Commit
·
1483955
1
Parent(s):
1fec38b
Add weights
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- .gitattributes +1 -0
- README.md +15 -0
- config.json +5 -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
.gitattributes
CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
README.md
CHANGED
@@ -1,3 +1,18 @@
|
|
1 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2 |
license: llama3.2
|
|
|
|
|
|
|
|
|
3 |
---
|
|
|
|
|
|
1 |
---
|
2 |
+
language:
|
3 |
+
- en
|
4 |
+
- de
|
5 |
+
- fr
|
6 |
+
- it
|
7 |
+
- pt
|
8 |
+
- hi
|
9 |
+
- es
|
10 |
+
- th
|
11 |
license: llama3.2
|
12 |
+
base_model: FuseAI/FuseChat-Llama-3.2-1B-Instruct
|
13 |
+
base_model_relation: quantized
|
14 |
+
library_name: mlc-llm
|
15 |
+
pipeline_tag: text-generation
|
16 |
---
|
17 |
+
|
18 |
+
Unquantized (fp16, the parent model is bf16) version of [FuseChat-Llama-3.2-1B-Instruct](https://huggingface.co/FuseAI/FuseChat-Llama-3.2-1B-Instruct) for inference with [Private LLM](http://privatellm.app).
|
config.json
ADDED
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"quantization_config": {
|
3 |
+
"bits": 4
|
4 |
+
}
|
5 |
+
}
|
ndarray-cache.json
ADDED
@@ -0,0 +1,1446 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"metadata": {
|
3 |
+
"ParamSize": 98,
|
4 |
+
"ParamBytes": 2471628800.0,
|
5 |
+
"BitsPerParam": 16.0
|
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": "float16",
|
20 |
+
"format": "f32-to-bf16",
|
21 |
+
"nbytes": 525336576,
|
22 |
+
"byteOffset": 0
|
23 |
+
}
|
24 |
+
],
|
25 |
+
"md5sum": "96ecea76fb745a56ee7bc9a00606f3da"
|
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": "float16",
|
39 |
+
"format": "f32-to-bf16",
|
40 |
+
"nbytes": 33554432,
|
41 |
+
"byteOffset": 0
|
42 |
+
}
|
43 |
+
],
|
44 |
+
"md5sum": "45ab6a597571f55d11310ad502ecd11c"
|
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": "float16",
|
58 |
+
"format": "f32-to-bf16",
|
59 |
+
"nbytes": 67108864,
|
60 |
+
"byteOffset": 0
|
61 |
+
}
|
62 |
+
],
|
63 |
+
"md5sum": "72068393e1767a06fd5d059251fefc72"
|
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": "float16",
|
77 |
+
"format": "f32-to-bf16",
|
78 |
+
"nbytes": 33554432,
|
79 |
+
"byteOffset": 0
|
80 |
+
}
|
81 |
+
],
|
82 |
+
"md5sum": "6fc65384fd5a6fb03c461e1022ea887f"
|
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": "float16",
|
96 |
+
"format": "f32-to-bf16",
|
97 |
+
"nbytes": 67108864,
|
98 |
+
"byteOffset": 0
|
99 |
+
}
|
100 |
+
],
|
101 |
+
"md5sum": "cee36a8591282bcb9d842d0f32f1f04c"
|
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": "float16",
|
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": "float16",
|
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": "float16",
|
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": "float16",
|
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": "float16",
|
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": "float16",
|
166 |
+
"format": "f32-to-bf16",
|
167 |
+
"nbytes": 4096,
|
168 |
+
"byteOffset": 20983808
|
169 |
+
}
|
170 |
+
],
|
171 |
+
"md5sum": "2f7e6171ac0351f78163af8b1a6e4762"
|
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": "float16",
|
185 |
+
"format": "f32-to-bf16",
|
186 |
+
"nbytes": 33554432,
|
187 |
+
"byteOffset": 0
|
188 |
+
}
|
189 |
+
],
|
190 |
+
"md5sum": "ed36c50971738bdd08ae2ab1150820fd"
|
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": "float16",
|
204 |
+
"format": "f32-to-bf16",
|
205 |
+
"nbytes": 67108864,
|
206 |
+
"byteOffset": 0
|
207 |
+
}
|
208 |
+
],
|
209 |
+
"md5sum": "47e9ad785e2c976074789c8b5d83ab5a"
|
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": "float16",
|
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": "float16",
|
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": "float16",
|
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": "float16",
|
254 |
+
"format": "f32-to-bf16",
|
255 |
+
"nbytes": 4096,
|
256 |
+
"byteOffset": 20975616
|
257 |
+
}
|
258 |
+
],
|
259 |
+
"md5sum": "3063f6be2136e6ed98c1d73b1e0ccaab"
|
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": "float16",
|
273 |
+
"format": "f32-to-bf16",
|
274 |
+
"nbytes": 33554432,
|
275 |
+
"byteOffset": 0
|
276 |
+
}
|
277 |
+
],
|
278 |
+
"md5sum": "1264f1a44eb9ab68745d01ea53da5e0b"
|
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": "float16",
|
292 |
+
"format": "f32-to-bf16",
|
293 |
+
"nbytes": 67108864,
|
294 |
+
"byteOffset": 0
|
295 |
+
}
|
296 |
+
],
|
297 |
+
"md5sum": "a19047b7973f1066042d0bedaac882b8"
|
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": "float16",
|
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": "float16",
|
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": "float16",
|
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": "float16",
|
342 |
+
"format": "f32-to-bf16",
|
343 |
+
"nbytes": 4096,
|
344 |
+
"byteOffset": 20975616
|
345 |
+
}
|
346 |
+
],
|
347 |
+
"md5sum": "4e8e76bfd35611401d5396504f54c276"
|
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": "float16",
|
361 |
+
"format": "f32-to-bf16",
|
362 |
+
"nbytes": 33554432,
|
363 |
+
"byteOffset": 0
|
364 |
+
}
|
365 |
+
],
|
366 |
+
"md5sum": "ae0e5310659ab9716e61d03ec2114693"
|
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": "float16",
|
380 |
+
"format": "f32-to-bf16",
|
381 |
+
"nbytes": 67108864,
|
382 |
+
"byteOffset": 0
|
383 |
+
}
|
384 |
+
],
|
385 |
+
"md5sum": "f6a2b966db0ff70ba3125c96a5e6f8e0"
|
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": "float16",
|
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": "float16",
|
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": "float16",
|
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": "float16",
|
430 |
+
"format": "f32-to-bf16",
|
431 |
+
"nbytes": 4096,
|
432 |
+
"byteOffset": 20975616
|
433 |
+
}
|
434 |
+
],
|
435 |
+
"md5sum": "e8004ca46980e8515eab568c169618c4"
|
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": "float16",
|
449 |
+
"format": "f32-to-bf16",
|
450 |
+
"nbytes": 33554432,
|
451 |
+
"byteOffset": 0
|
452 |
+
}
|
453 |
+
],
|
454 |
+
"md5sum": "b06dbff200487e8963abfe2a18faa10c"
|
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": "float16",
|
468 |
+
"format": "f32-to-bf16",
|
469 |
+
"nbytes": 67108864,
|
470 |
+
"byteOffset": 0
|
471 |
+
}
|
472 |
+
],
|
473 |
+
"md5sum": "bd87851fed4a03435b0a28d9f42447c9"
|
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": "float16",
|
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": "float16",
|
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": "float16",
|
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": "float16",
|
518 |
+
"format": "f32-to-bf16",
|
519 |
+
"nbytes": 4096,
|
520 |
+
"byteOffset": 20975616
|
521 |
+
}
|
522 |
+
],
|
523 |
+
"md5sum": "27d40a71fc5d26371d8baa46c8d72b31"
|
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": "float16",
|
537 |
+
"format": "f32-to-bf16",
|
538 |
+
"nbytes": 33554432,
|
539 |
+
"byteOffset": 0
|
540 |
+
}
|
541 |
+
],
|
542 |
+
"md5sum": "83337b46f585fa676dcd5a8761ad3df0"
|
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": "float16",
|
556 |
+
"format": "f32-to-bf16",
|
557 |
+
"nbytes": 67108864,
|
558 |
+
"byteOffset": 0
|
559 |
+
}
|
560 |
+
],
|
561 |
+
"md5sum": "5082712a00fe7140ef9c9215846b3d60"
|
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": "float16",
|
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": "float16",
|
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": "float16",
|
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": "float16",
|
606 |
+
"format": "f32-to-bf16",
|
607 |
+
"nbytes": 4096,
|
608 |
+
"byteOffset": 20975616
|
609 |
+
}
|
610 |
+
],
|
611 |
+
"md5sum": "7f3978ef783e8e42895a2486316f9304"
|
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": "float16",
|
625 |
+
"format": "f32-to-bf16",
|
626 |
+
"nbytes": 33554432,
|
627 |
+
"byteOffset": 0
|
628 |
+
}
|
629 |
+
],
|
630 |
+
"md5sum": "622b5ce5905b898048f2eaf79caedfbd"
|
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": "float16",
|
644 |
+
"format": "f32-to-bf16",
|
645 |
+
"nbytes": 67108864,
|
646 |
+
"byteOffset": 0
|
647 |
+
}
|
648 |
+
],
|
649 |
+
"md5sum": "ace31b45f71cf2c0bf9b1056d74e1fe1"
|
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": "float16",
|
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": "float16",
|
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": "float16",
|
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": "float16",
|
694 |
+
"format": "f32-to-bf16",
|
695 |
+
"nbytes": 4096,
|
696 |
+
"byteOffset": 20975616
|
697 |
+
}
|
698 |
+
],
|
699 |
+
"md5sum": "2f7afc97c52867936a854ad44fe0c191"
|
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": "float16",
|
713 |
+
"format": "f32-to-bf16",
|
714 |
+
"nbytes": 33554432,
|
715 |
+
"byteOffset": 0
|
716 |
+
}
|
717 |
+
],
|
718 |
+
"md5sum": "494e89ca81bf466c8ce17b5ee5f85cdf"
|
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": "float16",
|
732 |
+
"format": "f32-to-bf16",
|
733 |
+
"nbytes": 67108864,
|
734 |
+
"byteOffset": 0
|
735 |
+
}
|
736 |
+
],
|
737 |
+
"md5sum": "13c70878199744779a54933d728727f8"
|
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": "float16",
|
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": "float16",
|
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": "float16",
|
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": "float16",
|
782 |
+
"format": "f32-to-bf16",
|
783 |
+
"nbytes": 4096,
|
784 |
+
"byteOffset": 20975616
|
785 |
+
}
|
786 |
+
],
|
787 |
+
"md5sum": "f6e5b110dc063026eb64f03b3fa20bee"
|
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": "float16",
|
801 |
+
"format": "f32-to-bf16",
|
802 |
+
"nbytes": 33554432,
|
803 |
+
"byteOffset": 0
|
804 |
+
}
|
805 |
+
],
|
806 |
+
"md5sum": "910d39d3f068b37b2df084f9762571b4"
|
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": "float16",
|
820 |
+
"format": "f32-to-bf16",
|
821 |
+
"nbytes": 67108864,
|
822 |
+
"byteOffset": 0
|
823 |
+
}
|
824 |
+
],
|
825 |
+
"md5sum": "49f61ec31d545e7569fb2a44a2b7b07f"
|
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": "float16",
|
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": "float16",
|
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": "float16",
|
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": "float16",
|
870 |
+
"format": "f32-to-bf16",
|
871 |
+
"nbytes": 4096,
|
872 |
+
"byteOffset": 20975616
|
873 |
+
}
|
874 |
+
],
|
875 |
+
"md5sum": "1eb0bdc450a0fca3053b47dc24368565"
|
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": "float16",
|
889 |
+
"format": "f32-to-bf16",
|
890 |
+
"nbytes": 33554432,
|
891 |
+
"byteOffset": 0
|
892 |
+
}
|
893 |
+
],
|
894 |
+
"md5sum": "f5b3c59b6ab43fe2f4892ad53d246905"
|
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": "float16",
|
908 |
+
"format": "f32-to-bf16",
|
909 |
+
"nbytes": 67108864,
|
910 |
+
"byteOffset": 0
|
911 |
+
}
|
912 |
+
],
|
913 |
+
"md5sum": "38d72936eaf8dc4bacf812d8fdb2d551"
|
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": "float16",
|
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": "float16",
|
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": "float16",
|
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": "float16",
|
958 |
+
"format": "f32-to-bf16",
|
959 |
+
"nbytes": 4096,
|
960 |
+
"byteOffset": 20975616
|
961 |
+
}
|
962 |
+
],
|
963 |
+
"md5sum": "773e500fd6e2ad9b4b9306b1e94af630"
|
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": "float16",
|
977 |
+
"format": "f32-to-bf16",
|
978 |
+
"nbytes": 33554432,
|
979 |
+
"byteOffset": 0
|
980 |
+
}
|
981 |
+
],
|
982 |
+
"md5sum": "90826d2d305b088531c014dd0ce66ec6"
|
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": "float16",
|
996 |
+
"format": "f32-to-bf16",
|
997 |
+
"nbytes": 67108864,
|
998 |
+
"byteOffset": 0
|
999 |
+
}
|
1000 |
+
],
|
1001 |
+
"md5sum": "4a44e23743fed303acca7cd7d910a8ae"
|
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": "float16",
|
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": "float16",
|
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": "float16",
|
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": "float16",
|
1046 |
+
"format": "f32-to-bf16",
|
1047 |
+
"nbytes": 4096,
|
1048 |
+
"byteOffset": 20975616
|
1049 |
+
}
|
1050 |
+
],
|
1051 |
+
"md5sum": "06a369e56d5da237caaa2b9cd972be08"
|
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": "float16",
|
1065 |
+
"format": "f32-to-bf16",
|
1066 |
+
"nbytes": 33554432,
|
1067 |
+
"byteOffset": 0
|
1068 |
+
}
|
1069 |
+
],
|
1070 |
+
"md5sum": "8ba19ff095dc05dfcea429ff62adc5d7"
|
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": "float16",
|
1084 |
+
"format": "f32-to-bf16",
|
1085 |
+
"nbytes": 67108864,
|
1086 |
+
"byteOffset": 0
|
1087 |
+
}
|
1088 |
+
],
|
1089 |
+
"md5sum": "3fbdebbc72ec4e5529e3e90a96d9ddec"
|
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": "float16",
|
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": "float16",
|
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": "float16",
|
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": "float16",
|
1134 |
+
"format": "f32-to-bf16",
|
1135 |
+
"nbytes": 4096,
|
1136 |
+
"byteOffset": 20975616
|
1137 |
+
}
|
1138 |
+
],
|
1139 |
+
"md5sum": "e0c825ac82f14adb91b255cec234cd72"
|
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": "float16",
|
1153 |
+
"format": "f32-to-bf16",
|
1154 |
+
"nbytes": 33554432,
|
1155 |
+
"byteOffset": 0
|
1156 |
+
}
|
1157 |
+
],
|
1158 |
+
"md5sum": "fef5beab293cc482e63947c7aa133778"
|
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": "float16",
|
1172 |
+
"format": "f32-to-bf16",
|
1173 |
+
"nbytes": 67108864,
|
1174 |
+
"byteOffset": 0
|
1175 |
+
}
|
1176 |
+
],
|
1177 |
+
"md5sum": "f219b3aeb641094c9506d63d34f61594"
|
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": "float16",
|
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": "float16",
|
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": "float16",
|
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": "float16",
|
1222 |
+
"format": "f32-to-bf16",
|
1223 |
+
"nbytes": 4096,
|
1224 |
+
"byteOffset": 20975616
|
1225 |
+
}
|
1226 |
+
],
|
1227 |
+
"md5sum": "afe26b0283ed633feaa3784374d866b3"
|
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": "float16",
|
1241 |
+
"format": "f32-to-bf16",
|
1242 |
+
"nbytes": 33554432,
|
1243 |
+
"byteOffset": 0
|
1244 |
+
}
|
1245 |
+
],
|
1246 |
+
"md5sum": "4f0cd14ab865c2f8553f79466e85a6ab"
|
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": "float16",
|
1260 |
+
"format": "f32-to-bf16",
|
1261 |
+
"nbytes": 67108864,
|
1262 |
+
"byteOffset": 0
|
1263 |
+
}
|
1264 |
+
],
|
1265 |
+
"md5sum": "e47e8214362118313253663b2c3ce43e"
|
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": "float16",
|
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": "float16",
|
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": "float16",
|
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": "float16",
|
1310 |
+
"format": "f32-to-bf16",
|
1311 |
+
"nbytes": 4096,
|
1312 |
+
"byteOffset": 20975616
|
1313 |
+
}
|
1314 |
+
],
|
1315 |
+
"md5sum": "8bdcc2a37898c5b61dc2e9d30f7ffcc2"
|
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": "float16",
|
1329 |
+
"format": "f32-to-bf16",
|
1330 |
+
"nbytes": 33554432,
|
1331 |
+
"byteOffset": 0
|
1332 |
+
}
|
1333 |
+
],
|
1334 |
+
"md5sum": "32e3d2650ce2fcb5ba7e8ebbcf7f8b2c"
|
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": "float16",
|
1348 |
+
"format": "f32-to-bf16",
|
1349 |
+
"nbytes": 67108864,
|
1350 |
+
"byteOffset": 0
|
1351 |
+
}
|
1352 |
+
],
|
1353 |
+
"md5sum": "fe1013105c419278c23b765e981940fb"
|
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": "float16",
|
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": "float16",
|
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": "float16",
|
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": "float16",
|
1398 |
+
"format": "f32-to-bf16",
|
1399 |
+
"nbytes": 4096,
|
1400 |
+
"byteOffset": 20975616
|
1401 |
+
}
|
1402 |
+
],
|
1403 |
+
"md5sum": "9a3e24a308a77520ec39767e540973be"
|
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": "float16",
|
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": "float16",
|
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": "float16",
|
1438 |
+
"format": "f32-to-bf16",
|
1439 |
+
"nbytes": 4096,
|
1440 |
+
"byteOffset": 20971520
|
1441 |
+
}
|
1442 |
+
],
|
1443 |
+
"md5sum": "4d899f886c5eb1df29d31ae4897fae61"
|
1444 |
+
}
|
1445 |
+
]
|
1446 |
+
}
|
params_shard_0.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0f3113fe3a8fbef23e4826a385ea2999bda2030b3cc28c35fd2c306ac9cc2449
|
3 |
+
size 525336576
|
params_shard_1.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9f56005f381e8cef2662d82dff751251075b99c4ac46c86863146af87c576422
|
3 |
+
size 33554432
|
params_shard_10.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c3ac19137d514f4a732adb00fb43008bbbbfa441b63d7ff2766da0b6cbe65a2f
|
3 |
+
size 67108864
|
params_shard_11.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:435482b808a886c8f3f955afd757759c37f0a4c2d0fdde3a1ab43c34c8ce5489
|
3 |
+
size 20979712
|
params_shard_12.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:18f838de8bbbe7ad00ec6f2c22c9364673a073ca469fa3b4971a49b3d8c7d163
|
3 |
+
size 33554432
|
params_shard_13.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c0eca514480039a369bdf506b8b632a38617e92352480d89d0f2f62c63a306b4
|
3 |
+
size 67108864
|
params_shard_14.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b04d29897cf2fa644fdc8eb283d32106e1516c443dd716bd5d9d492cd3e11f1d
|
3 |
+
size 20979712
|
params_shard_15.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f99d33369538ec4d80c80d12b6071c6a764b16648ca9b8b1f78326db3803e335
|
3 |
+
size 33554432
|
params_shard_16.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6a5d9c86ec72a6ca86bde1384b65c628f887c6d9f43c1238cf9836d8bfa8026c
|
3 |
+
size 67108864
|
params_shard_17.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:921ddf7c4296596db813d416309a31e09e2db5f16c415ae3ab2f75b22ec7b398
|
3 |
+
size 20979712
|
params_shard_18.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f69d7d52de1fda71b005573fa9aca62e5aa508a7fc252e16e007ed4a6a7afd6c
|
3 |
+
size 33554432
|
params_shard_19.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c5df0ce90af1a64574308d53e762216aa96d81f7b6a65c523259c5f809bc5e3b
|
3 |
+
size 67108864
|
params_shard_2.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5eeabe8be66a0045f6464320d1e03abfad4c50a1eda42fc3d3f11213cfddb355
|
3 |
+
size 67108864
|
params_shard_20.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:93b0a8e67237749c434d85ba8645a87be15260f04979aa5a0dea478b77b5e362
|
3 |
+
size 20979712
|
params_shard_21.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5f24bc4463dce1dde44210b2051b2bece9725249a24561fec255eab384df1e4c
|
3 |
+
size 33554432
|
params_shard_22.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e508ee1d4aacac7b6775082f2f3d400bb7605f0f63c0b7ccdab140f1852e6d37
|
3 |
+
size 67108864
|
params_shard_23.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:65f033520f834fa0c806792bf3912bb14b1c14371a3a206333bf541e856f24e9
|
3 |
+
size 20979712
|
params_shard_24.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:179f277b6abaf8e3dfe27af0f364fba256ebb213d80b703fc6a3ddfd7bd27e17
|
3 |
+
size 33554432
|
params_shard_25.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:69b6a702a511d418db85398656e489573b93e59fd87524acd3de8afcdb0ae579
|
3 |
+
size 67108864
|
params_shard_26.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e65cfd062c7218461f47cd033acaa1808a19106d70edab44c6d06a77e00ae912
|
3 |
+
size 20979712
|
params_shard_27.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d2b1c9dfc2641d129c31b70c3e52d230e1742cd4a6f1656b0e63208aa7b73efd
|
3 |
+
size 33554432
|
params_shard_28.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c188885902752da5a1d4293dbd3d4159318e444f69e99108b93cc4fe160be906
|
3 |
+
size 67108864
|
params_shard_29.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ce74a46a16620307eab87be44d9494a08219a903022e8a10309e4522edc1b932
|
3 |
+
size 20979712
|
params_shard_3.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8a4c8130c447c2b28130c07b71287eeb890565adfa412f2098c65c4f6fbdc148
|
3 |
+
size 33554432
|
params_shard_30.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dc7b92ee5b216f65643bc364a5a7ac0ff0ed367ea1d753d364e21fe593fc9478
|
3 |
+
size 33554432
|
params_shard_31.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3790f89594d0fa6e52055d031171107e40b84a9f059a6750eea73d781011cdaf
|
3 |
+
size 67108864
|
params_shard_32.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:048f0a1ca7faeb233c3bcaffd816e0767f15ff7019205090c63e5cdbd69b8d4a
|
3 |
+
size 20979712
|
params_shard_33.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f8cbe8047f97a16dca29d579949b756ba4ae8c2b25dc77e2d099fa2e530294c0
|
3 |
+
size 33554432
|
params_shard_34.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:69168891dce13f765c87f92d8a15b68c7d81ae22208b4e2676921f087921f2b9
|
3 |
+
size 67108864
|
params_shard_35.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:27163ec0b7fe0693bc8f2c92ad81b5e44773d351f8e960149a3de9ef8b0c41e2
|
3 |
+
size 20979712
|
params_shard_36.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9f1ab1bcaab1dc0b27ef23f558b63f3174eef383316315432cd664ac465582e7
|
3 |
+
size 33554432
|
params_shard_37.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b44cb323beac914f35110187fac5872d51d8a52530347dd92aef10610ab7c0b6
|
3 |
+
size 67108864
|
params_shard_38.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1ba25e79a55832e650ac34629c395cab21795862ff539bcbe129be0ebf2a269c
|
3 |
+
size 20979712
|
params_shard_39.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e3b61f8327067b72e90c5e4a3c3197404e1289b7fac1c6ee560c830cbfefc04a
|
3 |
+
size 33554432
|
params_shard_4.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:73e335eb68f67d56cac0415bc2af496cc0380b8ac345ead638496feda766a945
|
3 |
+
size 67108864
|
params_shard_40.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:70edb094aa5be38ef6e1b6f9d54f88613f5317137b7dcb4d4c244a30e02bacfc
|
3 |
+
size 67108864
|
params_shard_41.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d4b1d992553d4645eeeb85427d3e590b64394b304c44520e82ac8b442f012d48
|
3 |
+
size 20979712
|
params_shard_42.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7585419c0a26267b9f0b1b2448a332eace9591d97f30d7a9d86dc04b6c029909
|
3 |
+
size 33554432
|
params_shard_43.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:aa1c997bf3c4b0ad64e869f18fa67516b63523ba35fdfed10b09621382cf9333
|
3 |
+
size 67108864
|
params_shard_44.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ae25780d2ff035df814979efb395797aa70adceb702c0c828cc6a760b29fd50c
|
3 |
+
size 20979712
|
params_shard_45.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6bf50f3068d1d761d2e9846528377d582a20a1b4ed2ddae40cd211bd6fc61c1f
|
3 |
+
size 33554432
|
params_shard_46.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:97d894d666c36538c4dee92716f06bfd7e811f2849facc769a9eb4dee3d9c475
|
3 |
+
size 67108864
|
params_shard_47.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4498b980d02ab0cd60dbaa4abe94c2408fe0ef4ab880b75e6305f4b31255af44
|
3 |
+
size 20979712
|
params_shard_48.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1921951ae23775a0ce2c182325aa1a843742111267ed80c0cb07e8fcfa5977b4
|
3 |
+
size 20975616
|
params_shard_5.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f4358114b38faa979a97b4046cfbfd23af716f0726acd5958e16fdc51db87676
|
3 |
+
size 20987904
|
params_shard_6.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:86df0e7f469c1090b4bb0da57a8e052b3e15e2e5308ce07f86692ef44e211fdb
|
3 |
+
size 33554432
|