Hugging Face's logo

Quicksilver1
/
DOE-Model-test-v2

Safetensors
phi3
custom_code
Model card Files
xet
Community
Quicksilver1 commited on
Commit
58122a3
·
verified ·
1 Parent(s): 5a6c0d8

Upload folder using huggingface_hub

Browse files
Files changed (9) hide show
  1. config.json +142 -0
  2. generation_config.json +7 -0
  3. model-00001-of-00006.safetensors +3 -0
  4. model-00002-of-00006.safetensors +3 -0
  5. model-00003-of-00006.safetensors +3 -0
  6. model-00004-of-00006.safetensors +3 -0
  7. model-00005-of-00006.safetensors +3 -0
  8. model-00006-of-00006.safetensors +3 -0
  9. model.safetensors.index.json +267 -0
config.json ADDED
@@ -0,0 +1,142 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/content/gdrive/MyDrive/Colab Notebooks/DOE/src/models/weights/Phi-3ex",
3
+ "ar_loss_weight": 0.7,
4
+ "architectures": [
5
+ "Phi3exForCausalLM"
6
+ ],
7
+ "attention_bias": false,
8
+ "attention_dropout": 0.0,
9
+ "auto_map": {
10
+ "AutoConfig": "configuration_phi3.Phi3Config",
11
+ "AutoModelForCausalLM": "modeling_phi3.Phi3ForCausalLM"
12
+ },
13
+ "bos_token_id": 1,
14
+ "embd_pdrop": 0.0,
15
+ "eos_token_id": 32000,
16
+ "gating_loss_weight": 0.3,
17
+ "hidden_act": "silu",
18
+ "hidden_size": 3072,
19
+ "initializer_range": 0.02,
20
+ "intermediate_size": 8192,
21
+ "max_position_embeddings": 131072,
22
+ "model_type": "phi3",
23
+ "num_attention_heads": 32,
24
+ "num_hidden_layers": 32,
25
+ "num_key_value_heads": 32,
26
+ "num_local_experts": 2,
27
+ "original_max_position_embeddings": 4096,
28
+ "pad_token_id": 32000,
29
+ "resid_pdrop": 0.0,
30
+ "rms_norm_eps": 1e-05,
31
+ "rope_scaling": {
32
+ "long_factor": [
33
+ 1.0299999713897705,
34
+ 1.0499999523162842,
35
+ 1.0499999523162842,
36
+ 1.0799999237060547,
37
+ 1.2299998998641968,
38
+ 1.2299998998641968,
39
+ 1.2999999523162842,
40
+ 1.4499999284744263,
41
+ 1.5999999046325684,
42
+ 1.6499998569488525,
43
+ 1.8999998569488525,
44
+ 2.859999895095825,
45
+ 3.68999981880188,
46
+ 5.419999599456787,
47
+ 5.489999771118164,
48
+ 5.489999771118164,
49
+ 9.09000015258789,
50
+ 11.579999923706055,
51
+ 15.65999984741211,
52
+ 15.769999504089355,
53
+ 15.789999961853027,
54
+ 18.360000610351562,
55
+ 21.989999771118164,
56
+ 23.079999923706055,
57
+ 30.009998321533203,
58
+ 32.35000228881836,
59
+ 32.590003967285156,
60
+ 35.56000518798828,
61
+ 39.95000457763672,
62
+ 53.840003967285156,
63
+ 56.20000457763672,
64
+ 57.95000457763672,
65
+ 59.29000473022461,
66
+ 59.77000427246094,
67
+ 59.920005798339844,
68
+ 61.190006256103516,
69
+ 61.96000671386719,
70
+ 62.50000762939453,
71
+ 63.3700065612793,
72
+ 63.48000717163086,
73
+ 63.48000717163086,
74
+ 63.66000747680664,
75
+ 63.850006103515625,
76
+ 64.08000946044922,
77
+ 64.760009765625,
78
+ 64.80001068115234,
79
+ 64.81001281738281,
80
+ 64.81001281738281
81
+ ],
82
+ "short_factor": [
83
+ 1.05,
84
+ 1.05,
85
+ 1.05,
86
+ 1.1,
87
+ 1.1,
88
+ 1.1500000000000001,
89
+ 1.2000000000000002,
90
+ 1.2500000000000002,
91
+ 1.3000000000000003,
92
+ 1.3500000000000003,
93
+ 1.5000000000000004,
94
+ 2.000000000000001,
95
+ 2.000000000000001,
96
+ 2.000000000000001,
97
+ 2.000000000000001,
98
+ 2.000000000000001,
99
+ 2.000000000000001,
100
+ 2.000000000000001,
101
+ 2.000000000000001,
102
+ 2.000000000000001,
103
+ 2.000000000000001,
104
+ 2.000000000000001,
105
+ 2.000000000000001,
106
+ 2.000000000000001,
107
+ 2.000000000000001,
108
+ 2.000000000000001,
109
+ 2.000000000000001,
110
+ 2.000000000000001,
111
+ 2.000000000000001,
112
+ 2.000000000000001,
113
+ 2.000000000000001,
114
+ 2.000000000000001,
115
+ 2.0500000000000007,
116
+ 2.0500000000000007,
117
+ 2.0500000000000007,
118
+ 2.1000000000000005,
119
+ 2.1000000000000005,
120
+ 2.1000000000000005,
121
+ 2.1500000000000004,
122
+ 2.1500000000000004,
123
+ 2.3499999999999996,
124
+ 2.549999999999999,
125
+ 2.5999999999999988,
126
+ 2.5999999999999988,
127
+ 2.7499999999999982,
128
+ 2.849999999999998,
129
+ 2.849999999999998,
130
+ 2.9499999999999975
131
+ ],
132
+ "type": "su"
133
+ },
134
+ "rope_theta": 10000.0,
135
+ "sliding_window": 262144,
136
+ "threshold": 0.5,
137
+ "tie_word_embeddings": false,
138
+ "torch_dtype": "float32",
139
+ "transformers_version": "4.42.4",
140
+ "use_cache": true,
141
+ "vocab_size": 32064
142
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 32000,
5
+ "pad_token_id": 32000,
6
+ "transformers_version": "4.42.4"
7
+ }
model-00001-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1cadfed14309bafb2045637fbd6798ad47dddf5c4c7f43c73aae6fb8139938f0
3
+ size 4915365464
model-00002-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5518115a170ae661ca0fe29caf3f760f0f6c328c13298b39d70e1adfd0d091d8
3
+ size 4970403984
model-00003-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50e7d8cce753db44c9b55ede53743b8871071fc72f8bedcdc4e98f0dc3614205
3
+ size 4945262888
model-00004-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:745504d1e0ad11bb4a1dacbe1e32b3eb5f390e1d42714d37d4d6dc53cd1b7300
3
+ size 4983011744
model-00005-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc8919c6b9430632d9ff56440cdb900939bd302e2221889c758754d7c0efbc20
3
+ size 4831991760
model-00006-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e419afd9038fca099f76e54985e8af4afd11f43a9fd4331439b28971640fcd8c
3
+ size 302014840
model.safetensors.index.json ADDED
@@ -0,0 +1,267 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 24948019200
4
+ },
5
+ "weight_map": {
6
+ "gating_model.gate.weight": "model-00006-of-00006.safetensors",
7
+ "lm_head.weight": "model-00001-of-00006.safetensors",
8
+ "model.embed_tokens.weight": "model-00001-of-00006.safetensors",
9
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors",
10
+ "model.layers.0.mlp.experts.0.down_proj.weight": "model-00001-of-00006.safetensors",
11
+ "model.layers.0.mlp.experts.0.gate_up_proj.weight": "model-00001-of-00006.safetensors",
12
+ "model.layers.0.mlp.experts.1.down_proj.weight": "model-00001-of-00006.safetensors",
13
+ "model.layers.0.mlp.experts.1.gate_up_proj.weight": "model-00001-of-00006.safetensors",
14
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
15
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
16
+ "model.layers.0.self_attn.qkv_proj.weight": "model-00001-of-00006.safetensors",
17
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors",
18
+ "model.layers.1.mlp.experts.0.down_proj.weight": "model-00001-of-00006.safetensors",
19
+ "model.layers.1.mlp.experts.0.gate_up_proj.weight": "model-00001-of-00006.safetensors",
20
+ "model.layers.1.mlp.experts.1.down_proj.weight": "model-00001-of-00006.safetensors",
21
+ "model.layers.1.mlp.experts.1.gate_up_proj.weight": "model-00001-of-00006.safetensors",
22
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
23
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
24
+ "model.layers.1.self_attn.qkv_proj.weight": "model-00001-of-00006.safetensors",
25
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00006.safetensors",
26
+ "model.layers.10.mlp.experts.0.down_proj.weight": "model-00002-of-00006.safetensors",
27
+ "model.layers.10.mlp.experts.0.gate_up_proj.weight": "model-00002-of-00006.safetensors",
28
+ "model.layers.10.mlp.experts.1.down_proj.weight": "model-00002-of-00006.safetensors",
29
+ "model.layers.10.mlp.experts.1.gate_up_proj.weight": "model-00002-of-00006.safetensors",
30
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
31
+ "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
32
+ "model.layers.10.self_attn.qkv_proj.weight": "model-00002-of-00006.safetensors",
33
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00006.safetensors",
34
+ "model.layers.11.mlp.experts.0.down_proj.weight": "model-00002-of-00006.safetensors",
35
+ "model.layers.11.mlp.experts.0.gate_up_proj.weight": "model-00002-of-00006.safetensors",
36
+ "model.layers.11.mlp.experts.1.down_proj.weight": "model-00002-of-00006.safetensors",
37
+ "model.layers.11.mlp.experts.1.gate_up_proj.weight": "model-00002-of-00006.safetensors",
38
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
39
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
40
+ "model.layers.11.self_attn.qkv_proj.weight": "model-00002-of-00006.safetensors",
41
+ "model.layers.12.input_layernorm.weight": "model-00003-of-00006.safetensors",
42
+ "model.layers.12.mlp.experts.0.down_proj.weight": "model-00003-of-00006.safetensors",
43
+ "model.layers.12.mlp.experts.0.gate_up_proj.weight": "model-00003-of-00006.safetensors",
44
+ "model.layers.12.mlp.experts.1.down_proj.weight": "model-00003-of-00006.safetensors",
45
+ "model.layers.12.mlp.experts.1.gate_up_proj.weight": "model-00003-of-00006.safetensors",
46
+ "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
47
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
48
+ "model.layers.12.self_attn.qkv_proj.weight": "model-00003-of-00006.safetensors",
49
+ "model.layers.13.input_layernorm.weight": "model-00003-of-00006.safetensors",
50
+ "model.layers.13.mlp.experts.0.down_proj.weight": "model-00003-of-00006.safetensors",
51
+ "model.layers.13.mlp.experts.0.gate_up_proj.weight": "model-00003-of-00006.safetensors",
52
+ "model.layers.13.mlp.experts.1.down_proj.weight": "model-00003-of-00006.safetensors",
53
+ "model.layers.13.mlp.experts.1.gate_up_proj.weight": "model-00003-of-00006.safetensors",
54
+ "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
55
+ "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
56
+ "model.layers.13.self_attn.qkv_proj.weight": "model-00003-of-00006.safetensors",
57
+ "model.layers.14.input_layernorm.weight": "model-00003-of-00006.safetensors",
58
+ "model.layers.14.mlp.experts.0.down_proj.weight": "model-00003-of-00006.safetensors",
59
+ "model.layers.14.mlp.experts.0.gate_up_proj.weight": "model-00003-of-00006.safetensors",
60
+ "model.layers.14.mlp.experts.1.down_proj.weight": "model-00003-of-00006.safetensors",
61
+ "model.layers.14.mlp.experts.1.gate_up_proj.weight": "model-00003-of-00006.safetensors",
62
+ "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
63
+ "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
64
+ "model.layers.14.self_attn.qkv_proj.weight": "model-00003-of-00006.safetensors",
65
+ "model.layers.15.input_layernorm.weight": "model-00003-of-00006.safetensors",
66
+ "model.layers.15.mlp.experts.0.down_proj.weight": "model-00003-of-00006.safetensors",
67
+ "model.layers.15.mlp.experts.0.gate_up_proj.weight": "model-00003-of-00006.safetensors",
68
+ "model.layers.15.mlp.experts.1.down_proj.weight": "model-00003-of-00006.safetensors",
69
+ "model.layers.15.mlp.experts.1.gate_up_proj.weight": "model-00003-of-00006.safetensors",
70
+ "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
71
+ "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
72
+ "model.layers.15.self_attn.qkv_proj.weight": "model-00003-of-00006.safetensors",
73
+ "model.layers.16.input_layernorm.weight": "model-00003-of-00006.safetensors",
74
+ "model.layers.16.mlp.experts.0.down_proj.weight": "model-00003-of-00006.safetensors",
75
+ "model.layers.16.mlp.experts.0.gate_up_proj.weight": "model-00003-of-00006.safetensors",
76
+ "model.layers.16.mlp.experts.1.down_proj.weight": "model-00003-of-00006.safetensors",
77
+ "model.layers.16.mlp.experts.1.gate_up_proj.weight": "model-00003-of-00006.safetensors",
78
+ "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
79
+ "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
80
+ "model.layers.16.self_attn.qkv_proj.weight": "model-00003-of-00006.safetensors",
81
+ "model.layers.17.input_layernorm.weight": "model-00003-of-00006.safetensors",
82
+ "model.layers.17.mlp.experts.0.down_proj.weight": "model-00003-of-00006.safetensors",
83
+ "model.layers.17.mlp.experts.0.gate_up_proj.weight": "model-00003-of-00006.safetensors",
84
+ "model.layers.17.mlp.experts.1.down_proj.weight": "model-00003-of-00006.safetensors",
85
+ "model.layers.17.mlp.experts.1.gate_up_proj.weight": "model-00003-of-00006.safetensors",
86
+ "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
87
+ "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
88
+ "model.layers.17.self_attn.qkv_proj.weight": "model-00003-of-00006.safetensors",
89
+ "model.layers.18.input_layernorm.weight": "model-00003-of-00006.safetensors",
90
+ "model.layers.18.mlp.experts.0.down_proj.weight": "model-00003-of-00006.safetensors",
91
+ "model.layers.18.mlp.experts.0.gate_up_proj.weight": "model-00003-of-00006.safetensors",
92
+ "model.layers.18.mlp.experts.1.down_proj.weight": "model-00004-of-00006.safetensors",
93
+ "model.layers.18.mlp.experts.1.gate_up_proj.weight": "model-00004-of-00006.safetensors",
94
+ "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
95
+ "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
96
+ "model.layers.18.self_attn.qkv_proj.weight": "model-00003-of-00006.safetensors",
97
+ "model.layers.19.input_layernorm.weight": "model-00004-of-00006.safetensors",
98
+ "model.layers.19.mlp.experts.0.down_proj.weight": "model-00004-of-00006.safetensors",
99
+ "model.layers.19.mlp.experts.0.gate_up_proj.weight": "model-00004-of-00006.safetensors",
100
+ "model.layers.19.mlp.experts.1.down_proj.weight": "model-00004-of-00006.safetensors",
101
+ "model.layers.19.mlp.experts.1.gate_up_proj.weight": "model-00004-of-00006.safetensors",
102
+ "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
103
+ "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
104
+ "model.layers.19.self_attn.qkv_proj.weight": "model-00004-of-00006.safetensors",
105
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00006.safetensors",
106
+ "model.layers.2.mlp.experts.0.down_proj.weight": "model-00001-of-00006.safetensors",
107
+ "model.layers.2.mlp.experts.0.gate_up_proj.weight": "model-00001-of-00006.safetensors",
108
+ "model.layers.2.mlp.experts.1.down_proj.weight": "model-00001-of-00006.safetensors",
109
+ "model.layers.2.mlp.experts.1.gate_up_proj.weight": "model-00001-of-00006.safetensors",
110
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
111
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
112
+ "model.layers.2.self_attn.qkv_proj.weight": "model-00001-of-00006.safetensors",
113
+ "model.layers.20.input_layernorm.weight": "model-00004-of-00006.safetensors",
114
+ "model.layers.20.mlp.experts.0.down_proj.weight": "model-00004-of-00006.safetensors",
115
+ "model.layers.20.mlp.experts.0.gate_up_proj.weight": "model-00004-of-00006.safetensors",
116
+ "model.layers.20.mlp.experts.1.down_proj.weight": "model-00004-of-00006.safetensors",
117
+ "model.layers.20.mlp.experts.1.gate_up_proj.weight": "model-00004-of-00006.safetensors",
118
+ "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
119
+ "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
120
+ "model.layers.20.self_attn.qkv_proj.weight": "model-00004-of-00006.safetensors",
121
+ "model.layers.21.input_layernorm.weight": "model-00004-of-00006.safetensors",
122
+ "model.layers.21.mlp.experts.0.down_proj.weight": "model-00004-of-00006.safetensors",
123
+ "model.layers.21.mlp.experts.0.gate_up_proj.weight": "model-00004-of-00006.safetensors",
124
+ "model.layers.21.mlp.experts.1.down_proj.weight": "model-00004-of-00006.safetensors",
125
+ "model.layers.21.mlp.experts.1.gate_up_proj.weight": "model-00004-of-00006.safetensors",
126
+ "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
127
+ "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
128
+ "model.layers.21.self_attn.qkv_proj.weight": "model-00004-of-00006.safetensors",
129
+ "model.layers.22.input_layernorm.weight": "model-00004-of-00006.safetensors",
130
+ "model.layers.22.mlp.experts.0.down_proj.weight": "model-00004-of-00006.safetensors",
131
+ "model.layers.22.mlp.experts.0.gate_up_proj.weight": "model-00004-of-00006.safetensors",
132
+ "model.layers.22.mlp.experts.1.down_proj.weight": "model-00004-of-00006.safetensors",
133
+ "model.layers.22.mlp.experts.1.gate_up_proj.weight": "model-00004-of-00006.safetensors",
134
+ "model.layers.22.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
135
+ "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
136
+ "model.layers.22.self_attn.qkv_proj.weight": "model-00004-of-00006.safetensors",
137
+ "model.layers.23.input_layernorm.weight": "model-00004-of-00006.safetensors",
138
+ "model.layers.23.mlp.experts.0.down_proj.weight": "model-00004-of-00006.safetensors",
139
+ "model.layers.23.mlp.experts.0.gate_up_proj.weight": "model-00004-of-00006.safetensors",
140
+ "model.layers.23.mlp.experts.1.down_proj.weight": "model-00004-of-00006.safetensors",
141
+ "model.layers.23.mlp.experts.1.gate_up_proj.weight": "model-00004-of-00006.safetensors",
142
+ "model.layers.23.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
143
+ "model.layers.23.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
144
+ "model.layers.23.self_attn.qkv_proj.weight": "model-00004-of-00006.safetensors",
145
+ "model.layers.24.input_layernorm.weight": "model-00004-of-00006.safetensors",
146
+ "model.layers.24.mlp.experts.0.down_proj.weight": "model-00004-of-00006.safetensors",
147
+ "model.layers.24.mlp.experts.0.gate_up_proj.weight": "model-00004-of-00006.safetensors",
148
+ "model.layers.24.mlp.experts.1.down_proj.weight": "model-00004-of-00006.safetensors",
149
+ "model.layers.24.mlp.experts.1.gate_up_proj.weight": "model-00004-of-00006.safetensors",
150
+ "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
151
+ "model.layers.24.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
152
+ "model.layers.24.self_attn.qkv_proj.weight": "model-00004-of-00006.safetensors",
153
+ "model.layers.25.input_layernorm.weight": "model-00004-of-00006.safetensors",
154
+ "model.layers.25.mlp.experts.0.down_proj.weight": "model-00005-of-00006.safetensors",
155
+ "model.layers.25.mlp.experts.0.gate_up_proj.weight": "model-00005-of-00006.safetensors",
156
+ "model.layers.25.mlp.experts.1.down_proj.weight": "model-00005-of-00006.safetensors",
157
+ "model.layers.25.mlp.experts.1.gate_up_proj.weight": "model-00005-of-00006.safetensors",
158
+ "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
159
+ "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
160
+ "model.layers.25.self_attn.qkv_proj.weight": "model-00004-of-00006.safetensors",
161
+ "model.layers.26.input_layernorm.weight": "model-00005-of-00006.safetensors",
162
+ "model.layers.26.mlp.experts.0.down_proj.weight": "model-00005-of-00006.safetensors",
163
+ "model.layers.26.mlp.experts.0.gate_up_proj.weight": "model-00005-of-00006.safetensors",
164
+ "model.layers.26.mlp.experts.1.down_proj.weight": "model-00005-of-00006.safetensors",
165
+ "model.layers.26.mlp.experts.1.gate_up_proj.weight": "model-00005-of-00006.safetensors",
166
+ "model.layers.26.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
167
+ "model.layers.26.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
168
+ "model.layers.26.self_attn.qkv_proj.weight": "model-00005-of-00006.safetensors",
169
+ "model.layers.27.input_layernorm.weight": "model-00005-of-00006.safetensors",
170
+ "model.layers.27.mlp.experts.0.down_proj.weight": "model-00005-of-00006.safetensors",
171
+ "model.layers.27.mlp.experts.0.gate_up_proj.weight": "model-00005-of-00006.safetensors",
172
+ "model.layers.27.mlp.experts.1.down_proj.weight": "model-00005-of-00006.safetensors",
173
+ "model.layers.27.mlp.experts.1.gate_up_proj.weight": "model-00005-of-00006.safetensors",
174
+ "model.layers.27.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
175
+ "model.layers.27.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
176
+ "model.layers.27.self_attn.qkv_proj.weight": "model-00005-of-00006.safetensors",
177
+ "model.layers.28.input_layernorm.weight": "model-00005-of-00006.safetensors",
178
+ "model.layers.28.mlp.experts.0.down_proj.weight": "model-00005-of-00006.safetensors",
179
+ "model.layers.28.mlp.experts.0.gate_up_proj.weight": "model-00005-of-00006.safetensors",
180
+ "model.layers.28.mlp.experts.1.down_proj.weight": "model-00005-of-00006.safetensors",
181
+ "model.layers.28.mlp.experts.1.gate_up_proj.weight": "model-00005-of-00006.safetensors",
182
+ "model.layers.28.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
183
+ "model.layers.28.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
184
+ "model.layers.28.self_attn.qkv_proj.weight": "model-00005-of-00006.safetensors",
185
+ "model.layers.29.input_layernorm.weight": "model-00005-of-00006.safetensors",
186
+ "model.layers.29.mlp.experts.0.down_proj.weight": "model-00005-of-00006.safetensors",
187
+ "model.layers.29.mlp.experts.0.gate_up_proj.weight": "model-00005-of-00006.safetensors",
188
+ "model.layers.29.mlp.experts.1.down_proj.weight": "model-00005-of-00006.safetensors",
189
+ "model.layers.29.mlp.experts.1.gate_up_proj.weight": "model-00005-of-00006.safetensors",
190
+ "model.layers.29.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
191
+ "model.layers.29.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
192
+ "model.layers.29.self_attn.qkv_proj.weight": "model-00005-of-00006.safetensors",
193
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00006.safetensors",
194
+ "model.layers.3.mlp.experts.0.down_proj.weight": "model-00001-of-00006.safetensors",
195
+ "model.layers.3.mlp.experts.0.gate_up_proj.weight": "model-00001-of-00006.safetensors",
196
+ "model.layers.3.mlp.experts.1.down_proj.weight": "model-00001-of-00006.safetensors",
197
+ "model.layers.3.mlp.experts.1.gate_up_proj.weight": "model-00001-of-00006.safetensors",
198
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
199
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
200
+ "model.layers.3.self_attn.qkv_proj.weight": "model-00001-of-00006.safetensors",
201
+ "model.layers.30.input_layernorm.weight": "model-00005-of-00006.safetensors",
202
+ "model.layers.30.mlp.experts.0.down_proj.weight": "model-00005-of-00006.safetensors",
203
+ "model.layers.30.mlp.experts.0.gate_up_proj.weight": "model-00005-of-00006.safetensors",
204
+ "model.layers.30.mlp.experts.1.down_proj.weight": "model-00005-of-00006.safetensors",
205
+ "model.layers.30.mlp.experts.1.gate_up_proj.weight": "model-00005-of-00006.safetensors",
206
+ "model.layers.30.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
207
+ "model.layers.30.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
208
+ "model.layers.30.self_attn.qkv_proj.weight": "model-00005-of-00006.safetensors",
209
+ "model.layers.31.input_layernorm.weight": "model-00005-of-00006.safetensors",
210
+ "model.layers.31.mlp.experts.0.down_proj.weight": "model-00005-of-00006.safetensors",
211
+ "model.layers.31.mlp.experts.0.gate_up_proj.weight": "model-00005-of-00006.safetensors",
212
+ "model.layers.31.mlp.experts.1.down_proj.weight": "model-00006-of-00006.safetensors",
213
+ "model.layers.31.mlp.experts.1.gate_up_proj.weight": "model-00006-of-00006.safetensors",
214
+ "model.layers.31.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
215
+ "model.layers.31.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
216
+ "model.layers.31.self_attn.qkv_proj.weight": "model-00005-of-00006.safetensors",
217
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00006.safetensors",
218
+ "model.layers.4.mlp.experts.0.down_proj.weight": "model-00001-of-00006.safetensors",
219
+ "model.layers.4.mlp.experts.0.gate_up_proj.weight": "model-00001-of-00006.safetensors",
220
+ "model.layers.4.mlp.experts.1.down_proj.weight": "model-00001-of-00006.safetensors",
221
+ "model.layers.4.mlp.experts.1.gate_up_proj.weight": "model-00001-of-00006.safetensors",
222
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
223
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
224
+ "model.layers.4.self_attn.qkv_proj.weight": "model-00001-of-00006.safetensors",
225
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00006.safetensors",
226
+ "model.layers.5.mlp.experts.0.down_proj.weight": "model-00002-of-00006.safetensors",
227
+ "model.layers.5.mlp.experts.0.gate_up_proj.weight": "model-00001-of-00006.safetensors",
228
+ "model.layers.5.mlp.experts.1.down_proj.weight": "model-00002-of-00006.safetensors",
229
+ "model.layers.5.mlp.experts.1.gate_up_proj.weight": "model-00002-of-00006.safetensors",
230
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
231
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
232
+ "model.layers.5.self_attn.qkv_proj.weight": "model-00001-of-00006.safetensors",
233
+ "model.layers.6.input_layernorm.weight": "model-00002-of-00006.safetensors",
234
+ "model.layers.6.mlp.experts.0.down_proj.weight": "model-00002-of-00006.safetensors",
235
+ "model.layers.6.mlp.experts.0.gate_up_proj.weight": "model-00002-of-00006.safetensors",
236
+ "model.layers.6.mlp.experts.1.down_proj.weight": "model-00002-of-00006.safetensors",
237
+ "model.layers.6.mlp.experts.1.gate_up_proj.weight": "model-00002-of-00006.safetensors",
238
+ "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
239
+ "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
240
+ "model.layers.6.self_attn.qkv_proj.weight": "model-00002-of-00006.safetensors",
241
+ "model.layers.7.input_layernorm.weight": "model-00002-of-00006.safetensors",
242
+ "model.layers.7.mlp.experts.0.down_proj.weight": "model-00002-of-00006.safetensors",
243
+ "model.layers.7.mlp.experts.0.gate_up_proj.weight": "model-00002-of-00006.safetensors",
244
+ "model.layers.7.mlp.experts.1.down_proj.weight": "model-00002-of-00006.safetensors",
245
+ "model.layers.7.mlp.experts.1.gate_up_proj.weight": "model-00002-of-00006.safetensors",
246
+ "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
247
+ "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
248
+ "model.layers.7.self_attn.qkv_proj.weight": "model-00002-of-00006.safetensors",
249
+ "model.layers.8.input_layernorm.weight": "model-00002-of-00006.safetensors",
250
+ "model.layers.8.mlp.experts.0.down_proj.weight": "model-00002-of-00006.safetensors",
251
+ "model.layers.8.mlp.experts.0.gate_up_proj.weight": "model-00002-of-00006.safetensors",
252
+ "model.layers.8.mlp.experts.1.down_proj.weight": "model-00002-of-00006.safetensors",
253
+ "model.layers.8.mlp.experts.1.gate_up_proj.weight": "model-00002-of-00006.safetensors",
254
+ "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
255
+ "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
256
+ "model.layers.8.self_attn.qkv_proj.weight": "model-00002-of-00006.safetensors",
257
+ "model.layers.9.input_layernorm.weight": "model-00002-of-00006.safetensors",
258
+ "model.layers.9.mlp.experts.0.down_proj.weight": "model-00002-of-00006.safetensors",
259
+ "model.layers.9.mlp.experts.0.gate_up_proj.weight": "model-00002-of-00006.safetensors",
260
+ "model.layers.9.mlp.experts.1.down_proj.weight": "model-00002-of-00006.safetensors",
261
+ "model.layers.9.mlp.experts.1.gate_up_proj.weight": "model-00002-of-00006.safetensors",
262
+ "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
263
+ "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
264
+ "model.layers.9.self_attn.qkv_proj.weight": "model-00002-of-00006.safetensors",
265
+ "model.norm.weight": "model-00001-of-00006.safetensors"
266
+ }
267
+ }