Upload folder using huggingface_hub
Browse files- config.json +46 -46
- model-00001-of-00012.safetensors +2 -2
- model-00002-of-00012.safetensors +2 -2
- model-00003-of-00012.safetensors +2 -2
- model-00004-of-00012.safetensors +2 -2
- model-00005-of-00012.safetensors +2 -2
- model-00006-of-00012.safetensors +2 -2
- model-00007-of-00012.safetensors +2 -2
- model-00008-of-00012.safetensors +2 -2
- model-00009-of-00012.safetensors +2 -2
- model-00010-of-00012.safetensors +2 -2
- model-00011-of-00012.safetensors +2 -2
- model-00012-of-00012.safetensors +2 -2
- model.safetensors.index.json +0 -0
config.json
CHANGED
@@ -24,65 +24,65 @@
|
|
24 |
"num_key_value_heads": 4,
|
25 |
"output_router_logits": false,
|
26 |
"quantization_config": {
|
27 |
-
"activation_scheme": "
|
28 |
"ignored_layers": [
|
29 |
-
"model.layers.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
30 |
"model.layers.23.mlp.gate",
|
31 |
"model.layers.27.mlp.shared_expert_gate",
|
32 |
-
"model.layers.
|
33 |
-
"model.layers.
|
34 |
-
"model.layers.
|
|
|
|
|
35 |
"model.layers.19.mlp.gate",
|
|
|
|
|
|
|
|
|
|
|
|
|
36 |
"model.layers.18.mlp.gate",
|
37 |
-
"model.layers.
|
38 |
-
"model.layers.27.mlp.gate",
|
39 |
-
"model.layers.14.mlp.gate",
|
40 |
"model.layers.22.mlp.shared_expert_gate",
|
|
|
|
|
|
|
41 |
"model.layers.21.mlp.gate",
|
42 |
-
"model.layers.24.mlp.shared_expert_gate",
|
43 |
-
"model.layers.18.mlp.shared_expert_gate",
|
44 |
-
"model.layers.26.mlp.shared_expert_gate",
|
45 |
-
"model.layers.13.mlp.shared_expert_gate",
|
46 |
-
"model.layers.6.mlp.gate",
|
47 |
-
"model.layers.0.mlp.gate",
|
48 |
-
"model.layers.12.mlp.gate",
|
49 |
"model.layers.2.mlp.shared_expert_gate",
|
50 |
-
"model.layers.
|
|
|
|
|
51 |
"model.layers.8.mlp.shared_expert_gate",
|
52 |
-
"model.layers.
|
53 |
-
"model.layers.
|
54 |
-
"model.layers.
|
55 |
-
"model.layers.
|
56 |
-
"model.layers.
|
57 |
-
"model.layers.
|
58 |
"model.layers.8.mlp.gate",
|
59 |
"model.layers.14.mlp.shared_expert_gate",
|
60 |
-
"model.layers.5.mlp.shared_expert_gate",
|
61 |
-
"model.layers.2.mlp.gate",
|
62 |
-
"model.layers.1.mlp.shared_expert_gate",
|
63 |
-
"model.layers.6.mlp.shared_expert_gate",
|
64 |
-
"model.layers.12.mlp.shared_expert_gate",
|
65 |
-
"model.layers.22.mlp.gate",
|
66 |
"model.layers.16.mlp.shared_expert_gate",
|
67 |
-
"model.layers.
|
68 |
-
"model.layers.
|
69 |
-
"model.layers.19.mlp.shared_expert_gate",
|
70 |
-
"model.layers.23.mlp.shared_expert_gate",
|
71 |
-
"model.layers.3.mlp.gate",
|
72 |
-
"lm_head",
|
73 |
-
"model.layers.3.mlp.shared_expert_gate",
|
74 |
-
"model.layers.11.mlp.gate",
|
75 |
"model.layers.1.mlp.gate",
|
76 |
-
"model.layers.
|
77 |
-
"model.layers.
|
78 |
-
"model.layers.
|
79 |
-
"model.layers.
|
80 |
-
"model.layers.11.mlp.shared_expert_gate",
|
81 |
-
"model.layers.15.mlp.shared_expert_gate",
|
82 |
-
"model.layers.9.mlp.gate",
|
83 |
-
"model.layers.16.mlp.gate",
|
84 |
-
"model.layers.5.mlp.gate",
|
85 |
-
"model.layers.24.mlp.gate"
|
86 |
],
|
87 |
"kv_cache_scheme": "static",
|
88 |
"quant_method": "fp8"
|
|
|
24 |
"num_key_value_heads": 4,
|
25 |
"output_router_logits": false,
|
26 |
"quantization_config": {
|
27 |
+
"activation_scheme": "static",
|
28 |
"ignored_layers": [
|
29 |
+
"model.layers.21.mlp.shared_expert_gate",
|
30 |
+
"model.layers.5.mlp.shared_expert_gate",
|
31 |
+
"model.layers.25.mlp.shared_expert_gate",
|
32 |
+
"model.layers.20.mlp.shared_expert_gate",
|
33 |
+
"model.layers.7.mlp.shared_expert_gate",
|
34 |
+
"model.layers.19.mlp.shared_expert_gate",
|
35 |
+
"lm_head",
|
36 |
+
"model.layers.14.mlp.gate",
|
37 |
+
"model.layers.16.mlp.gate",
|
38 |
+
"model.layers.15.mlp.shared_expert_gate",
|
39 |
+
"model.layers.17.mlp.shared_expert_gate",
|
40 |
+
"model.layers.5.mlp.gate",
|
41 |
+
"model.layers.4.mlp.gate",
|
42 |
+
"model.layers.10.mlp.gate",
|
43 |
+
"model.layers.17.mlp.gate",
|
44 |
"model.layers.23.mlp.gate",
|
45 |
"model.layers.27.mlp.shared_expert_gate",
|
46 |
+
"model.layers.0.mlp.shared_expert_gate",
|
47 |
+
"model.layers.27.mlp.gate",
|
48 |
+
"model.layers.12.mlp.gate",
|
49 |
+
"model.layers.3.mlp.shared_expert_gate",
|
50 |
+
"model.layers.7.mlp.gate",
|
51 |
"model.layers.19.mlp.gate",
|
52 |
+
"model.layers.24.mlp.gate",
|
53 |
+
"model.layers.9.mlp.gate",
|
54 |
+
"model.layers.6.mlp.gate",
|
55 |
+
"model.layers.10.mlp.shared_expert_gate",
|
56 |
+
"model.layers.11.mlp.shared_expert_gate",
|
57 |
+
"model.layers.12.mlp.shared_expert_gate",
|
58 |
"model.layers.18.mlp.gate",
|
59 |
+
"model.layers.22.mlp.gate",
|
|
|
|
|
60 |
"model.layers.22.mlp.shared_expert_gate",
|
61 |
+
"model.layers.3.mlp.gate",
|
62 |
+
"model.layers.9.mlp.shared_expert_gate",
|
63 |
+
"model.layers.13.mlp.gate",
|
64 |
"model.layers.21.mlp.gate",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
65 |
"model.layers.2.mlp.shared_expert_gate",
|
66 |
+
"model.layers.24.mlp.shared_expert_gate",
|
67 |
+
"model.layers.20.mlp.gate",
|
68 |
+
"model.layers.25.mlp.gate",
|
69 |
"model.layers.8.mlp.shared_expert_gate",
|
70 |
+
"model.layers.2.mlp.gate",
|
71 |
+
"model.layers.13.mlp.shared_expert_gate",
|
72 |
+
"model.layers.23.mlp.shared_expert_gate",
|
73 |
+
"model.layers.15.mlp.gate",
|
74 |
+
"model.layers.26.mlp.shared_expert_gate",
|
75 |
+
"model.layers.26.mlp.gate",
|
76 |
"model.layers.8.mlp.gate",
|
77 |
"model.layers.14.mlp.shared_expert_gate",
|
|
|
|
|
|
|
|
|
|
|
|
|
78 |
"model.layers.16.mlp.shared_expert_gate",
|
79 |
+
"model.layers.18.mlp.shared_expert_gate",
|
80 |
+
"model.layers.0.mlp.gate",
|
|
|
|
|
|
|
|
|
|
|
|
|
81 |
"model.layers.1.mlp.gate",
|
82 |
+
"model.layers.11.mlp.gate",
|
83 |
+
"model.layers.6.mlp.shared_expert_gate",
|
84 |
+
"model.layers.1.mlp.shared_expert_gate",
|
85 |
+
"model.layers.4.mlp.shared_expert_gate"
|
|
|
|
|
|
|
|
|
|
|
|
|
86 |
],
|
87 |
"kv_cache_scheme": "static",
|
88 |
"quant_method": "fp8"
|
model-00001-of-00012.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6e38c6117c88b9c8be60ba0e20819f0142ba7b8bf61e69c693a347e44abd48a7
|
3 |
+
size 4965711264
|
model-00002-of-00012.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c080c598df03b935e9229cc85e065df508995be818694cb415fef751df90f2c8
|
3 |
+
size 4998368852
|
model-00003-of-00012.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5047c6d2200e6089b1dea7e65d31a620cb5a5a6a3596e2d1aef8ed22515ac3c9
|
3 |
+
size 4986872824
|
model-00004-of-00012.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ca409dc3dd756936e2a8f45d3ee6998d10fc89896ecb0cc598abf55d1302118a
|
3 |
+
size 4998366420
|
model-00005-of-00012.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:251ebfad1ce1b93a9d9290a147080d0a260eafe59cef45c2643b94c6e8677719
|
3 |
+
size 4996049392
|
model-00006-of-00012.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bba86a42ee4f7549df4119dca2a20d77e1dda8a76e34128d22ea1f9a3a3dae4c
|
3 |
+
size 4998367884
|
model-00007-of-00012.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e0676d133c2314b3f83cb36e792586bc2370042ed13b191092732a6b5f1ea132
|
3 |
+
size 4996049744
|
model-00008-of-00012.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b108b7edcf8961ff9b6d6ed1125a978b7f0c22655c7de5691dfe1124fd52382a
|
3 |
+
size 4998367876
|
model-00009-of-00012.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5f66ef7f71945785ef45c959e4ee53fb23b0fe202a9dc63c0f7e8976fe1fee7d
|
3 |
+
size 4996049744
|
model-00010-of-00012.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:270f7f0097b8efaa59cc4bc4a4233d3e6851198bd04056a9077694e1720f122e
|
3 |
+
size 4998367876
|
model-00011-of-00012.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7c4604c1bbfd6bd284f299a6897a92c6c8e9eed0fc5c7da2488c30d6ff3a612a
|
3 |
+
size 4996049736
|
model-00012-of-00012.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3b02ce65e01ef81d47c1f9ed382ffcb9e2330a4132af2d7a90ff97f0ee87c2b0
|
3 |
+
size 3577948452
|
model.safetensors.index.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|