Hugging Face's logo

diffusionfamily
/
diffullama

Text Generation
Transformers
Safetensors
llama
llama-factory
full
diffusion
text-generation-inference
Inference Endpoints
Model card Files Community
1
Sansa commited on
Commit
01ea216
•
1 Parent(s): 72e1be8

End of training

Browse files
Files changed (7) hide show
  1. config.json +1 -1
  2. generation_config.json +11 -0
  3. model-00001-of-00003.safetensors +2 -2
  4. model-00002-of-00003.safetensors +2 -2
  5. model-00003-of-00003.safetensors +2 -2
  6. model.safetensors.index.json +291 -291
  7. training_args.bin +1 -1
config.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
  "_name_or_path": "output/llama2-ddm",
3
  "architectures": [
4
- "DiscreteDiffusionModel"
5
  ],
6
  "attention_bias": false,
7
  "attention_dropout": 0.0,
 
1
  {
2
  "_name_or_path": "output/llama2-ddm",
3
  "architectures": [
4
+ "LlamaForCausalLM"
5
  ],
6
  "attention_bias": false,
7
  "attention_dropout": 0.0,
generation_config.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_attn_implementation": "flash_attention_2",
3
+ "bos_token_id": 1,
4
+ "do_sample": true,
5
+ "eos_token_id": 2,
6
+ "max_length": 4096,
7
+ "pad_token_id": 0,
8
+ "temperature": 0.6,
9
+ "top_p": 0.9,
10
+ "transformers_version": "4.44.2"
11
+ }
model-00001-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7b1b1456ee0114f2d578f9f345f20c6913309923b357915fdcbb40d510c76e29
3
- size 4938986152
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfa70e8a3f757e2b9f95b225eaa08f45072f8e7805c513340764966975076a29
3
+ size 4938985352
model-00002-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1eb1677f5e09762c5cd9d7b2d2c28f2652b03cf4c4a3145b85b5e9e3c806ce68
3
- size 4947391752
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f61aec63b2c2e7de80c1f9c531d38fab99cb5b63e9323b734569e533e319fbd8
3
+ size 4947390880
model-00003-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4a81c619ae8c0c53793454282f9eb6af56ca013e95a4e4f4926ca31ab38a1af3
3
- size 3590489392
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:15aac74de157984cbd2ae9b999cf4411fae9d5561b0354f7eda62032c54d43c7
3
+ size 3590488816
model.safetensors.index.json CHANGED
@@ -3,296 +3,296 @@
3
  "total_size": 13476831232
4
  },
5
  "weight_map": {
6
- "denoise_model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
7
- "denoise_model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
8
- "denoise_model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
9
- "denoise_model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
10
- "denoise_model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
11
- "denoise_model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
12
- "denoise_model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
13
- "denoise_model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
14
- "denoise_model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
15
- "denoise_model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
16
- "denoise_model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
17
- "denoise_model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
18
- "denoise_model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
19
- "denoise_model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
20
- "denoise_model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
21
- "denoise_model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
22
- "denoise_model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
23
- "denoise_model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
24
- "denoise_model.layers.10.input_layernorm.weight": "model-00001-of-00003.safetensors",
25
- "denoise_model.layers.10.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
26
- "denoise_model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
27
- "denoise_model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
28
- "denoise_model.layers.10.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
29
- "denoise_model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
30
- "denoise_model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
31
- "denoise_model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
32
- "denoise_model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
33
- "denoise_model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
34
- "denoise_model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
35
- "denoise_model.layers.11.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
36
- "denoise_model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
37
- "denoise_model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
38
- "denoise_model.layers.11.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
39
- "denoise_model.layers.11.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
40
- "denoise_model.layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
41
- "denoise_model.layers.11.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
42
- "denoise_model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
43
- "denoise_model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
44
- "denoise_model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
45
- "denoise_model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
46
- "denoise_model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
47
- "denoise_model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
48
- "denoise_model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
49
- "denoise_model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
50
- "denoise_model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
51
- "denoise_model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
52
- "denoise_model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
53
- "denoise_model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
54
- "denoise_model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
55
- "denoise_model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
56
- "denoise_model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
57
- "denoise_model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
58
- "denoise_model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
59
- "denoise_model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
60
- "denoise_model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
61
- "denoise_model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
62
- "denoise_model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
63
- "denoise_model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
64
- "denoise_model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
65
- "denoise_model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
66
- "denoise_model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
67
- "denoise_model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
68
- "denoise_model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
69
- "denoise_model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
70
- "denoise_model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
71
- "denoise_model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
72
- "denoise_model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
73
- "denoise_model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
74
- "denoise_model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
75
- "denoise_model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
76
- "denoise_model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
77
- "denoise_model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
78
- "denoise_model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
79
- "denoise_model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
80
- "denoise_model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
81
- "denoise_model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
82
- "denoise_model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
83
- "denoise_model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
84
- "denoise_model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
85
- "denoise_model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
86
- "denoise_model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
87
- "denoise_model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
88
- "denoise_model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
89
- "denoise_model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
90
- "denoise_model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
91
- "denoise_model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
92
- "denoise_model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
93
- "denoise_model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
94
- "denoise_model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
95
- "denoise_model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
96
- "denoise_model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
97
- "denoise_model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
98
- "denoise_model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
99
- "denoise_model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
100
- "denoise_model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
101
- "denoise_model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
102
- "denoise_model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
103
- "denoise_model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
104
- "denoise_model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
105
- "denoise_model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
106
- "denoise_model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
107
- "denoise_model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
108
- "denoise_model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
109
- "denoise_model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
110
- "denoise_model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
111
- "denoise_model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
112
- "denoise_model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
113
- "denoise_model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
114
- "denoise_model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
115
- "denoise_model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
116
- "denoise_model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
117
- "denoise_model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
118
- "denoise_model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
119
- "denoise_model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
120
- "denoise_model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
121
- "denoise_model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
122
- "denoise_model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
123
- "denoise_model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
124
- "denoise_model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
125
- "denoise_model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
126
- "denoise_model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
127
- "denoise_model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
128
- "denoise_model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
129
- "denoise_model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
130
- "denoise_model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
131
- "denoise_model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
132
- "denoise_model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
133
- "denoise_model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
134
- "denoise_model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
135
- "denoise_model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
136
- "denoise_model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
137
- "denoise_model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
138
- "denoise_model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
139
- "denoise_model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
140
- "denoise_model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
141
- "denoise_model.layers.22.input_layernorm.weight": "model-00002-of-00003.safetensors",
142
- "denoise_model.layers.22.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
143
- "denoise_model.layers.22.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
144
- "denoise_model.layers.22.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
145
- "denoise_model.layers.22.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
146
- "denoise_model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
147
- "denoise_model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
148
- "denoise_model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
149
- "denoise_model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
150
- "denoise_model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors",
151
- "denoise_model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
152
- "denoise_model.layers.23.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
153
- "denoise_model.layers.23.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
154
- "denoise_model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
155
- "denoise_model.layers.23.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
156
- "denoise_model.layers.23.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
157
- "denoise_model.layers.23.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
158
- "denoise_model.layers.23.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
159
- "denoise_model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
160
- "denoise_model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
161
- "denoise_model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
162
- "denoise_model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
163
- "denoise_model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
164
- "denoise_model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
165
- "denoise_model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
166
- "denoise_model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
167
- "denoise_model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
168
- "denoise_model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
169
- "denoise_model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
170
- "denoise_model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
171
- "denoise_model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
172
- "denoise_model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
173
- "denoise_model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
174
- "denoise_model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
175
- "denoise_model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
176
- "denoise_model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
177
- "denoise_model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
178
- "denoise_model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
179
- "denoise_model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
180
- "denoise_model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
181
- "denoise_model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
182
- "denoise_model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
183
- "denoise_model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
184
- "denoise_model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
185
- "denoise_model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
186
- "denoise_model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
187
- "denoise_model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
188
- "denoise_model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
189
- "denoise_model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
190
- "denoise_model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
191
- "denoise_model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
192
- "denoise_model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
193
- "denoise_model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
194
- "denoise_model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
195
- "denoise_model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
196
- "denoise_model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
197
- "denoise_model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
198
- "denoise_model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
199
- "denoise_model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
200
- "denoise_model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
201
- "denoise_model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
202
- "denoise_model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
203
- "denoise_model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
204
- "denoise_model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
205
- "denoise_model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
206
- "denoise_model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
207
- "denoise_model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
208
- "denoise_model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
209
- "denoise_model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
210
- "denoise_model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
211
- "denoise_model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
212
- "denoise_model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
213
- "denoise_model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
214
- "denoise_model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
215
- "denoise_model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
216
- "denoise_model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
217
- "denoise_model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
218
- "denoise_model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
219
- "denoise_model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
220
- "denoise_model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
221
- "denoise_model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
222
- "denoise_model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
223
- "denoise_model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
224
- "denoise_model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
225
- "denoise_model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
226
- "denoise_model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
227
- "denoise_model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
228
- "denoise_model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
229
- "denoise_model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
230
- "denoise_model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
231
- "denoise_model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
232
- "denoise_model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
233
- "denoise_model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
234
- "denoise_model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
235
- "denoise_model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
236
- "denoise_model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
237
- "denoise_model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
238
- "denoise_model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
239
- "denoise_model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
240
- "denoise_model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
241
- "denoise_model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
242
- "denoise_model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
243
- "denoise_model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
244
- "denoise_model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
245
- "denoise_model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
246
- "denoise_model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
247
- "denoise_model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
248
- "denoise_model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
249
- "denoise_model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
250
- "denoise_model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
251
- "denoise_model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
252
- "denoise_model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
253
- "denoise_model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
254
- "denoise_model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
255
- "denoise_model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
256
- "denoise_model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
257
- "denoise_model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
258
- "denoise_model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
259
- "denoise_model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
260
- "denoise_model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
261
- "denoise_model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
262
- "denoise_model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
263
- "denoise_model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
264
- "denoise_model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
265
- "denoise_model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
266
- "denoise_model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
267
- "denoise_model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
268
- "denoise_model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
269
- "denoise_model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
270
- "denoise_model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
271
- "denoise_model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
272
- "denoise_model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
273
- "denoise_model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
274
- "denoise_model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
275
- "denoise_model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
276
- "denoise_model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
277
- "denoise_model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
278
- "denoise_model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
279
- "denoise_model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
280
- "denoise_model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
281
- "denoise_model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
282
- "denoise_model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
283
- "denoise_model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
284
- "denoise_model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
285
- "denoise_model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
286
- "denoise_model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
287
- "denoise_model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
288
- "denoise_model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
289
- "denoise_model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
290
- "denoise_model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
291
- "denoise_model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
292
- "denoise_model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
293
- "denoise_model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
294
- "denoise_model.norm.weight": "model-00003-of-00003.safetensors",
295
- "embed_tokens.weight": "model-00001-of-00003.safetensors",
296
- "lm_head.weight": "model-00003-of-00003.safetensors"
297
  }
298
  }
 
3
  "total_size": 13476831232
4
  },
5
  "weight_map": {
6
+ "lm_head.weight": "model-00003-of-00003.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
13
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
14
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
15
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
16
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
17
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
18
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
19
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
20
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
21
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
22
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
23
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
24
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
25
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
26
+ "model.layers.10.input_layernorm.weight": "model-00001-of-00003.safetensors",
27
+ "model.layers.10.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
28
+ "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
29
+ "model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
30
+ "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
31
+ "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
32
+ "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
33
+ "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
34
+ "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
35
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
36
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
37
+ "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
38
+ "model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
39
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
40
+ "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
41
+ "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
42
+ "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
43
+ "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
44
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
45
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
46
+ "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
47
+ "model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
48
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
49
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
50
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
51
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
52
+ "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
53
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
54
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
55
+ "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
56
+ "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
57
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
58
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
59
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
60
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
61
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
62
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
63
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
64
+ "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
65
+ "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
66
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
67
+ "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
68
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
69
+ "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
70
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
71
+ "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
72
+ "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
73
+ "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
74
+ "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
75
+ "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
76
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
77
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
78
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
79
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
80
+ "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
81
+ "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
82
+ "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
83
+ "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
84
+ "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
85
+ "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
86
+ "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
87
+ "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
88
+ "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
89
+ "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
90
+ "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
91
+ "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
92
+ "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
93
+ "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
94
+ "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
95
+ "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
96
+ "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
97
+ "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
98
+ "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
99
+ "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
100
+ "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
101
+ "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
102
+ "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
103
+ "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
104
+ "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
105
+ "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
106
+ "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
107
+ "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
108
+ "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
109
+ "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
110
+ "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
111
+ "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
112
+ "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
113
+ "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
114
+ "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
115
+ "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
116
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
117
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
118
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
119
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
120
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
121
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
122
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
123
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
124
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
125
+ "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
126
+ "model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
127
+ "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
128
+ "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
129
+ "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
130
+ "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
131
+ "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
132
+ "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
133
+ "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
134
+ "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
135
+ "model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
136
+ "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
137
+ "model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
138
+ "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
139
+ "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
140
+ "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
141
+ "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
142
+ "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
143
+ "model.layers.22.input_layernorm.weight": "model-00002-of-00003.safetensors",
144
+ "model.layers.22.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
145
+ "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
146
+ "model.layers.22.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
147
+ "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
148
+ "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
149
+ "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
150
+ "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
151
+ "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
152
+ "model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors",
153
+ "model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
154
+ "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
155
+ "model.layers.23.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
156
+ "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
157
+ "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
158
+ "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
159
+ "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
160
+ "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
161
+ "model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
162
+ "model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
163
+ "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
164
+ "model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
165
+ "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
166
+ "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
167
+ "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
168
+ "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
169
+ "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
170
+ "model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
171
+ "model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
172
+ "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
173
+ "model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
174
+ "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
175
+ "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
176
+ "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
177
+ "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
178
+ "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
179
+ "model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
180
+ "model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
181
+ "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
182
+ "model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
183
+ "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
184
+ "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
185
+ "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
186
+ "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
187
+ "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
188
+ "model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
189
+ "model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
190
+ "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
191
+ "model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
192
+ "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
193
+ "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
194
+ "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
195
+ "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
196
+ "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
197
+ "model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
198
+ "model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
199
+ "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
200
+ "model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
201
+ "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
202
+ "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
203
+ "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
204
+ "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
205
+ "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
206
+ "model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
207
+ "model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
208
+ "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
209
+ "model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
210
+ "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
211
+ "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
212
+ "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
213
+ "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
214
+ "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
215
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
216
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
217
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
218
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
219
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
220
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
221
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
222
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
223
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
224
+ "model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
225
+ "model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
226
+ "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
227
+ "model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
228
+ "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
229
+ "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
230
+ "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
231
+ "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
232
+ "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
233
+ "model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
234
+ "model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
235
+ "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
236
+ "model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
237
+ "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
238
+ "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
239
+ "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
240
+ "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
241
+ "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
242
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
243
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
244
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
245
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
246
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
247
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
248
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
249
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
250
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
251
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
252
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
253
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
254
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
255
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
256
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
257
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
258
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
259
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
260
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
261
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
262
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
263
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
264
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
265
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
266
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
267
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
268
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
269
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
270
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
271
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
272
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
273
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
274
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
275
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
276
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
277
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
278
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
279
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
280
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
281
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
282
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
283
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
284
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
285
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
286
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
287
+ "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
288
+ "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
289
+ "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
290
+ "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
291
+ "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
292
+ "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
293
+ "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
294
+ "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
295
+ "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
296
+ "model.norm.weight": "model-00003-of-00003.safetensors"
297
  }
298
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9a574afd82e6f6ababddfb8d8e5ce772823ff404fa8bb71fa77a6df3cc5f183f
3
  size 5368
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:17feda60f83055da97d59f9a83a09971077be7ad9546d1b95caf088e3c2c93ab
3
  size 5368