
"nbytes": 20975616,
|
| 1409 |
+
"records": [
|
| 1410 |
+
{
|
| 1411 |
+
"name": "model.layers.9.self_attn.qkv_proj.weight",
|
| 1412 |
+
"shape": [
|
| 1413 |
+
3072,
|
| 1414 |
+
2048
|
| 1415 |
+
],
|
| 1416 |
+
"dtype": "bfloat16",
|
| 1417 |
+
"format": "raw",
|
| 1418 |
+
"nbytes": 12582912,
|
| 1419 |
+
"byteOffset": 0
|
| 1420 |
+
},
|
| 1421 |
+
{
|
| 1422 |
+
"name": "model.layers.9.self_attn.o_proj.weight",
|
| 1423 |
+
"shape": [
|
| 1424 |
+
2048,
|
| 1425 |
+
2048
|
| 1426 |
+
],
|
| 1427 |
+
"dtype": "bfloat16",
|
| 1428 |
+
"format": "raw",
|
| 1429 |
+
"nbytes": 8388608,
|
| 1430 |
+
"byteOffset": 12582912
|
| 1431 |
+
},
|
| 1432 |
+
{
|
| 1433 |
+
"name": "model.norm.weight",
|
| 1434 |
+
"shape": [
|
| 1435 |
+
2048
|
| 1436 |
+
],
|
| 1437 |
+
"dtype": "bfloat16",
|
| 1438 |
+
"format": "raw",
|
| 1439 |
+
"nbytes": 4096,
|
| 1440 |
+
"byteOffset": 20971520
|
| 1441 |
+
}
|
| 1442 |
+
],
|
| 1443 |
+
"md5sum": "2484e69deb5afeb91287322eac29c4f8"
|
| 1444 |
+
}
|
| 1445 |
+
]
|
| 1446 |
+
}
|
ndarray-cache.json
ADDED
|
@@ -0,0 +1,1446 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"ParamSize": 98,
|
| 4 |
+
"ParamBytes": 4943257600.0,
|
| 5 |
+
"BitsPerParam": 32.0
|
| 6 |
+
},
|
| 7 |
+
"records": [
|
| 8 |
+
{
|
| 9 |
+
"dataPath": "params_shard_0.bin",
|
| 10 |
+
"format": "raw-shard",
|
| 11 |
+
"nbytes": 525336576,
|
| 12 |
+
"records": [
|
| 13 |
+
{
|
| 14 |
+
"name": "model.embed_tokens.weight",
|
| 15 |
+
"shape": [
|
| 16 |
+
128256,
|
| 17 |
+
2048
|
| 18 |
+
],
|
| 19 |
+
"dtype": "float32",
|
| 20 |
+
"format": "f32-to-bf16",
|
| 21 |
+
"nbytes": 525336576,
|
| 22 |
+
"byteOffset": 0
|
| 23 |
+
}
|
| 24 |
+
],
|
| 25 |
+
"md5sum": "2097305f352cca56c3dc0ad1edb5bcbf"
|
| 26 |
+
},
|
| 27 |
+
{
|
| 28 |
+
"dataPath": "params_shard_1.bin",
|
| 29 |
+
"format": "raw-shard",
|
| 30 |
+
"nbytes": 33554432,
|
| 31 |
+
"records": [
|
| 32 |
+
{
|
| 33 |
+
"name": "model.layers.0.mlp.down_proj.weight",
|
| 34 |
+
"shape": [
|
| 35 |
+
2048,
|
| 36 |
+
8192
|
| 37 |
+
],
|
| 38 |
+
"dtype": "float32",
|
| 39 |
+
"format": "f32-to-bf16",
|
| 40 |
+
"nbytes": 33554432,
|
| 41 |
+
"byteOffset": 0
|
| 42 |
+
}
|
| 43 |
+
],
|
| 44 |
+
"md5sum": "800df08c617c74598d4ca6af76553de0"
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"dataPath": "params_shard_2.bin",
|
| 48 |
+
"format": "raw-shard",
|
| 49 |
+
"nbytes": 67108864,
|
| 50 |
+
"records": [
|
| 51 |
+
{
|
| 52 |
+
"name": "model.layers.0.mlp.gate_up_proj.weight",
|
| 53 |
+
"shape": [
|
| 54 |
+
16384,
|
| 55 |
+
2048
|
| 56 |
+
],
|
| 57 |
+
"dtype": "float32",
|
| 58 |
+
"format": "f32-to-bf16",
|
| 59 |
+
"nbytes": 67108864,
|
| 60 |
+
"byteOffset": 0
|
| 61 |
+
}
|
| 62 |
+
],
|
| 63 |
+
"md5sum": "eb3b214c8e085725718f03cf804164ae"
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"dataPath": "params_shard_3.bin",
|
| 67 |
+
"format": "raw-shard",
|
| 68 |
+
"nbytes": 33554432,
|
| 69 |
+
"records": [
|
| 70 |
+
{
|
| 71 |
+
"name": "model.layers.1.mlp.down_proj.weight",
|
| 72 |
+
"shape": [
|
| 73 |
+
2048,
|
| 74 |
+
8192
|
| 75 |
+
],
|
| 76 |
+
"dtype": "float32",
|
| 77 |
+
"format": "f32-to-bf16",
|
| 78 |
+
"nbytes": 33554432,
|
| 79 |
+
"byteOffset": 0
|
| 80 |
+
}
|
| 81 |
+
],
|
| 82 |
+
"md5sum": "6a9a2411562a216b805451d914163a8c"
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"dataPath": "params_shard_4.bin",
|
| 86 |
+
"format": "raw-shard",
|
| 87 |
+
"nbytes": 67108864,
|
| 88 |
+
"records": [
|
| 89 |
+
{
|
| 90 |
+
"name": "model.layers.1.mlp.gate_up_proj.weight",
|
| 91 |
+
"shape": [
|
| 92 |
+
16384,
|
| 93 |
+
2048
|
| 94 |
+
],
|
| 95 |
+
"dtype": "float32",
|
| 96 |
+
"format": "f32-to-bf16",
|
| 97 |
+
"nbytes": 67108864,
|
| 98 |
+
"byteOffset": 0
|
| 99 |
+
}
|
| 100 |
+
],
|
| 101 |
+
"md5sum": "32b4b83389df3b212ef853f8f19fc2d1"
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"dataPath": "params_shard_5.bin",
|
| 105 |
+
"format": "raw-shard",
|
| 106 |
+
"nbytes": 20987904,
|
| 107 |
+
"records": [
|
| 108 |
+
{
|
| 109 |
+
"name": "model.layers.0.input_layernorm.weight",
|
| 110 |
+
"shape": [
|
| 111 |
+
2048
|
| 112 |
+
],
|
| 113 |
+
"dtype": "float32",
|
| 114 |
+
"format": "f32-to-bf16",
|
| 115 |
+
"nbytes": 4096,
|
| 116 |
+
"byteOffset": 0
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"name": "model.layers.0.post_attention_layernorm.weight",
|
| 120 |
+
"shape": [
|
| 121 |
+
2048
|
| 122 |
+
],
|
| 123 |
+
"dtype": "float32",
|
| 124 |
+
"format": "f32-to-bf16",
|
| 125 |
+
"nbytes": 4096,
|
| 126 |
+
"byteOffset": 4096
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"name": "model.layers.0.self_attn.qkv_proj.weight",
|
| 130 |
+
"shape": [
|
| 131 |
+
3072,
|
| 132 |
+
2048
|
| 133 |
+
],
|
| 134 |
+
"dtype": "float32",
|
| 135 |
+
"format": "f32-to-bf16",
|
| 136 |
+
"nbytes": 12582912,
|
| 137 |
+
"byteOffset": 8192
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"name": "model.layers.0.self_attn.o_proj.weight",
|
| 141 |
+
"shape": [
|
| 142 |
+
2048,
|
| 143 |
+
2048
|
| 144 |
+
],
|
| 145 |
+
"dtype": "float32",
|
| 146 |
+
"format": "f32-to-bf16",
|
| 147 |
+
"nbytes": 8388608,
|
| 148 |
+
"byteOffset": 12591104
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"name": "model.layers.1.input_layernorm.weight",
|
| 152 |
+
"shape": [
|
| 153 |
+
2048
|
| 154 |
+
],
|
| 155 |
+
"dtype": "float32",
|
| 156 |
+
"format": "f32-to-bf16",
|
| 157 |
+
"nbytes": 4096,
|
| 158 |
+
"byteOffset": 20979712
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"name": "model.layers.1.post_attention_layernorm.weight",
|
| 162 |
+
"shape": [
|
| 163 |
+
2048
|
| 164 |
+
],
|
| 165 |
+
"dtype": "float32",
|
| 166 |
+
"format": "f32-to-bf16",
|
| 167 |
+
"nbytes": 4096,
|
| 168 |
+
"byteOffset": 20983808
|
| 169 |
+
}
|
| 170 |
+
],
|
| 171 |
+
"md5sum": "35b8ff220ef5e2e6627dcfb621fb832d"
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"dataPath": "params_shard_6.bin",
|
| 175 |
+
"format": "raw-shard",
|
| 176 |
+
"nbytes": 33554432,
|
| 177 |
+
"records": [
|
| 178 |
+
{
|
| 179 |
+
"name": "model.layers.10.mlp.down_proj.weight",
|
| 180 |
+
"shape": [
|
| 181 |
+
2048,
|
| 182 |
+
8192
|
| 183 |
+
],
|
| 184 |
+
"dtype": "float32",
|
| 185 |
+
"format": "f32-to-bf16",
|
| 186 |
+
"nbytes": 33554432,
|
| 187 |
+
"byteOffset": 0
|
| 188 |
+
}
|
| 189 |
+
],
|
| 190 |
+
"md5sum": "9d8db30764216ea077a052dcd20fb2c4"
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"dataPath": "params_shard_7.bin",
|
| 194 |
+
"format": "raw-shard",
|
| 195 |
+
"nbytes": 67108864,
|
| 196 |
+
"records": [
|
| 197 |
+
{
|
| 198 |
+
"name": "model.layers.10.mlp.gate_up_proj.weight",
|
| 199 |
+
"shape": [
|
| 200 |
+
16384,
|
| 201 |
+
2048
|
| 202 |
+
],
|
| 203 |
+
"dtype": "float32",
|
| 204 |
+
"format": "f32-to-bf16",
|
| 205 |
+
"nbytes": 67108864,
|
| 206 |
+
"byteOffset": 0
|
| 207 |
+
}
|
| 208 |
+
],
|
| 209 |
+
"md5sum": "0856245486dd0d049581359e670f33e0"
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"dataPath": "params_shard_8.bin",
|
| 213 |
+
"format": "raw-shard",
|
| 214 |
+
"nbytes": 20979712,
|
| 215 |
+
"records": [
|
| 216 |
+
{
|
| 217 |
+
"name": "model.layers.1.self_attn.qkv_proj.weight",
|
| 218 |
+
"shape": [
|
| 219 |
+
3072,
|
| 220 |
+
2048
|
| 221 |
+
],
|
| 222 |
+
"dtype": "float32",
|
| 223 |
+
"format": "f32-to-bf16",
|
| 224 |
+
"nbytes": 12582912,
|
| 225 |
+
"byteOffset": 0
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"name": "model.layers.1.self_attn.o_proj.weight",
|
| 229 |
+
"shape": [
|
| 230 |
+
2048,
|
| 231 |
+
2048
|
| 232 |
+
],
|
| 233 |
+
"dtype": "float32",
|
| 234 |
+
"format": "f32-to-bf16",
|
| 235 |
+
"nbytes": 8388608,
|
| 236 |
+
"byteOffset": 12582912
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"name": "model.layers.10.input_layernorm.weight",
|
| 240 |
+
"shape": [
|
| 241 |
+
2048
|
| 242 |
+
],
|
| 243 |
+
"dtype": "float32",
|
| 244 |
+
"format": "f32-to-bf16",
|
| 245 |
+
"nbytes": 4096,
|
| 246 |
+
"byteOffset": 20971520
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"name": "model.layers.10.post_attention_layernorm.weight",
|
| 250 |
+
"shape": [
|
| 251 |
+
2048
|
| 252 |
+
],
|
| 253 |
+
"dtype": "float32",
|
| 254 |
+
"format": "f32-to-bf16",
|
| 255 |
+
"nbytes": 4096,
|
| 256 |
+
"byteOffset": 20975616
|
| 257 |
+
}
|
| 258 |
+
],
|
| 259 |
+
"md5sum": "af71427b909126ccc9a9635a8279e0a9"
|
| 260 |
+
},
|
| 261 |
+
{
|
| 262 |
+
"dataPath": "params_shard_9.bin",
|
| 263 |
+
"format": "raw-shard",
|
| 264 |
+
"nbytes": 33554432,
|
| 265 |
+
"records": [
|
| 266 |
+
{
|
| 267 |
+
"name": "model.layers.11.mlp.down_proj.weight",
|
| 268 |
+
"shape": [
|
| 269 |
+
2048,
|
| 270 |
+
8192
|
| 271 |
+
],
|
| 272 |
+
"dtype": "float32",
|
| 273 |
+
"format": "f32-to-bf16",
|
| 274 |
+
"nbytes": 33554432,
|
| 275 |
+
"byteOffset": 0
|
| 276 |
+
}
|
| 277 |
+
],
|
| 278 |
+
"md5sum": "795af0ca2c531da387572abece860a7e"
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"dataPath": "params_shard_10.bin",
|
| 282 |
+
"format": "raw-shard",
|
| 283 |
+
"nbytes": 67108864,
|
| 284 |
+
"records": [
|
| 285 |
+
{
|
| 286 |
+
"name": "model.layers.11.mlp.gate_up_proj.weight",
|
| 287 |
+
"shape": [
|
| 288 |
+
16384,
|
| 289 |
+
2048
|
| 290 |
+
],
|
| 291 |
+
"dtype": "float32",
|
| 292 |
+
"format": "f32-to-bf16",
|
| 293 |
+
"nbytes": 67108864,
|
| 294 |
+
"byteOffset": 0
|
| 295 |
+
}
|
| 296 |
+
],
|
| 297 |
+
"md5sum": "4c8d8ed56e53eb99608130db0c1de05d"
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"dataPath": "params_shard_11.bin",
|
| 301 |
+
"format": "raw-shard",
|
| 302 |
+
"nbytes": 20979712,
|
| 303 |
+
"records": [
|
| 304 |
+
{
|
| 305 |
+
"name": "model.layers.10.self_attn.qkv_proj.weight",
|
| 306 |
+
"shape": [
|
| 307 |
+
3072,
|
| 308 |
+
2048
|
| 309 |
+
],
|
| 310 |
+
"dtype": "float32",
|
| 311 |
+
"format": "f32-to-bf16",
|
| 312 |
+
"nbytes": 12582912,
|
| 313 |
+
"byteOffset": 0
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"name": "model.layers.10.self_attn.o_proj.weight",
|
| 317 |
+
"shape": [
|
| 318 |
+
2048,
|
| 319 |
+
2048
|
| 320 |
+
],
|
| 321 |
+
"dtype": "float32",
|
| 322 |
+
"format": "f32-to-bf16",
|
| 323 |
+
"nbytes": 8388608,
|
| 324 |
+
"byteOffset": 12582912
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"name": "model.layers.11.input_layernorm.weight",
|
| 328 |
+
"shape": [
|
| 329 |
+
2048
|
| 330 |
+
],
|
| 331 |
+
"dtype": "float32",
|
| 332 |
+
"format": "f32-to-bf16",
|
| 333 |
+
"nbytes": 4096,
|
| 334 |
+
"byteOffset": 20971520
|
| 335 |
+
},
|
| 336 |
+
{
|
| 337 |
+
"name": "model.layers.11.post_attention_layernorm.weight",
|
| 338 |
+
"shape": [
|
| 339 |
+
2048
|
| 340 |
+
],
|
| 341 |
+
"dtype": "float32",
|
| 342 |
+
"format": "f32-to-bf16",
|
| 343 |
+
"nbytes": 4096,
|
| 344 |
+
"byteOffset": 20975616
|
| 345 |
+
}
|
| 346 |
+
],
|
| 347 |
+
"md5sum": "f7628a591cb04c54546aaaa4f9398a68"
|
| 348 |
+
},
|
| 349 |
+
{
|
| 350 |
+
"dataPath": "params_shard_12.bin",
|
| 351 |
+
"format": "raw-shard",
|
| 352 |
+
"nbytes": 33554432,
|
| 353 |
+
"records": [
|
| 354 |
+
{
|
| 355 |
+
"name": "model.layers.12.mlp.down_proj.weight",
|
| 356 |
+
"shape": [
|
| 357 |
+
2048,
|
| 358 |
+
8192
|
| 359 |
+
],
|
| 360 |
+
"dtype": "float32",
|
| 361 |
+
"format": "f32-to-bf16",
|
| 362 |
+
"nbytes": 33554432,
|
| 363 |
+
"byteOffset": 0
|
| 364 |
+
}
|
| 365 |
+
],
|
| 366 |
+
"md5sum": "64f4c86756397349e929cd1f2f849e5c"
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"dataPath": "params_shard_13.bin",
|
| 370 |
+
"format": "raw-shard",
|
| 371 |
+
"nbytes": 67108864,
|
| 372 |
+
"records": [
|
| 373 |
+
{
|
| 374 |
+
"name": "model.layers.12.mlp.gate_up_proj.weight",
|
| 375 |
+
"shape": [
|
| 376 |
+
16384,
|
| 377 |
+
2048
|
| 378 |
+
],
|
| 379 |
+
"dtype": "float32",
|
| 380 |
+
"format": "f32-to-bf16",
|
| 381 |
+
"nbytes": 67108864,
|
| 382 |
+
"byteOffset": 0
|
| 383 |
+
}
|
| 384 |
+
],
|
| 385 |
+
"md5sum": "ea4ff7cec9e3c5ec3c805a6586bdd2ee"
|
| 386 |
+
},
|
| 387 |
+
{
|
| 388 |
+
"dataPath": "params_shard_14.bin",
|
| 389 |
+
"format": "raw-shard",
|
| 390 |
+
"nbytes": 20979712,
|
| 391 |
+
"records": [
|
| 392 |
+
{
|
| 393 |
+
"name": "model.layers.11.self_attn.qkv_proj.weight",
|
| 394 |
+
"shape": [
|
| 395 |
+
3072,
|
| 396 |
+
2048
|
| 397 |
+
],
|
| 398 |
+
"dtype": "float32",
|
| 399 |
+
"format": "f32-to-bf16",
|
| 400 |
+
"nbytes": 12582912,
|
| 401 |
+
"byteOffset": 0
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"name": "model.layers.11.self_attn.o_proj.weight",
|
| 405 |
+
"shape": [
|
| 406 |
+
2048,
|
| 407 |
+
2048
|
| 408 |
+
],
|
| 409 |
+
"dtype": "float32",
|
| 410 |
+
"format": "f32-to-bf16",
|
| 411 |
+
"nbytes": 8388608,
|
| 412 |
+
"byteOffset": 12582912
|
| 413 |
+
},
|
| 414 |
+
{
|
| 415 |
+
"name": "model.layers.12.input_layernorm.weight",
|
| 416 |
+
"shape": [
|
| 417 |
+
2048
|
| 418 |
+
],
|
| 419 |
+
"dtype": "float32",
|
| 420 |
+
"format": "f32-to-bf16",
|
| 421 |
+
"nbytes": 4096,
|
| 422 |
+
"byteOffset": 20971520
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"name": "model.layers.12.post_attention_layernorm.weight",
|
| 426 |
+
"shape": [
|
| 427 |
+
2048
|
| 428 |
+
],
|
| 429 |
+
"dtype": "float32",
|
| 430 |
+
"format": "f32-to-bf16",
|
| 431 |
+
"nbytes": 4096,
|
| 432 |
+
"byteOffset": 20975616
|
| 433 |
+
}
|
| 434 |
+
],
|
| 435 |
+
"md5sum": "90f829661b428a1095ad0216de8f525e"
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"dataPath": "params_shard_15.bin",
|
| 439 |
+
"format": "raw-shard",
|
| 440 |
+
"nbytes": 33554432,
|
| 441 |
+
"records": [
|
| 442 |
+
{
|
| 443 |
+
"name": "model.layers.13.mlp.down_proj.weight",
|
| 444 |
+
"shape": [
|
| 445 |
+
2048,
|
| 446 |
+
8192
|
| 447 |
+
],
|
| 448 |
+
"dtype": "float32",
|
| 449 |
+
"format": "f32-to-bf16",
|
| 450 |
+
"nbytes": 33554432,
|
| 451 |
+
"byteOffset": 0
|
| 452 |
+
}
|
| 453 |
+
],
|
| 454 |
+
"md5sum": "fb6f9e666f95e8149da896c79bbb730c"
|
| 455 |
+
},
|
| 456 |
+
{
|
| 457 |
+
"dataPath": "params_shard_16.bin",
|
| 458 |
+
"format": "raw-shard",
|
| 459 |
+
"nbytes": 67108864,
|
| 460 |
+
"records": [
|
| 461 |
+
{
|
| 462 |
+
"name": "model.layers.13.mlp.gate_up_proj.weight",
|
| 463 |
+
"shape": [
|
| 464 |
+
16384,
|
| 465 |
+
2048
|
| 466 |
+
],
|
| 467 |
+
"dtype": "float32",
|
| 468 |
+
"format": "f32-to-bf16",
|
| 469 |
+
"nbytes": 67108864,
|
| 470 |
+
"byteOffset": 0
|
| 471 |
+
}
|
| 472 |
+
],
|
| 473 |
+
"md5sum": "097a18cf907839e45e7bceedcfeee09c"
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"dataPath": "params_shard_17.bin",
|
| 477 |
+
"format": "raw-shard",
|
| 478 |
+
"nbytes": 20979712,
|
| 479 |
+
"records": [
|
| 480 |
+
{
|
| 481 |
+
"name": "model.layers.12.self_attn.qkv_proj.weight",
|
| 482 |
+
"shape": [
|
| 483 |
+
3072,
|
| 484 |
+
2048
|
| 485 |
+
],
|
| 486 |
+
"dtype": "float32",
|
| 487 |
+
"format": "f32-to-bf16",
|
| 488 |
+
"nbytes": 12582912,
|
| 489 |
+
"byteOffset": 0
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"name": "model.layers.12.self_attn.o_proj.weight",
|
| 493 |
+
"shape": [
|
| 494 |
+
2048,
|
| 495 |
+
2048
|
| 496 |
+
],
|
| 497 |
+
"dtype": "float32",
|
| 498 |
+
"format": "f32-to-bf16",
|
| 499 |
+
"nbytes": 8388608,
|
| 500 |
+
"byteOffset": 12582912
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"name": "model.layers.13.input_layernorm.weight",
|
| 504 |
+
"shape": [
|
| 505 |
+
2048
|
| 506 |
+
],
|
| 507 |
+
"dtype": "float32",
|
| 508 |
+
"format": "f32-to-bf16",
|
| 509 |
+
"nbytes": 4096,
|
| 510 |
+
"byteOffset": 20971520
|
| 511 |
+
},
|
| 512 |
+
{
|
| 513 |
+
"name": "model.layers.13.post_attention_layernorm.weight",
|
| 514 |
+
"shape": [
|
| 515 |
+
2048
|
| 516 |
+
],
|
| 517 |
+
"dtype": "float32",
|
| 518 |
+
"format": "f32-to-bf16",
|
| 519 |
+
"nbytes": 4096,
|
| 520 |
+
"byteOffset": 20975616
|
| 521 |
+
}
|
| 522 |
+
],
|
| 523 |
+
"md5sum": "8c3f48c9a1fb32d02410baeb954f1bb6"
|
| 524 |
+
},
|
| 525 |
+
{
|
| 526 |
+
"dataPath": "params_shard_18.bin",
|
| 527 |
+
"format": "raw-shard",
|
| 528 |
+
"nbytes": 33554432,
|
| 529 |
+
"records": [
|
| 530 |
+
{
|
| 531 |
+
"name": "model.layers.14.mlp.down_proj.weight",
|
| 532 |
+
"shape": [
|
| 533 |
+
2048,
|
| 534 |
+
8192
|
| 535 |
+
],
|
| 536 |
+
"dtype": "float32",
|
| 537 |
+
"format": "f32-to-bf16",
|
| 538 |
+
"nbytes": 33554432,
|
| 539 |
+
"byteOffset": 0
|
| 540 |
+
}
|
| 541 |
+
],
|
| 542 |
+
"md5sum": "ab16992964f5135c087f55a6c96eaf30"
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"dataPath": "params_shard_19.bin",
|
| 546 |
+
"format": "raw-shard",
|
| 547 |
+
"nbytes": 67108864,
|
| 548 |
+
"records": [
|
| 549 |
+
{
|
| 550 |
+
"name": "model.layers.14.mlp.gate_up_proj.weight",
|
| 551 |
+
"shape": [
|
| 552 |
+
16384,
|
| 553 |
+
2048
|
| 554 |
+
],
|
| 555 |
+
"dtype": "float32",
|
| 556 |
+
"format": "f32-to-bf16",
|
| 557 |
+
"nbytes": 67108864,
|
| 558 |
+
"byteOffset": 0
|
| 559 |
+
}
|
| 560 |
+
],
|
| 561 |
+
"md5sum": "75e6fc44ba742deec3aea8e1bd310f22"
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"dataPath": "params_shard_20.bin",
|
| 565 |
+
"format": "raw-shard",
|
| 566 |
+
"nbytes": 20979712,
|
| 567 |
+
"records": [
|
| 568 |
+
{
|
| 569 |
+
"name": "model.layers.13.self_attn.qkv_proj.weight",
|
| 570 |
+
"shape": [
|
| 571 |
+
3072,
|
| 572 |
+
2048
|
| 573 |
+
],
|
| 574 |
+
"dtype": "float32",
|
| 575 |
+
"format": "f32-to-bf16",
|
| 576 |
+
"nbytes": 12582912,
|
| 577 |
+
"byteOffset": 0
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"name": "model.layers.13.self_attn.o_proj.weight",
|
| 581 |
+
"shape": [
|
| 582 |
+
2048,
|
| 583 |
+
2048
|
| 584 |
+
],
|
| 585 |
+
"dtype": "float32",
|
| 586 |
+
"format": "f32-to-bf16",
|
| 587 |
+
"nbytes": 8388608,
|
| 588 |
+
"byteOffset": 12582912
|
| 589 |
+
},
|
| 590 |
+
{
|
| 591 |
+
"name": "model.layers.14.input_layernorm.weight",
|
| 592 |
+
"shape": [
|
| 593 |
+
2048
|
| 594 |
+
],
|
| 595 |
+
"dtype": "float32",
|
| 596 |
+
"format": "f32-to-bf16",
|
| 597 |
+
"nbytes": 4096,
|
| 598 |
+
"byteOffset": 20971520
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"name": "model.layers.14.post_attention_layernorm.weight",
|
| 602 |
+
"shape": [
|
| 603 |
+
2048
|
| 604 |
+
],
|
| 605 |
+
"dtype": "float32",
|
| 606 |
+
"format": "f32-to-bf16",
|
| 607 |
+
"nbytes": 4096,
|
| 608 |
+
"byteOffset": 20975616
|
| 609 |
+
}
|
| 610 |
+
],
|
| 611 |
+
"md5sum": "a2c7db5bc8440c57f50b3c38a403c9f8"
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"dataPath": "params_shard_21.bin",
|
| 615 |
+
"format": "raw-shard",
|
| 616 |
+
"nbytes": 33554432,
|
| 617 |
+
"records": [
|
| 618 |
+
{
|
| 619 |
+
"name": "model.layers.15.mlp.down_proj.weight",
|
| 620 |
+
"shape": [
|
| 621 |
+
2048,
|
| 622 |
+
8192
|
| 623 |
+
],
|
| 624 |
+
"dtype": "float32",
|
| 625 |
+
"format": "f32-to-bf16",
|
| 626 |
+
"nbytes": 33554432,
|
| 627 |
+
"byteOffset": 0
|
| 628 |
+
}
|
| 629 |
+
],
|
| 630 |
+
"md5sum": "3fe8a1e2c9e49e659f3411c7e138cd9f"
|
| 631 |
+
},
|
| 632 |
+
{
|
| 633 |
+
"dataPath": "params_shard_22.bin",
|
| 634 |
+
"format": "raw-shard",
|
| 635 |
+
"nbytes": 67108864,
|
| 636 |
+
"records": [
|
| 637 |
+
{
|
| 638 |
+
"name": "model.layers.15.mlp.gate_up_proj.weight",
|
| 639 |
+
"shape": [
|
| 640 |
+
16384,
|
| 641 |
+
2048
|
| 642 |
+
],
|
| 643 |
+
"dtype": "float32",
|
| 644 |
+
"format": "f32-to-bf16",
|
| 645 |
+
"nbytes": 67108864,
|
| 646 |
+
"byteOffset": 0
|
| 647 |
+
}
|
| 648 |
+
],
|
| 649 |
+
"md5sum": "6929ff78c04aaf58088e2b0fd33c61c4"
|
| 650 |
+
},
|
| 651 |
+
{
|
| 652 |
+
"dataPath": "params_shard_23.bin",
|
| 653 |
+
"format": "raw-shard",
|
| 654 |
+
"nbytes": 20979712,
|
| 655 |
+
"records": [
|
| 656 |
+
{
|
| 657 |
+
"name": "model.layers.14.self_attn.qkv_proj.weight",
|
| 658 |
+
"shape": [
|
| 659 |
+
3072,
|
| 660 |
+
2048
|
| 661 |
+
],
|
| 662 |
+
"dtype": "float32",
|
| 663 |
+
"format": "f32-to-bf16",
|
| 664 |
+
"nbytes": 12582912,
|
| 665 |
+
"byteOffset": 0
|
| 666 |
+
},
|
| 667 |
+
{
|
| 668 |
+
"name": "model.layers.14.self_attn.o_proj.weight",
|
| 669 |
+
"shape": [
|
| 670 |
+
2048,
|
| 671 |
+
2048
|
| 672 |
+
],
|
| 673 |
+
"dtype": "float32",
|
| 674 |
+
"format": "f32-to-bf16",
|
| 675 |
+
"nbytes": 8388608,
|
| 676 |
+
"byteOffset": 12582912
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"name": "model.layers.15.input_layernorm.weight",
|
| 680 |
+
"shape": [
|
| 681 |
+
2048
|
| 682 |
+
],
|
| 683 |
+
"dtype": "float32",
|
| 684 |
+
"format": "f32-to-bf16",
|
| 685 |
+
"nbytes": 4096,
|
| 686 |
+
"byteOffset": 20971520
|
| 687 |
+
},
|
| 688 |
+
{
|
| 689 |
+
"name": "model.layers.15.post_attention_layernorm.weight",
|
| 690 |
+
"shape": [
|
| 691 |
+
2048
|
| 692 |
+
],
|
| 693 |
+
"dtype": "float32",
|
| 694 |
+
"format": "f32-to-bf16",
|
| 695 |
+
"nbytes": 4096,
|
| 696 |
+
"byteOffset": 20975616
|
| 697 |
+
}
|
| 698 |
+
],
|
| 699 |
+
"md5sum": "50aa881a0f07e3bf087ec22fd3c2c7f7"
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"dataPath": "params_shard_24.bin",
|
| 703 |
+
"format": "raw-shard",
|
| 704 |
+
"nbytes": 33554432,
|
| 705 |
+
"records": [
|
| 706 |
+
{
|
| 707 |
+
"name": "model.layers.2.mlp.down_proj.weight",
|
| 708 |
+
"shape": [
|
| 709 |
+
2048,
|
| 710 |
+
8192
|
| 711 |
+
],
|
| 712 |
+
"dtype": "float32",
|
| 713 |
+
"format": "f32-to-bf16",
|
| 714 |
+
"nbytes": 33554432,
|
| 715 |
+
"byteOffset": 0
|
| 716 |
+
}
|
| 717 |
+
],
|
| 718 |
+
"md5sum": "5814d5a86c183a63f441e473b96eac9f"
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"dataPath": "params_shard_25.bin",
|
| 722 |
+
"format": "raw-shard",
|
| 723 |
+
"nbytes": 67108864,
|
| 724 |
+
"records": [
|
| 725 |
+
{
|
| 726 |
+
"name": "model.layers.2.mlp.gate_up_proj.weight",
|
| 727 |
+
"shape": [
|
| 728 |
+
16384,
|
| 729 |
+
2048
|
| 730 |
+
],
|
| 731 |
+
"dtype": "float32",
|
| 732 |
+
"format": "f32-to-bf16",
|
| 733 |
+
"nbytes": 67108864,
|
| 734 |
+
"byteOffset": 0
|
| 735 |
+
}
|
| 736 |
+
],
|
| 737 |
+
"md5sum": "66938847fe03b3b7beb0c34e0ea3d146"
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"dataPath": "params_shard_26.bin",
|
| 741 |
+
"format": "raw-shard",
|
| 742 |
+
"nbytes": 20979712,
|
| 743 |
+
"records": [
|
| 744 |
+
{
|
| 745 |
+
"name": "model.layers.15.self_attn.qkv_proj.weight",
|
| 746 |
+
"shape": [
|
| 747 |
+
3072,
|
| 748 |
+
2048
|
| 749 |
+
],
|
| 750 |
+
"dtype": "float32",
|
| 751 |
+
"format": "f32-to-bf16",
|
| 752 |
+
"nbytes": 12582912,
|
| 753 |
+
"byteOffset": 0
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"name": "model.layers.15.self_attn.o_proj.weight",
|
| 757 |
+
"shape": [
|
| 758 |
+
2048,
|
| 759 |
+
2048
|
| 760 |
+
],
|
| 761 |
+
"dtype": "float32",
|
| 762 |
+
"format": "f32-to-bf16",
|
| 763 |
+
"nbytes": 8388608,
|
| 764 |
+
"byteOffset": 12582912
|
| 765 |
+
},
|
| 766 |
+
{
|
| 767 |
+
"name": "model.layers.2.input_layernorm.weight",
|
| 768 |
+
"shape": [
|
| 769 |
+
2048
|
| 770 |
+
],
|
| 771 |
+
"dtype": "float32",
|
| 772 |
+
"format": "f32-to-bf16",
|
| 773 |
+
"nbytes": 4096,
|
| 774 |
+
"byteOffset": 20971520
|
| 775 |
+
},
|
| 776 |
+
{
|
| 777 |
+
"name": "model.layers.2.post_attention_layernorm.weight",
|
| 778 |
+
"shape": [
|
| 779 |
+
2048
|
| 780 |
+
],
|
| 781 |
+
"dtype": "float32",
|
| 782 |
+
"format": "f32-to-bf16",
|
| 783 |
+
"nbytes": 4096,
|
| 784 |
+
"byteOffset": 20975616
|
| 785 |
+
}
|
| 786 |
+
],
|
| 787 |
+
"md5sum": "60e2dec95a7f652b11879a58814a0b72"
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"dataPath": "params_shard_27.bin",
|
| 791 |
+
"format": "raw-shard",
|
| 792 |
+
"nbytes": 33554432,
|
| 793 |
+
"records": [
|
| 794 |
+
{
|
| 795 |
+
"name": "model.layers.3.mlp.down_proj.weight",
|
| 796 |
+
"shape": [
|
| 797 |
+
2048,
|
| 798 |
+
8192
|
| 799 |
+
],
|
| 800 |
+
"dtype": "float32",
|
| 801 |
+
"format": "f32-to-bf16",
|
| 802 |
+
"nbytes": 33554432,
|
| 803 |
+
"byteOffset": 0
|
| 804 |
+
}
|
| 805 |
+
],
|
| 806 |
+
"md5sum": "daca4f0d1145ceba60aba195b6e4b717"
|
| 807 |
+
},
|
| 808 |
+
{
|
| 809 |
+
"dataPath": "params_shard_28.bin",
|
| 810 |
+
"format": "raw-shard",
|
| 811 |
+
"nbytes": 67108864,
|
| 812 |
+
"records": [
|
| 813 |
+
{
|
| 814 |
+
"name": "model.layers.3.mlp.gate_up_proj.weight",
|
| 815 |
+
"shape": [
|
| 816 |
+
16384,
|
| 817 |
+
2048
|
| 818 |
+
],
|
| 819 |
+
"dtype": "float32",
|
| 820 |
+
"format": "f32-to-bf16",
|
| 821 |
+
"nbytes": 67108864,
|
| 822 |
+
"byteOffset": 0
|
| 823 |
+
}
|
| 824 |
+
],
|
| 825 |
+
"md5sum": "a7d140e2aa8117b4e0251ab7d4f1e894"
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"dataPath": "params_shard_29.bin",
|
| 829 |
+
"format": "raw-shard",
|
| 830 |
+
"nbytes": 20979712,
|
| 831 |
+
"records": [
|
| 832 |
+
{
|
| 833 |
+
"name": "model.layers.2.self_attn.qkv_proj.weight",
|
| 834 |
+
"shape": [
|
| 835 |
+
3072,
|
| 836 |
+
2048
|
| 837 |
+
],
|
| 838 |
+
"dtype": "float32",
|
| 839 |
+
"format": "f32-to-bf16",
|
| 840 |
+
"nbytes": 12582912,
|
| 841 |
+
"byteOffset": 0
|
| 842 |
+
},
|
| 843 |
+
{
|
| 844 |
+
"name": "model.layers.2.self_attn.o_proj.weight",
|
| 845 |
+
"shape": [
|
| 846 |
+
2048,
|
| 847 |
+
2048
|
| 848 |
+
],
|
| 849 |
+
"dtype": "float32",
|
| 850 |
+
"format": "f32-to-bf16",
|
| 851 |
+
"nbytes": 8388608,
|
| 852 |
+
"byteOffset": 12582912
|
| 853 |
+
},
|
| 854 |
+
{
|
| 855 |
+
"name": "model.layers.3.input_layernorm.weight",
|
| 856 |
+
"shape": [
|
| 857 |
+
2048
|
| 858 |
+
],
|
| 859 |
+
"dtype": "float32",
|
| 860 |
+
"format": "f32-to-bf16",
|
| 861 |
+
"nbytes": 4096,
|
| 862 |
+
"byteOffset": 20971520
|
| 863 |
+
},
|
| 864 |
+
{
|
| 865 |
+
"name": "model.layers.3.post_attention_layernorm.weight",
|
| 866 |
+
"shape": [
|
| 867 |
+
2048
|
| 868 |
+
],
|
| 869 |
+
"dtype": "float32",
|
| 870 |
+
"format": "f32-to-bf16",
|
| 871 |
+
"nbytes": 4096,
|
| 872 |
+
"byteOffset": 20975616
|
| 873 |
+
}
|
| 874 |
+
],
|
| 875 |
+
"md5sum": "aa3290f5cbda1c5d43f00d0846fb3c5d"
|
| 876 |
+
},
|
| 877 |
+
{
|
| 878 |
+
"dataPath": "params_shard_30.bin",
|
| 879 |
+
"format": "raw-shard",
|
| 880 |
+
"nbytes": 33554432,
|
| 881 |
+
"records": [
|
| 882 |
+
{
|
| 883 |
+
"name": "model.layers.4.mlp.down_proj.weight",
|
| 884 |
+
"shape": [
|
| 885 |
+
2048,
|
| 886 |
+
8192
|
| 887 |
+
],
|
| 888 |
+
"dtype": "float32",
|
| 889 |
+
"format": "f32-to-bf16",
|
| 890 |
+
"nbytes": 33554432,
|
| 891 |
+
"byteOffset": 0
|
| 892 |
+
}
|
| 893 |
+
],
|
| 894 |
+
"md5sum": "6f6f0eafe2557a8793292023a93fc44d"
|
| 895 |
+
},
|
| 896 |
+
{
|
| 897 |
+
"dataPath": "params_shard_31.bin",
|
| 898 |
+
"format": "raw-shard",
|
| 899 |
+
"nbytes": 67108864,
|
| 900 |
+
"records": [
|
| 901 |
+
{
|
| 902 |
+
"name": "model.layers.4.mlp.gate_up_proj.weight",
|
| 903 |
+
"shape": [
|
| 904 |
+
16384,
|
| 905 |
+
2048
|
| 906 |
+
],
|
| 907 |
+
"dtype": "float32",
|
| 908 |
+
"format": "f32-to-bf16",
|
| 909 |
+
"nbytes": 67108864,
|
| 910 |
+
"byteOffset": 0
|
| 911 |
+
}
|
| 912 |
+
],
|
| 913 |
+
"md5sum": "ac207948c6dd9f8c618249b5c8370101"
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"dataPath": "params_shard_32.bin",
|
| 917 |
+
"format": "raw-shard",
|
| 918 |
+
"nbytes": 20979712,
|
| 919 |
+
"records": [
|
| 920 |
+
{
|
| 921 |
+
"name": "model.layers.3.self_attn.qkv_proj.weight",
|
| 922 |
+
"shape": [
|
| 923 |
+
3072,
|
| 924 |
+
2048
|
| 925 |
+
],
|
| 926 |
+
"dtype": "float32",
|
| 927 |
+
"format": "f32-to-bf16",
|
| 928 |
+
"nbytes": 12582912,
|
| 929 |
+
"byteOffset": 0
|
| 930 |
+
},
|
| 931 |
+
{
|
| 932 |
+
"name": "model.layers.3.self_attn.o_proj.weight",
|
| 933 |
+
"shape": [
|
| 934 |
+
2048,
|
| 935 |
+
2048
|
| 936 |
+
],
|
| 937 |
+
"dtype": "float32",
|
| 938 |
+
"format": "f32-to-bf16",
|
| 939 |
+
"nbytes": 8388608,
|
| 940 |
+
"byteOffset": 12582912
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"name": "model.layers.4.input_layernorm.weight",
|
| 944 |
+
"shape": [
|
| 945 |
+
2048
|
| 946 |
+
],
|
| 947 |
+
"dtype": "float32",
|
| 948 |
+
"format": "f32-to-bf16",
|
| 949 |
+
"nbytes": 4096,
|
| 950 |
+
"byteOffset": 20971520
|
| 951 |
+
},
|
| 952 |
+
{
|
| 953 |
+
"name": "model.layers.4.post_attention_layernorm.weight",
|
| 954 |
+
"shape": [
|
| 955 |
+
2048
|
| 956 |
+
],
|
| 957 |
+
"dtype": "float32",
|
| 958 |
+
"format": "f32-to-bf16",
|
| 959 |
+
"nbytes": 4096,
|
| 960 |
+
"byteOffset": 20975616
|
| 961 |
+
}
|
| 962 |
+
],
|
| 963 |
+
"md5sum": "5fd4c85aebd5f940fb7cb90a06bc0e3d"
|
| 964 |
+
},
|
| 965 |
+
{
|
| 966 |
+
"dataPath": "params_shard_33.bin",
|
| 967 |
+
"format": "raw-shard",
|
| 968 |
+
"nbytes": 33554432,
|
| 969 |
+
"records": [
|
| 970 |
+
{
|
| 971 |
+
"name": "model.layers.5.mlp.down_proj.weight",
|
| 972 |
+
"shape": [
|
| 973 |
+
2048,
|
| 974 |
+
8192
|
| 975 |
+
],
|
| 976 |
+
"dtype": "float32",
|
| 977 |
+
"format": "f32-to-bf16",
|
| 978 |
+
"nbytes": 33554432,
|
| 979 |
+
"byteOffset": 0
|
| 980 |
+
}
|
| 981 |
+
],
|
| 982 |
+
"md5sum": "385fbfd45620a6a7c7d555b8cf7d35ff"
|
| 983 |
+
},
|
| 984 |
+
{
|
| 985 |
+
"dataPath": "params_shard_34.bin",
|
| 986 |
+
"format": "raw-shard",
|
| 987 |
+
"nbytes": 67108864,
|
| 988 |
+
"records": [
|
| 989 |
+
{
|
| 990 |
+
"name": "model.layers.5.mlp.gate_up_proj.weight",
|
| 991 |
+
"shape": [
|
| 992 |
+
16384,
|
| 993 |
+
2048
|
| 994 |
+
],
|
| 995 |
+
"dtype": "float32",
|
| 996 |
+
"format": "f32-to-bf16",
|
| 997 |
+
"nbytes": 67108864,
|
| 998 |
+
"byteOffset": 0
|
| 999 |
+
}
|
| 1000 |
+
],
|
| 1001 |
+
"md5sum": "9d34ce6dc3d3bcecc868378358d66bcb"
|
| 1002 |
+
},
|
| 1003 |
+
{
|
| 1004 |
+
"dataPath": "params_shard_35.bin",
|
| 1005 |
+
"format": "raw-shard",
|
| 1006 |
+
"nbytes": 20979712,
|
| 1007 |
+
"records": [
|
| 1008 |
+
{
|
| 1009 |
+
"name": "model.layers.4.self_attn.qkv_proj.weight",
|
| 1010 |
+
"shape": [
|
| 1011 |
+
3072,
|
| 1012 |
+
2048
|
| 1013 |
+
],
|
| 1014 |
+
"dtype": "float32",
|
| 1015 |
+
"format": "f32-to-bf16",
|
| 1016 |
+
"nbytes": 12582912,
|
| 1017 |
+
"byteOffset": 0
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"name": "model.layers.4.self_attn.o_proj.weight",
|
| 1021 |
+
"shape": [
|
| 1022 |
+
2048,
|
| 1023 |
+
2048
|
| 1024 |
+
],
|
| 1025 |
+
"dtype": "float32",
|
| 1026 |
+
"format": "f32-to-bf16",
|
| 1027 |
+
"nbytes": 8388608,
|
| 1028 |
+
"byteOffset": 12582912
|
| 1029 |
+
},
|
| 1030 |
+
{
|
| 1031 |
+
"name": "model.layers.5.input_layernorm.weight",
|
| 1032 |
+
"shape": [
|
| 1033 |
+
2048
|
| 1034 |
+
],
|
| 1035 |
+
"dtype": "float32",
|
| 1036 |
+
"format": "f32-to-bf16",
|
| 1037 |
+
"nbytes": 4096,
|
| 1038 |
+
"byteOffset": 20971520
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"name": "model.layers.5.post_attention_layernorm.weight",
|
| 1042 |
+
"shape": [
|
| 1043 |
+
2048
|
| 1044 |
+
],
|
| 1045 |
+
"dtype": "float32",
|
| 1046 |
+
"format": "f32-to-bf16",
|
| 1047 |
+
"nbytes": 4096,
|
| 1048 |
+
"byteOffset": 20975616
|
| 1049 |
+
}
|
| 1050 |
+
],
|
| 1051 |
+
"md5sum": "24b869dad75eb377412439976e3ae012"
|
| 1052 |
+
},
|
| 1053 |
+
{
|
| 1054 |
+
"dataPath": "params_shard_36.bin",
|
| 1055 |
+
"format": "raw-shard",
|
| 1056 |
+
"nbytes": 33554432,
|
| 1057 |
+
"records": [
|
| 1058 |
+
{
|
| 1059 |
+
"name": "model.layers.6.mlp.down_proj.weight",
|
| 1060 |
+
"shape": [
|
| 1061 |
+
2048,
|
| 1062 |
+
8192
|
| 1063 |
+
],
|
| 1064 |
+
"dtype": "float32",
|
| 1065 |
+
"format": "f32-to-bf16",
|
| 1066 |
+
"nbytes": 33554432,
|
| 1067 |
+
"byteOffset": 0
|
| 1068 |
+
}
|
| 1069 |
+
],
|
| 1070 |
+
"md5sum": "0168cb04de60c94a82da930ef69dfc79"
|
| 1071 |
+
},
|
| 1072 |
+
{
|
| 1073 |
+
"dataPath": "params_shard_37.bin",
|
| 1074 |
+
"format": "raw-shard",
|
| 1075 |
+
"nbytes": 67108864,
|
| 1076 |
+
"records": [
|
| 1077 |
+
{
|
| 1078 |
+
"name": "model.layers.6.mlp.gate_up_proj.weight",
|
| 1079 |
+
"shape": [
|
| 1080 |
+
16384,
|
| 1081 |
+
2048
|
| 1082 |
+
],
|
| 1083 |
+
"dtype": "float32",
|
| 1084 |
+
"format": "f32-to-bf16",
|
| 1085 |
+
"nbytes": 67108864,
|
| 1086 |
+
"byteOffset": 0
|
| 1087 |
+
}
|
| 1088 |
+
],
|
| 1089 |
+
"md5sum": "f38fe5a46d483f933a79ce6577bd5236"
|
| 1090 |
+
},
|
| 1091 |
+
{
|
| 1092 |
+
"dataPath": "params_shard_38.bin",
|
| 1093 |
+
"format": "raw-shard",
|
| 1094 |
+
"nbytes": 20979712,
|
| 1095 |
+
"records": [
|
| 1096 |
+
{
|
| 1097 |
+
"name": "model.layers.5.self_attn.qkv_proj.weight",
|
| 1098 |
+
"shape": [
|
| 1099 |
+
3072,
|
| 1100 |
+
2048
|
| 1101 |
+
],
|
| 1102 |
+
"dtype": "float32",
|
| 1103 |
+
"format": "f32-to-bf16",
|
| 1104 |
+
"nbytes": 12582912,
|
| 1105 |
+
"byteOffset": 0
|
| 1106 |
+
},
|
| 1107 |
+
{
|
| 1108 |
+
"name": "model.layers.5.self_attn.o_proj.weight",
|
| 1109 |
+
"shape": [
|
| 1110 |
+
2048,
|
| 1111 |
+
2048
|
| 1112 |
+
],
|
| 1113 |
+
"dtype": "float32",
|
| 1114 |
+
"format": "f32-to-bf16",
|
| 1115 |
+
"nbytes": 8388608,
|
| 1116 |
+
"byteOffset": 12582912
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"name": "model.layers.6.input_layernorm.weight",
|
| 1120 |
+
"shape": [
|
| 1121 |
+
2048
|
| 1122 |
+
],
|
| 1123 |
+
"dtype": "float32",
|
| 1124 |
+
"format": "f32-to-bf16",
|
| 1125 |
+
"nbytes": 4096,
|
| 1126 |
+
"byteOffset": 20971520
|
| 1127 |
+
},
|
| 1128 |
+
{
|
| 1129 |
+
"name": "model.layers.6.post_attention_layernorm.weight",
|
| 1130 |
+
"shape": [
|
| 1131 |
+
2048
|
| 1132 |
+
],
|
| 1133 |
+
"dtype": "float32",
|
| 1134 |
+
"format": "f32-to-bf16",
|
| 1135 |
+
"nbytes": 4096,
|
| 1136 |
+
"byteOffset": 20975616
|
| 1137 |
+
}
|
| 1138 |
+
],
|
| 1139 |
+
"md5sum": "49401c003986778a26ab6e1d17dea5a9"
|
| 1140 |
+
},
|
| 1141 |
+
{
|
| 1142 |
+
"dataPath": "params_shard_39.bin",
|
| 1143 |
+
"format": "raw-shard",
|
| 1144 |
+
"nbytes": 33554432,
|
| 1145 |
+
"records": [
|
| 1146 |
+
{
|
| 1147 |
+
"name": "model.layers.7.mlp.down_proj.weight",
|
| 1148 |
+
"shape": [
|
| 1149 |
+
2048,
|
| 1150 |
+
8192
|
| 1151 |
+
],
|
| 1152 |
+
"dtype": "float32",
|
| 1153 |
+
"format": "f32-to-bf16",
|
| 1154 |
+
"nbytes": 33554432,
|
| 1155 |
+
"byteOffset": 0
|
| 1156 |
+
}
|
| 1157 |
+
],
|
| 1158 |
+
"md5sum": "c9edef3101ccb32cf23b9342315b1a38"
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"dataPath": "params_shard_40.bin",
|
| 1162 |
+
"format": "raw-shard",
|
| 1163 |
+
"nbytes": 67108864,
|
| 1164 |
+
"records": [
|
| 1165 |
+
{
|
| 1166 |
+
"name": "model.layers.7.mlp.gate_up_proj.weight",
|
| 1167 |
+
"shape": [
|
| 1168 |
+
16384,
|
| 1169 |
+
2048
|
| 1170 |
+
],
|
| 1171 |
+
"dtype": "float32",
|
| 1172 |
+
"format": "f32-to-bf16",
|
| 1173 |
+
"nbytes": 67108864,
|
| 1174 |
+
"byteOffset": 0
|
| 1175 |
+
}
|
| 1176 |
+
],
|
| 1177 |
+
"md5sum": "c7b95c82540aad932bca9ebac8caa96e"
|
| 1178 |
+
},
|
| 1179 |
+
{
|
| 1180 |
+
"dataPath": "params_shard_41.bin",
|
| 1181 |
+
"format": "raw-shard",
|
| 1182 |
+
"nbytes": 20979712,
|
| 1183 |
+
"records": [
|
| 1184 |
+
{
|
| 1185 |
+
"name": "model.layers.6.self_attn.qkv_proj.weight",
|
| 1186 |
+
"shape": [
|
| 1187 |
+
3072,
|
| 1188 |
+
2048
|
| 1189 |
+
],
|
| 1190 |
+
"dtype": "float32",
|
| 1191 |
+
"format": "f32-to-bf16",
|
| 1192 |
+
"nbytes": 12582912,
|
| 1193 |
+
"byteOffset": 0
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"name": "model.layers.6.self_attn.o_proj.weight",
|
| 1197 |
+
"shape": [
|
| 1198 |
+
2048,
|
| 1199 |
+
2048
|
| 1200 |
+
],
|
| 1201 |
+
"dtype": "float32",
|
| 1202 |
+
"format": "f32-to-bf16",
|
| 1203 |
+
"nbytes": 8388608,
|
| 1204 |
+
"byteOffset": 12582912
|
| 1205 |
+
},
|
| 1206 |
+
{
|
| 1207 |
+
"name": "model.layers.7.input_layernorm.weight",
|
| 1208 |
+
"shape": [
|
| 1209 |
+
2048
|
| 1210 |
+
],
|
| 1211 |
+
"dtype": "float32",
|
| 1212 |
+
"format": "f32-to-bf16",
|
| 1213 |
+
"nbytes": 4096,
|
| 1214 |
+
"byteOffset": 20971520
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"name": "model.layers.7.post_attention_layernorm.weight",
|
| 1218 |
+
"shape": [
|
| 1219 |
+
2048
|
| 1220 |
+
],
|
| 1221 |
+
"dtype": "float32",
|
| 1222 |
+
"format": "f32-to-bf16",
|
| 1223 |
+
"nbytes": 4096,
|
| 1224 |
+
"byteOffset": 20975616
|
| 1225 |
+
}
|
| 1226 |
+
],
|
| 1227 |
+
"md5sum": "e44904f0c432ad45b9919a22b590ae9a"
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"dataPath": "params_shard_42.bin",
|
| 1231 |
+
"format": "raw-shard",
|
| 1232 |
+
"nbytes": 33554432,
|
| 1233 |
+
"records": [
|
| 1234 |
+
{
|
| 1235 |
+
"name": "model.layers.8.mlp.down_proj.weight",
|
| 1236 |
+
"shape": [
|
| 1237 |
+
2048,
|
| 1238 |
+
8192
|
| 1239 |
+
],
|
| 1240 |
+
"dtype": "float32",
|
| 1241 |
+
"format": "f32-to-bf16",
|
| 1242 |
+
"nbytes": 33554432,
|
| 1243 |
+
"byteOffset": 0
|
| 1244 |
+
}
|
| 1245 |
+
],
|
| 1246 |
+
"md5sum": "3e337579a791f65389f4a5a93dc95633"
|
| 1247 |
+
},
|
| 1248 |
+
{
|
| 1249 |
+
"dataPath": "params_shard_43.bin",
|
| 1250 |
+
"format": "raw-shard",
|
| 1251 |
+
"nbytes": 67108864,
|
| 1252 |
+
"records": [
|
| 1253 |
+
{
|
| 1254 |
+
"name": "model.layers.8.mlp.gate_up_proj.weight",
|
| 1255 |
+
"shape": [
|
| 1256 |
+
16384,
|
| 1257 |
+
2048
|
| 1258 |
+
],
|
| 1259 |
+
"dtype": "float32",
|
| 1260 |
+
"format": "f32-to-bf16",
|
| 1261 |
+
"nbytes": 67108864,
|
| 1262 |
+
"byteOffset": 0
|
| 1263 |
+
}
|
| 1264 |
+
],
|
| 1265 |
+
"md5sum": "79c0f7d1fa6519b778d30ef952522121"
|
| 1266 |
+
},
|
| 1267 |
+
{
|
| 1268 |
+
"dataPath": "params_shard_44.bin",
|
| 1269 |
+
"format": "raw-shard",
|
| 1270 |
+
"nbytes": 20979712,
|
| 1271 |
+
"records": [
|
| 1272 |
+
{
|
| 1273 |
+
"name": "model.layers.7.self_attn.qkv_proj.weight",
|
| 1274 |
+
"shape": [
|
| 1275 |
+
3072,
|
| 1276 |
+
2048
|
| 1277 |
+
],
|
| 1278 |
+
"dtype": "float32",
|
| 1279 |
+
"format": "f32-to-bf16",
|
| 1280 |
+
"nbytes": 12582912,
|
| 1281 |
+
"byteOffset": 0
|
| 1282 |
+
},
|
| 1283 |
+
{
|
| 1284 |
+
"name": "model.layers.7.self_attn.o_proj.weight",
|
| 1285 |
+
"shape": [
|
| 1286 |
+
2048,
|
| 1287 |
+
2048
|
| 1288 |
+
],
|
| 1289 |
+
"dtype": "float32",
|
| 1290 |
+
"format": "f32-to-bf16",
|
| 1291 |
+
"nbytes": 8388608,
|
| 1292 |
+
"byteOffset": 12582912
|
| 1293 |
+
},
|
| 1294 |
+
{
|
| 1295 |
+
"name": "model.layers.8.input_layernorm.weight",
|
| 1296 |
+
"shape": [
|
| 1297 |
+
2048
|
| 1298 |
+
],
|
| 1299 |
+
"dtype": "float32",
|
| 1300 |
+
"format": "f32-to-bf16",
|
| 1301 |
+
"nbytes": 4096,
|
| 1302 |
+
"byteOffset": 20971520
|
| 1303 |
+
},
|
| 1304 |
+
{
|
| 1305 |
+
"name": "model.layers.8.post_attention_layernorm.weight",
|
| 1306 |
+
"shape": [
|
| 1307 |
+
2048
|
| 1308 |
+
],
|
| 1309 |
+
"dtype": "float32",
|
| 1310 |
+
"format": "f32-to-bf16",
|
| 1311 |
+
"nbytes": 4096,
|
| 1312 |
+
"byteOffset": 20975616
|
| 1313 |
+
}
|
| 1314 |
+
],
|
| 1315 |
+
"md5sum": "5a57388997fefe29f3788be628569150"
|
| 1316 |
+
},
|
| 1317 |
+
{
|
| 1318 |
+
"dataPath": "params_shard_45.bin",
|
| 1319 |
+
"format": "raw-shard",
|
| 1320 |
+
"nbytes": 33554432,
|
| 1321 |
+
"records": [
|
| 1322 |
+
{
|
| 1323 |
+
"name": "model.layers.9.mlp.down_proj.weight",
|
| 1324 |
+
"shape": [
|
| 1325 |
+
2048,
|
| 1326 |
+
8192
|
| 1327 |
+
],
|
| 1328 |
+
"dtype": "float32",
|
| 1329 |
+
"format": "f32-to-bf16",
|
| 1330 |
+
"nbytes": 33554432,
|
| 1331 |
+
"byteOffset": 0
|
| 1332 |
+
}
|
| 1333 |
+
],
|
| 1334 |
+
"md5sum": "e2d663fbf063a76d8845a1117834610f"
|
| 1335 |
+
},
|
| 1336 |
+
{
|
| 1337 |
+
"dataPath": "params_shard_46.bin",
|
| 1338 |
+
"format": "raw-shard",
|
| 1339 |
+
"nbytes": 67108864,
|
| 1340 |
+
"records": [
|
| 1341 |
+
{
|
| 1342 |
+
"name": "model.layers.9.mlp.gate_up_proj.weight",
|
| 1343 |
+
"shape": [
|
| 1344 |
+
16384,
|
| 1345 |
+
2048
|
| 1346 |
+
],
|
| 1347 |
+
"dtype": "float32",
|
| 1348 |
+
"format": "f32-to-bf16",
|
| 1349 |
+
"nbytes": 67108864,
|
| 1350 |
+
"byteOffset": 0
|
| 1351 |
+
}
|
| 1352 |
+
],
|
| 1353 |
+
"md5sum": "50e4119a748b23e67bfa10d1ec8e1f00"
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"dataPath": "params_shard_47.bin",
|
| 1357 |
+
"format": "raw-shard",
|
| 1358 |
+
"nbytes": 20979712,
|
| 1359 |
+
"records": [
|
| 1360 |
+
{
|
| 1361 |
+
"name": "model.layers.8.self_attn.qkv_proj.weight",
|
| 1362 |
+
"shape": [
|
| 1363 |
+
3072,
|
| 1364 |
+
2048
|
| 1365 |
+
],
|
| 1366 |
+
"dtype": "float32",
|
| 1367 |
+
"format": "f32-to-bf16",
|
| 1368 |
+
"nbytes": 12582912,
|
| 1369 |
+
"byteOffset": 0
|
| 1370 |
+
},
|
| 1371 |
+
{
|
| 1372 |
+
"name": "model.layers.8.self_attn.o_proj.weight",
|
| 1373 |
+
"shape": [
|
| 1374 |
+
2048,
|
| 1375 |
+
2048
|
| 1376 |
+
],
|
| 1377 |
+
"dtype": "float32",
|
| 1378 |
+
"format": "f32-to-bf16",
|
| 1379 |
+
"nbytes": 8388608,
|
| 1380 |
+
"byteOffset": 12582912
|
| 1381 |
+
},
|
| 1382 |
+
{
|
| 1383 |
+
"name": "model.layers.9.input_layernorm.weight",
|
| 1384 |
+
"shape": [
|
| 1385 |
+
2048
|
| 1386 |
+
],
|
| 1387 |
+
"dtype": "float32",
|
| 1388 |
+
"format": "f32-to-bf16",
|
| 1389 |
+
"nbytes": 4096,
|
| 1390 |
+
"byteOffset": 20971520
|
| 1391 |
+
},
|
| 1392 |
+
{
|
| 1393 |
+
"name": "model.layers.9.post_attention_layernorm.weight",
|
| 1394 |
+
"shape": [
|
| 1395 |
+
2048
|
| 1396 |
+
],
|
| 1397 |
+
"dtype": "float32",
|
| 1398 |
+
"format": "f32-to-bf16",
|
| 1399 |
+
"nbytes": 4096,
|
| 1400 |
+
"byteOffset": 20975616
|
| 1401 |
+
}
|
| 1402 |
+
],
|
| 1403 |
+
"md5sum": "c7f736b657c13231c2c106aab8827f06"
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"dataPath": "params_shard_48.bin",
|
| 1407 |
+
"format": "raw-shard",
|
| 1408 |
+
"nbytes": 20975616,
|
| 1409 |
+
"records": [
|
| 1410 |
+
{
|
| 1411 |
+
"name": "model.layers.9.self_attn.qkv_proj.weight",
|
| 1412 |
+
"shape": [
|
| 1413 |
+
3072,
|
| 1414 |
+
2048
|
| 1415 |
+
],
|
| 1416 |
+
"dtype": "float32",
|
| 1417 |
+
"format": "f32-to-bf16",
|
| 1418 |
+
"nbytes": 12582912,
|
| 1419 |
+
"byteOffset": 0
|
| 1420 |
+
},
|
| 1421 |
+
{
|
| 1422 |
+
"name": "model.layers.9.self_attn.o_proj.weight",
|
| 1423 |
+
"shape": [
|
| 1424 |
+
2048,
|
| 1425 |
+
2048
|
| 1426 |
+
],
|
| 1427 |
+
"dtype": "float32",
|
| 1428 |
+
"format": "f32-to-bf16",
|
| 1429 |
+
"nbytes": 8388608,
|
| 1430 |
+
"byteOffset": 12582912
|
| 1431 |
+
},
|
| 1432 |
+
{
|
| 1433 |
+
"name": "model.norm.weight",
|
| 1434 |
+
"shape": [
|
| 1435 |
+
2048
|
| 1436 |
+
],
|
| 1437 |
+
"dtype": "float32",
|
| 1438 |
+
"format": "f32-to-bf16",
|
| 1439 |
+
"nbytes": 4096,
|
| 1440 |
+
"byteOffset": 20971520
|
| 1441 |
+
}
|
| 1442 |
+
],
|
| 1443 |
+
"md5sum": "2484e69deb5afeb91287322eac29c4f8"
|
| 1444 |
+
}
|
| 1445 |
+
]
|
| 1446 |
+
}
|
params_shard_0.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b111063841df6851fa28395ca43f6570c81486a16d4830d0026cb62cf14a7b5d
|
| 3 |
+
size 525336576
|
params_shard_1.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2751b067ffdfc7c9b3501307f9b0dedf655c2a2ced5c13e67a27b02a497dbb30
|
| 3 |
+
size 33554432
|
params_shard_10.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5fec79d8e298aac768aaeaa71871877fe60291bcc14c236c56c345bbab5a00b2
|
| 3 |
+
size 67108864
|
params_shard_11.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f0f2f6e8a15dd3ef655d7f76d3ef58cd208b5f34058ffe88f43242ddc8cbe955
|
| 3 |
+
size 20979712
|
params_shard_12.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b9eca1a84eb57c68fb3c4b33a1c5f6688a8605c31bd42dd1af5c04063cbfb378
|
| 3 |
+
size 33554432
|
params_shard_13.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ee0d12905ad47315b08849029622d665c60e97396f35b5307c25079c6afefe5b
|
| 3 |
+
size 67108864
|
params_shard_14.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6d3e0f88920cc5b66aa7b0fa5ba87d51e1bbdb21de6c6227f93e0a5a87d9070f
|
| 3 |
+
size 20979712
|
params_shard_15.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1eda51a024f20c599fbf8dd0041a16419676661415019a4a050722b56dc82a9e
|
| 3 |
+
size 33554432
|
params_shard_16.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4dd082bad03d500d58887307c0f8eba7036173bcfc6cd0b0acd2ad4023231e04
|
| 3 |
+
size 67108864
|
params_shard_17.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1d66d0cc6d0128c6e83b7bff692922161ddb1350d0f467c09ffd024890d26421
|
| 3 |
+
size 20979712
|
params_shard_18.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bc01f83069720ca78330773cc349bd8bd9ce27511a594f0a874ad81dd1892b5c
|
| 3 |
+
size 33554432
|
params_shard_19.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:619592501a586e71828897bba1dd0447f675ffece9aecf135fb317d40bbf5728
|
| 3 |
+
size 67108864
|
params_shard_2.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:76f4c8e627a778e1ffa7369a3a32981e90f2a104319753aefac4c7565c6fa731
|
| 3 |
+
size 67108864
|
params_shard_20.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d958501265d40f9ef4cd9ae95c472d2fe74fe0695e7173f8d7369d58cf04683e
|
| 3 |
+
size 20979712
|
params_shard_21.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:284ca029330d3ce6413f8ecd0c38dd6bd0dd0077d2facf182bbfe2074827e72a
|
| 3 |
+
size 33554432
|
params_shard_22.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:01d69ffac141f44459044e61873d16f8d9fff64f978e4ef06cc7a62dee0e891c
|
| 3 |
+
size 67108864
|
params_shard_23.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d8ffd629d0ed973ae01b4f97d87cecb48ccfebf7ae94f8ec171b51d22046fb7a
|
| 3 |
+
size 20979712
|
params_shard_24.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c6c322e8f8a3641339375d21dfa0e52b6bec3976f5a8ede49f200dec8bc38149
|
| 3 |
+
size 33554432
|
params_shard_25.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9b68611f11765f27e65c60bc5a4391b9e7bffbd62da6a0039c01f8d7e39ee210
|
| 3 |
+
size 67108864
|
params_shard_26.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:23673cab99976fa38cee9b9bc53c9f1d40b5e9686ad21d9b32a7827f3dfccb59
|
| 3 |
+
size 20979712
|
params_shard_27.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:87981c1be8b95a602ed901fa3fc525b4ba83e2e1ef4769b9f382073b408e17f7
|
| 3 |
+
size 33554432
|
params_shard_28.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:712c6f7d3358449a33d0c42f5563a7df91315bb1c8208392722eb8d329e9bd81
|
| 3 |
+
size 67108864
|
params_shard_29.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8f85f4f5c404a1548aac2a8b6589c26e79e6a70550411b0ad6ee14822122ecc5
|
| 3 |
+
size 20979712
|
params_shard_3.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3a813f0b5f69255660f70c184476fe1e07380eae849ebb82ef774d923b2ec1bc
|
| 3 |
+
size 33554432
|
params_shard_30.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d40fe993e7ed4a0b51d71b02bf8b16761ce56b36f232f14e3c31c394f1c0804e
|
| 3 |
+
size 33554432
|
params_shard_31.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b762587add02e7b63f8ffab05a46f30d3cb3fa04710db88f0894a78ce192abb8
|
| 3 |
+
size 67108864
|
params_shard_32.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7f869262e90c2e4ed78d52bb227b57bb6731a3c85b1b52c2f2dbb42aaf6be21c
|
| 3 |
+
size 20979712
|
params_shard_33.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:eac72c3b0d2484e25de526c0869435f2581722547ca2ff19526a9f28ec06a2c4
|
| 3 |
+
size 33554432
|
params_shard_34.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5cf1039cd6f774e0d4a9ff4111a2abce43c46bf07b1f7c472a44d4f780c23663
|
| 3 |
+
size 67108864
|
params_shard_35.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4b98d5d31457778c761b58f658a49afb0076be3f7ecf55aeceec3fae7110da0c
|
| 3 |
+
size 20979712
|
params_shard_36.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:21d3162b619ec7e50359470bca94bb1a9900866179068ef7c0b6d577afd24c69
|
| 3 |
+
size 33554432
|
params_shard_37.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1b154094b220e60f814e0892f52004fd27d05fe46af23e4483fe70d7fff31ae1
|
| 3 |
+
size 67108864
|
params_shard_38.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3d0b88b362fac5b32e9609c0ab26197277b118a43a61bac5210045317a3e9a5e
|
| 3 |
+
size 20979712
|
params_shard_39.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a7c35432c958b20627cb04fa50b56429affc65085baebc8ba3603af31bb928f2
|
| 3 |
+
size 33554432
|
params_shard_4.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8bb6ade0e13361d86784563d721c7141e58f9b17cbd5df261de1a0e861a16b7a
|
| 3 |
+
size 67108864
|
params_shard_40.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:185db985b99858d6f3beeace72f38e639528e0b943a8a1cd81b101d3b3cae471
|
| 3 |
+
size 67108864
|
params_shard_41.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b74abe9959a32f904b1156963e46ae08e33f317055c2653d5a639bc4d2959e79
|
| 3 |
+
size 20979712
|
params_shard_42.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f665309b6599288f471acd10c5c6d109799dfa1087693b549fdf76fdf735843c
|
| 3 |
+
size 33554432
|
params_shard_43.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d0c4cc3b469adfe6521251ec0afdfbed7fc1981b9b80a6bbb8f6eed7f04795da
|
| 3 |
+
size 67108864
|
params_shard_44.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d36b1e0c801344cfcaefa2f98ce5e9187b17d4ec42b042d924eed4ceaaeea72b
|
| 3 |
+
size 20979712
|
params_shard_45.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1607dace1e9c113055b5d232141dd8938d84fc11c9e82ac50ab68830504f5da7
|
| 3 |
+
size 33554432
|
params_shard_46.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:678cc0c4b0deccc816101952e4129511543cefb40a47af72a34cf7d34279c16d
|
| 3 |
+
size 67108864
|
params_shard_47.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cedef3e2ff9d4c9778dda120ab80c82ab7fb09a360ad33b648d1cf98563aecf1
|
| 3 |
+
size 20979712
|
params_shard_48.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3e2cf0d445902f6dfcff13a47076c2f908adc1b2b99b276cd1eed41ec6529c76
|
| 3 |
+
size 20975616
|
params_shard_5.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:21c5a7920cfcc502e7e7c8faf63c7a74826a9a6636df11a703c86f700e7ac0c9
|
| 3 |
+
size 20987904
|
params_shard_6.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:39d89336af2cf06d717decc432cdf30706c798f77af5699a5de78ff08910091b
|
| 3 |
+
size 33554432
|
params_shard_7.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:155426c2069b8426af85978fb0ae63d6e6e09969144fe2758966d984abd42a51
|
| 3 |
+
size 67108864
|
params_shard_8.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:97453c83cc7bc80bb0e705aa8134d91cad229e2528e3675161b9cf02cd2bf243
|
| 3 |
+
size 20979712
|