Hugging Face's logo

beomi
/
KoRWKV-1.5B

Text Generation
Transformers
PyTorch
Safetensors
Korean
rwkv
KoRWKV
Inference Endpoints
Model card Files Community
beomi commited on
Commit
d3fd582
•
1 Parent(s): 46a5e35

Add 100B tokens ckpt

Browse files
Files changed (8) hide show
  1. pytorch_model-00001-of-00002.bin → pytorch_model-00001-of-00007.bin +2 -2
  2. pytorch_model-00002-of-00002.bin → pytorch_model-00002-of-00007.bin +2 -2
  3. pytorch_model-00003-of-00007.bin +3 -0
  4. pytorch_model-00004-of-00007.bin +3 -0
  5. pytorch_model-00005-of-00007.bin +3 -0
  6. pytorch_model-00006-of-00007.bin +3 -0
  7. pytorch_model-00007-of-00007.bin +3 -0
  8. pytorch_model.bin.index.json +438 -438
pytorch_model-00001-of-00002.bin → pytorch_model-00001-of-00007.bin RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:10fb267e6a23ffe5b4f3229d28d8c6de693abe4fd58b07a1964c957377b98152
3
- size 3984404577
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d9824593ff175045fd9410158a8f587765db31a5893c8546f0b090767d91155c
3
+ size 996714221
pytorch_model-00002-of-00002.bin → pytorch_model-00002-of-00007.bin RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:29418368311e6b63906585d4b69e5f7be786b871b6c5419b5e9aca91b12b1cd1
3
- size 2104396855
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c77bdb67063627181ed54ba5467abc578990fe9fe0d88d7cc2fe1f14495966f
3
+ size 990318153
pytorch_model-00003-of-00007.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48be7452f587c9741b27ef6d49559ccce7a5f587a80408434dae87db407dcee3
3
+ size 990258571
pytorch_model-00004-of-00007.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:070c3594c14eaf9ab1bcf323bbc499e60208c7725ec1b5b25e63c86b3d1fd210
3
+ size 990318217
pytorch_model-00005-of-00007.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99585dba978c45c3e4828378f9d521bd04bb2d69e48d2949622fa4b9b8638f5d
3
+ size 973481081
pytorch_model-00006-of-00007.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e3a421829b36606f823ab56eb80e9378e22f2c5172713382fd025a96bcdde08
3
+ size 721725905
pytorch_model-00007-of-00007.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:04b5da856bf56f981bc4d30072649ef0beee33d54d6003118971a47fd2dea2d4
3
+ size 425984938
pytorch_model.bin.index.json CHANGED
@@ -3,443 +3,443 @@
3
  "total_size": 6088654848
4
  },
5
  "weight_map": {
6
- "head.weight": "pytorch_model-00002-of-00002.bin",
7
- "rwkv.blocks.0.attention.key.weight": "pytorch_model-00001-of-00002.bin",
8
- "rwkv.blocks.0.attention.output.weight": "pytorch_model-00001-of-00002.bin",
9
- "rwkv.blocks.0.attention.receptance.weight": "pytorch_model-00001-of-00002.bin",
10
- "rwkv.blocks.0.attention.time_decay": "pytorch_model-00001-of-00002.bin",
11
- "rwkv.blocks.0.attention.time_first": "pytorch_model-00001-of-00002.bin",
12
- "rwkv.blocks.0.attention.time_mix_key": "pytorch_model-00001-of-00002.bin",
13
- "rwkv.blocks.0.attention.time_mix_receptance": "pytorch_model-00001-of-00002.bin",
14
- "rwkv.blocks.0.attention.time_mix_value": "pytorch_model-00001-of-00002.bin",
15
- "rwkv.blocks.0.attention.value.weight": "pytorch_model-00001-of-00002.bin",
16
- "rwkv.blocks.0.feed_forward.key.weight": "pytorch_model-00001-of-00002.bin",
17
- "rwkv.blocks.0.feed_forward.receptance.weight": "pytorch_model-00001-of-00002.bin",
18
- "rwkv.blocks.0.feed_forward.time_mix_key": "pytorch_model-00001-of-00002.bin",
19
- "rwkv.blocks.0.feed_forward.time_mix_receptance": "pytorch_model-00001-of-00002.bin",
20
- "rwkv.blocks.0.feed_forward.value.weight": "pytorch_model-00001-of-00002.bin",
21
- "rwkv.blocks.0.ln1.bias": "pytorch_model-00001-of-00002.bin",
22
- "rwkv.blocks.0.ln1.weight": "pytorch_model-00001-of-00002.bin",
23
- "rwkv.blocks.0.ln2.bias": "pytorch_model-00001-of-00002.bin",
24
- "rwkv.blocks.0.ln2.weight": "pytorch_model-00001-of-00002.bin",
25
- "rwkv.blocks.0.pre_ln.bias": "pytorch_model-00001-of-00002.bin",
26
- "rwkv.blocks.0.pre_ln.weight": "pytorch_model-00001-of-00002.bin",
27
- "rwkv.blocks.1.attention.key.weight": "pytorch_model-00001-of-00002.bin",
28
- "rwkv.blocks.1.attention.output.weight": "pytorch_model-00001-of-00002.bin",
29
- "rwkv.blocks.1.attention.receptance.weight": "pytorch_model-00001-of-00002.bin",
30
- "rwkv.blocks.1.attention.time_decay": "pytorch_model-00001-of-00002.bin",
31
- "rwkv.blocks.1.attention.time_first": "pytorch_model-00001-of-00002.bin",
32
- "rwkv.blocks.1.attention.time_mix_key": "pytorch_model-00001-of-00002.bin",
33
- "rwkv.blocks.1.attention.time_mix_receptance": "pytorch_model-00001-of-00002.bin",
34
- "rwkv.blocks.1.attention.time_mix_value": "pytorch_model-00001-of-00002.bin",
35
- "rwkv.blocks.1.attention.value.weight": "pytorch_model-00001-of-00002.bin",
36
- "rwkv.blocks.1.feed_forward.key.weight": "pytorch_model-00001-of-00002.bin",
37
- "rwkv.blocks.1.feed_forward.receptance.weight": "pytorch_model-00001-of-00002.bin",
38
- "rwkv.blocks.1.feed_forward.time_mix_key": "pytorch_model-00001-of-00002.bin",
39
- "rwkv.blocks.1.feed_forward.time_mix_receptance": "pytorch_model-00001-of-00002.bin",
40
- "rwkv.blocks.1.feed_forward.value.weight": "pytorch_model-00001-of-00002.bin",
41
- "rwkv.blocks.1.ln1.bias": "pytorch_model-00001-of-00002.bin",
42
- "rwkv.blocks.1.ln1.weight": "pytorch_model-00001-of-00002.bin",
43
- "rwkv.blocks.1.ln2.bias": "pytorch_model-00001-of-00002.bin",
44
- "rwkv.blocks.1.ln2.weight": "pytorch_model-00001-of-00002.bin",
45
- "rwkv.blocks.10.attention.key.weight": "pytorch_model-00001-of-00002.bin",
46
- "rwkv.blocks.10.attention.output.weight": "pytorch_model-00001-of-00002.bin",
47
- "rwkv.blocks.10.attention.receptance.weight": "pytorch_model-00001-of-00002.bin",
48
- "rwkv.blocks.10.attention.time_decay": "pytorch_model-00001-of-00002.bin",
49
- "rwkv.blocks.10.attention.time_first": "pytorch_model-00001-of-00002.bin",
50
- "rwkv.blocks.10.attention.time_mix_key": "pytorch_model-00001-of-00002.bin",
51
- "rwkv.blocks.10.attention.time_mix_receptance": "pytorch_model-00001-of-00002.bin",
52
- "rwkv.blocks.10.attention.time_mix_value": "pytorch_model-00001-of-00002.bin",
53
- "rwkv.blocks.10.attention.value.weight": "pytorch_model-00001-of-00002.bin",
54
- "rwkv.blocks.10.feed_forward.key.weight": "pytorch_model-00001-of-00002.bin",
55
- "rwkv.blocks.10.feed_forward.receptance.weight": "pytorch_model-00001-of-00002.bin",
56
- "rwkv.blocks.10.feed_forward.time_mix_key": "pytorch_model-00001-of-00002.bin",
57
- "rwkv.blocks.10.feed_forward.time_mix_receptance": "pytorch_model-00001-of-00002.bin",
58
- "rwkv.blocks.10.feed_forward.value.weight": "pytorch_model-00001-of-00002.bin",
59
- "rwkv.blocks.10.ln1.bias": "pytorch_model-00001-of-00002.bin",
60
- "rwkv.blocks.10.ln1.weight": "pytorch_model-00001-of-00002.bin",
61
- "rwkv.blocks.10.ln2.bias": "pytorch_model-00001-of-00002.bin",
62
- "rwkv.blocks.10.ln2.weight": "pytorch_model-00001-of-00002.bin",
63
- "rwkv.blocks.11.attention.key.weight": "pytorch_model-00001-of-00002.bin",
64
- "rwkv.blocks.11.attention.output.weight": "pytorch_model-00001-of-00002.bin",
65
- "rwkv.blocks.11.attention.receptance.weight": "pytorch_model-00001-of-00002.bin",
66
- "rwkv.blocks.11.attention.time_decay": "pytorch_model-00001-of-00002.bin",
67
- "rwkv.blocks.11.attention.time_first": "pytorch_model-00001-of-00002.bin",
68
- "rwkv.blocks.11.attention.time_mix_key": "pytorch_model-00001-of-00002.bin",
69
- "rwkv.blocks.11.attention.time_mix_receptance": "pytorch_model-00001-of-00002.bin",
70
- "rwkv.blocks.11.attention.time_mix_value": "pytorch_model-00001-of-00002.bin",
71
- "rwkv.blocks.11.attention.value.weight": "pytorch_model-00001-of-00002.bin",
72
- "rwkv.blocks.11.feed_forward.key.weight": "pytorch_model-00001-of-00002.bin",
73
- "rwkv.blocks.11.feed_forward.receptance.weight": "pytorch_model-00001-of-00002.bin",
74
- "rwkv.blocks.11.feed_forward.time_mix_key": "pytorch_model-00001-of-00002.bin",
75
- "rwkv.blocks.11.feed_forward.time_mix_receptance": "pytorch_model-00001-of-00002.bin",
76
- "rwkv.blocks.11.feed_forward.value.weight": "pytorch_model-00001-of-00002.bin",
77
- "rwkv.blocks.11.ln1.bias": "pytorch_model-00001-of-00002.bin",
78
- "rwkv.blocks.11.ln1.weight": "pytorch_model-00001-of-00002.bin",
79
- "rwkv.blocks.11.ln2.bias": "pytorch_model-00001-of-00002.bin",
80
- "rwkv.blocks.11.ln2.weight": "pytorch_model-00001-of-00002.bin",
81
- "rwkv.blocks.12.attention.key.weight": "pytorch_model-00001-of-00002.bin",
82
- "rwkv.blocks.12.attention.output.weight": "pytorch_model-00001-of-00002.bin",
83
- "rwkv.blocks.12.attention.receptance.weight": "pytorch_model-00001-of-00002.bin",
84
- "rwkv.blocks.12.attention.time_decay": "pytorch_model-00001-of-00002.bin",
85
- "rwkv.blocks.12.attention.time_first": "pytorch_model-00001-of-00002.bin",
86
- "rwkv.blocks.12.attention.time_mix_key": "pytorch_model-00001-of-00002.bin",
87
- "rwkv.blocks.12.attention.time_mix_receptance": "pytorch_model-00001-of-00002.bin",
88
- "rwkv.blocks.12.attention.time_mix_value": "pytorch_model-00001-of-00002.bin",
89
- "rwkv.blocks.12.attention.value.weight": "pytorch_model-00001-of-00002.bin",
90
- "rwkv.blocks.12.feed_forward.key.weight": "pytorch_model-00001-of-00002.bin",
91
- "rwkv.blocks.12.feed_forward.receptance.weight": "pytorch_model-00001-of-00002.bin",
92
- "rwkv.blocks.12.feed_forward.time_mix_key": "pytorch_model-00001-of-00002.bin",
93
- "rwkv.blocks.12.feed_forward.time_mix_receptance": "pytorch_model-00001-of-00002.bin",
94
- "rwkv.blocks.12.feed_forward.value.weight": "pytorch_model-00001-of-00002.bin",
95
- "rwkv.blocks.12.ln1.bias": "pytorch_model-00001-of-00002.bin",
96
- "rwkv.blocks.12.ln1.weight": "pytorch_model-00001-of-00002.bin",
97
- "rwkv.blocks.12.ln2.bias": "pytorch_model-00001-of-00002.bin",
98
- "rwkv.blocks.12.ln2.weight": "pytorch_model-00001-of-00002.bin",
99
- "rwkv.blocks.13.attention.key.weight": "pytorch_model-00001-of-00002.bin",
100
- "rwkv.blocks.13.attention.output.weight": "pytorch_model-00001-of-00002.bin",
101
- "rwkv.blocks.13.attention.receptance.weight": "pytorch_model-00001-of-00002.bin",
102
- "rwkv.blocks.13.attention.time_decay": "pytorch_model-00001-of-00002.bin",
103
- "rwkv.blocks.13.attention.time_first": "pytorch_model-00001-of-00002.bin",
104
- "rwkv.blocks.13.attention.time_mix_key": "pytorch_model-00001-of-00002.bin",
105
- "rwkv.blocks.13.attention.time_mix_receptance": "pytorch_model-00001-of-00002.bin",
106
- "rwkv.blocks.13.attention.time_mix_value": "pytorch_model-00001-of-00002.bin",
107
- "rwkv.blocks.13.attention.value.weight": "pytorch_model-00001-of-00002.bin",
108
- "rwkv.blocks.13.feed_forward.key.weight": "pytorch_model-00001-of-00002.bin",
109
- "rwkv.blocks.13.feed_forward.receptance.weight": "pytorch_model-00001-of-00002.bin",
110
- "rwkv.blocks.13.feed_forward.time_mix_key": "pytorch_model-00001-of-00002.bin",
111
- "rwkv.blocks.13.feed_forward.time_mix_receptance": "pytorch_model-00001-of-00002.bin",
112
- "rwkv.blocks.13.feed_forward.value.weight": "pytorch_model-00001-of-00002.bin",
113
- "rwkv.blocks.13.ln1.bias": "pytorch_model-00001-of-00002.bin",
114
- "rwkv.blocks.13.ln1.weight": "pytorch_model-00001-of-00002.bin",
115
- "rwkv.blocks.13.ln2.bias": "pytorch_model-00001-of-00002.bin",
116
- "rwkv.blocks.13.ln2.weight": "pytorch_model-00001-of-00002.bin",
117
- "rwkv.blocks.14.attention.key.weight": "pytorch_model-00001-of-00002.bin",
118
- "rwkv.blocks.14.attention.output.weight": "pytorch_model-00001-of-00002.bin",
119
- "rwkv.blocks.14.attention.receptance.weight": "pytorch_model-00001-of-00002.bin",
120
- "rwkv.blocks.14.attention.time_decay": "pytorch_model-00001-of-00002.bin",
121
- "rwkv.blocks.14.attention.time_first": "pytorch_model-00001-of-00002.bin",
122
- "rwkv.blocks.14.attention.time_mix_key": "pytorch_model-00001-of-00002.bin",
123
- "rwkv.blocks.14.attention.time_mix_receptance": "pytorch_model-00001-of-00002.bin",
124
- "rwkv.blocks.14.attention.time_mix_value": "pytorch_model-00001-of-00002.bin",
125
- "rwkv.blocks.14.attention.value.weight": "pytorch_model-00001-of-00002.bin",
126
- "rwkv.blocks.14.feed_forward.key.weight": "pytorch_model-00001-of-00002.bin",
127
- "rwkv.blocks.14.feed_forward.receptance.weight": "pytorch_model-00001-of-00002.bin",
128
- "rwkv.blocks.14.feed_forward.time_mix_key": "pytorch_model-00001-of-00002.bin",
129
- "rwkv.blocks.14.feed_forward.time_mix_receptance": "pytorch_model-00001-of-00002.bin",
130
- "rwkv.blocks.14.feed_forward.value.weight": "pytorch_model-00001-of-00002.bin",
131
- "rwkv.blocks.14.ln1.bias": "pytorch_model-00001-of-00002.bin",
132
- "rwkv.blocks.14.ln1.weight": "pytorch_model-00001-of-00002.bin",
133
- "rwkv.blocks.14.ln2.bias": "pytorch_model-00001-of-00002.bin",
134
- "rwkv.blocks.14.ln2.weight": "pytorch_model-00001-of-00002.bin",
135
- "rwkv.blocks.15.attention.key.weight": "pytorch_model-00001-of-00002.bin",
136
- "rwkv.blocks.15.attention.output.weight": "pytorch_model-00001-of-00002.bin",
137
- "rwkv.blocks.15.attention.receptance.weight": "pytorch_model-00001-of-00002.bin",
138
- "rwkv.blocks.15.attention.time_decay": "pytorch_model-00001-of-00002.bin",
139
- "rwkv.blocks.15.attention.time_first": "pytorch_model-00001-of-00002.bin",
140
- "rwkv.blocks.15.attention.time_mix_key": "pytorch_model-00001-of-00002.bin",
141
- "rwkv.blocks.15.attention.time_mix_receptance": "pytorch_model-00001-of-00002.bin",
142
- "rwkv.blocks.15.attention.time_mix_value": "pytorch_model-00001-of-00002.bin",
143
- "rwkv.blocks.15.attention.value.weight": "pytorch_model-00001-of-00002.bin",
144
- "rwkv.blocks.15.feed_forward.key.weight": "pytorch_model-00001-of-00002.bin",
145
- "rwkv.blocks.15.feed_forward.receptance.weight": "pytorch_model-00001-of-00002.bin",
146
- "rwkv.blocks.15.feed_forward.time_mix_key": "pytorch_model-00001-of-00002.bin",
147
- "rwkv.blocks.15.feed_forward.time_mix_receptance": "pytorch_model-00001-of-00002.bin",
148
- "rwkv.blocks.15.feed_forward.value.weight": "pytorch_model-00001-of-00002.bin",
149
- "rwkv.blocks.15.ln1.bias": "pytorch_model-00001-of-00002.bin",
150
- "rwkv.blocks.15.ln1.weight": "pytorch_model-00001-of-00002.bin",
151
- "rwkv.blocks.15.ln2.bias": "pytorch_model-00001-of-00002.bin",
152
- "rwkv.blocks.15.ln2.weight": "pytorch_model-00001-of-00002.bin",
153
- "rwkv.blocks.16.attention.key.weight": "pytorch_model-00001-of-00002.bin",
154
- "rwkv.blocks.16.attention.output.weight": "pytorch_model-00001-of-00002.bin",
155
- "rwkv.blocks.16.attention.receptance.weight": "pytorch_model-00001-of-00002.bin",
156
- "rwkv.blocks.16.attention.time_decay": "pytorch_model-00001-of-00002.bin",
157
- "rwkv.blocks.16.attention.time_first": "pytorch_model-00001-of-00002.bin",
158
- "rwkv.blocks.16.attention.time_mix_key": "pytorch_model-00001-of-00002.bin",
159
- "rwkv.blocks.16.attention.time_mix_receptance": "pytorch_model-00001-of-00002.bin",
160
- "rwkv.blocks.16.attention.time_mix_value": "pytorch_model-00001-of-00002.bin",
161
- "rwkv.blocks.16.attention.value.weight": "pytorch_model-00001-of-00002.bin",
162
- "rwkv.blocks.16.feed_forward.key.weight": "pytorch_model-00002-of-00002.bin",
163
- "rwkv.blocks.16.feed_forward.receptance.weight": "pytorch_model-00002-of-00002.bin",
164
- "rwkv.blocks.16.feed_forward.time_mix_key": "pytorch_model-00001-of-00002.bin",
165
- "rwkv.blocks.16.feed_forward.time_mix_receptance": "pytorch_model-00001-of-00002.bin",
166
- "rwkv.blocks.16.feed_forward.value.weight": "pytorch_model-00002-of-00002.bin",
167
- "rwkv.blocks.16.ln1.bias": "pytorch_model-00001-of-00002.bin",
168
- "rwkv.blocks.16.ln1.weight": "pytorch_model-00001-of-00002.bin",
169
- "rwkv.blocks.16.ln2.bias": "pytorch_model-00001-of-00002.bin",
170
- "rwkv.blocks.16.ln2.weight": "pytorch_model-00001-of-00002.bin",
171
- "rwkv.blocks.17.attention.key.weight": "pytorch_model-00002-of-00002.bin",
172
- "rwkv.blocks.17.attention.output.weight": "pytorch_model-00002-of-00002.bin",
173
- "rwkv.blocks.17.attention.receptance.weight": "pytorch_model-00002-of-00002.bin",
174
- "rwkv.blocks.17.attention.time_decay": "pytorch_model-00002-of-00002.bin",
175
- "rwkv.blocks.17.attention.time_first": "pytorch_model-00002-of-00002.bin",
176
- "rwkv.blocks.17.attention.time_mix_key": "pytorch_model-00002-of-00002.bin",
177
- "rwkv.blocks.17.attention.time_mix_receptance": "pytorch_model-00002-of-00002.bin",
178
- "rwkv.blocks.17.attention.time_mix_value": "pytorch_model-00002-of-00002.bin",
179
- "rwkv.blocks.17.attention.value.weight": "pytorch_model-00002-of-00002.bin",
180
- "rwkv.blocks.17.feed_forward.key.weight": "pytorch_model-00002-of-00002.bin",
181
- "rwkv.blocks.17.feed_forward.receptance.weight": "pytorch_model-00002-of-00002.bin",
182
- "rwkv.blocks.17.feed_forward.time_mix_key": "pytorch_model-00002-of-00002.bin",
183
- "rwkv.blocks.17.feed_forward.time_mix_receptance": "pytorch_model-00002-of-00002.bin",
184
- "rwkv.blocks.17.feed_forward.value.weight": "pytorch_model-00002-of-00002.bin",
185
- "rwkv.blocks.17.ln1.bias": "pytorch_model-00002-of-00002.bin",
186
- "rwkv.blocks.17.ln1.weight": "pytorch_model-00002-of-00002.bin",
187
- "rwkv.blocks.17.ln2.bias": "pytorch_model-00002-of-00002.bin",
188
- "rwkv.blocks.17.ln2.weight": "pytorch_model-00002-of-00002.bin",
189
- "rwkv.blocks.18.attention.key.weight": "pytorch_model-00002-of-00002.bin",
190
- "rwkv.blocks.18.attention.output.weight": "pytorch_model-00002-of-00002.bin",
191
- "rwkv.blocks.18.attention.receptance.weight": "pytorch_model-00002-of-00002.bin",
192
- "rwkv.blocks.18.attention.time_decay": "pytorch_model-00002-of-00002.bin",
193
- "rwkv.blocks.18.attention.time_first": "pytorch_model-00002-of-00002.bin",
194
- "rwkv.blocks.18.attention.time_mix_key": "pytorch_model-00002-of-00002.bin",
195
- "rwkv.blocks.18.attention.time_mix_receptance": "pytorch_model-00002-of-00002.bin",
196
- "rwkv.blocks.18.attention.time_mix_value": "pytorch_model-00002-of-00002.bin",
197
- "rwkv.blocks.18.attention.value.weight": "pytorch_model-00002-of-00002.bin",
198
- "rwkv.blocks.18.feed_forward.key.weight": "pytorch_model-00002-of-00002.bin",
199
- "rwkv.blocks.18.feed_forward.receptance.weight": "pytorch_model-00002-of-00002.bin",
200
- "rwkv.blocks.18.feed_forward.time_mix_key": "pytorch_model-00002-of-00002.bin",
201
- "rwkv.blocks.18.feed_forward.time_mix_receptance": "pytorch_model-00002-of-00002.bin",
202
- "rwkv.blocks.18.feed_forward.value.weight": "pytorch_model-00002-of-00002.bin",
203
- "rwkv.blocks.18.ln1.bias": "pytorch_model-00002-of-00002.bin",
204
- "rwkv.blocks.18.ln1.weight": "pytorch_model-00002-of-00002.bin",
205
- "rwkv.blocks.18.ln2.bias": "pytorch_model-00002-of-00002.bin",
206
- "rwkv.blocks.18.ln2.weight": "pytorch_model-00002-of-00002.bin",
207
- "rwkv.blocks.19.attention.key.weight": "pytorch_model-00002-of-00002.bin",
208
- "rwkv.blocks.19.attention.output.weight": "pytorch_model-00002-of-00002.bin",
209
- "rwkv.blocks.19.attention.receptance.weight": "pytorch_model-00002-of-00002.bin",
210
- "rwkv.blocks.19.attention.time_decay": "pytorch_model-00002-of-00002.bin",
211
- "rwkv.blocks.19.attention.time_first": "pytorch_model-00002-of-00002.bin",
212
- "rwkv.blocks.19.attention.time_mix_key": "pytorch_model-00002-of-00002.bin",
213
- "rwkv.blocks.19.attention.time_mix_receptance": "pytorch_model-00002-of-00002.bin",
214
- "rwkv.blocks.19.attention.time_mix_value": "pytorch_model-00002-of-00002.bin",
215
- "rwkv.blocks.19.attention.value.weight": "pytorch_model-00002-of-00002.bin",
216
- "rwkv.blocks.19.feed_forward.key.weight": "pytorch_model-00002-of-00002.bin",
217
- "rwkv.blocks.19.feed_forward.receptance.weight": "pytorch_model-00002-of-00002.bin",
218
- "rwkv.blocks.19.feed_forward.time_mix_key": "pytorch_model-00002-of-00002.bin",
219
- "rwkv.blocks.19.feed_forward.time_mix_receptance": "pytorch_model-00002-of-00002.bin",
220
- "rwkv.blocks.19.feed_forward.value.weight": "pytorch_model-00002-of-00002.bin",
221
- "rwkv.blocks.19.ln1.bias": "pytorch_model-00002-of-00002.bin",
222
- "rwkv.blocks.19.ln1.weight": "pytorch_model-00002-of-00002.bin",
223
- "rwkv.blocks.19.ln2.bias": "pytorch_model-00002-of-00002.bin",
224
- "rwkv.blocks.19.ln2.weight": "pytorch_model-00002-of-00002.bin",
225
- "rwkv.blocks.2.attention.key.weight": "pytorch_model-00001-of-00002.bin",
226
- "rwkv.blocks.2.attention.output.weight": "pytorch_model-00001-of-00002.bin",
227
- "rwkv.blocks.2.attention.receptance.weight": "pytorch_model-00001-of-00002.bin",
228
- "rwkv.blocks.2.attention.time_decay": "pytorch_model-00001-of-00002.bin",
229
- "rwkv.blocks.2.attention.time_first": "pytorch_model-00001-of-00002.bin",
230
- "rwkv.blocks.2.attention.time_mix_key": "pytorch_model-00001-of-00002.bin",
231
- "rwkv.blocks.2.attention.time_mix_receptance": "pytorch_model-00001-of-00002.bin",
232
- "rwkv.blocks.2.attention.time_mix_value": "pytorch_model-00001-of-00002.bin",
233
- "rwkv.blocks.2.attention.value.weight": "pytorch_model-00001-of-00002.bin",
234
- "rwkv.blocks.2.feed_forward.key.weight": "pytorch_model-00001-of-00002.bin",
235
- "rwkv.blocks.2.feed_forward.receptance.weight": "pytorch_model-00001-of-00002.bin",
236
- "rwkv.blocks.2.feed_forward.time_mix_key": "pytorch_model-00001-of-00002.bin",
237
- "rwkv.blocks.2.feed_forward.time_mix_receptance": "pytorch_model-00001-of-00002.bin",
238
- "rwkv.blocks.2.feed_forward.value.weight": "pytorch_model-00001-of-00002.bin",
239
- "rwkv.blocks.2.ln1.bias": "pytorch_model-00001-of-00002.bin",
240
- "rwkv.blocks.2.ln1.weight": "pytorch_model-00001-of-00002.bin",
241
- "rwkv.blocks.2.ln2.bias": "pytorch_model-00001-of-00002.bin",
242
- "rwkv.blocks.2.ln2.weight": "pytorch_model-00001-of-00002.bin",
243
- "rwkv.blocks.20.attention.key.weight": "pytorch_model-00002-of-00002.bin",
244
- "rwkv.blocks.20.attention.output.weight": "pytorch_model-00002-of-00002.bin",
245
- "rwkv.blocks.20.attention.receptance.weight": "pytorch_model-00002-of-00002.bin",
246
- "rwkv.blocks.20.attention.time_decay": "pytorch_model-00002-of-00002.bin",
247
- "rwkv.blocks.20.attention.time_first": "pytorch_model-00002-of-00002.bin",
248
- "rwkv.blocks.20.attention.time_mix_key": "pytorch_model-00002-of-00002.bin",
249
- "rwkv.blocks.20.attention.time_mix_receptance": "pytorch_model-00002-of-00002.bin",
250
- "rwkv.blocks.20.attention.time_mix_value": "pytorch_model-00002-of-00002.bin",
251
- "rwkv.blocks.20.attention.value.weight": "pytorch_model-00002-of-00002.bin",
252
- "rwkv.blocks.20.feed_forward.key.weight": "pytorch_model-00002-of-00002.bin",
253
- "rwkv.blocks.20.feed_forward.receptance.weight": "pytorch_model-00002-of-00002.bin",
254
- "rwkv.blocks.20.feed_forward.time_mix_key": "pytorch_model-00002-of-00002.bin",
255
- "rwkv.blocks.20.feed_forward.time_mix_receptance": "pytorch_model-00002-of-00002.bin",
256
- "rwkv.blocks.20.feed_forward.value.weight": "pytorch_model-00002-of-00002.bin",
257
- "rwkv.blocks.20.ln1.bias": "pytorch_model-00002-of-00002.bin",
258
- "rwkv.blocks.20.ln1.weight": "pytorch_model-00002-of-00002.bin",
259
- "rwkv.blocks.20.ln2.bias": "pytorch_model-00002-of-00002.bin",
260
- "rwkv.blocks.20.ln2.weight": "pytorch_model-00002-of-00002.bin",
261
- "rwkv.blocks.21.attention.key.weight": "pytorch_model-00002-of-00002.bin",
262
- "rwkv.blocks.21.attention.output.weight": "pytorch_model-00002-of-00002.bin",
263
- "rwkv.blocks.21.attention.receptance.weight": "pytorch_model-00002-of-00002.bin",
264
- "rwkv.blocks.21.attention.time_decay": "pytorch_model-00002-of-00002.bin",
265
- "rwkv.blocks.21.attention.time_first": "pytorch_model-00002-of-00002.bin",
266
- "rwkv.blocks.21.attention.time_mix_key": "pytorch_model-00002-of-00002.bin",
267
- "rwkv.blocks.21.attention.time_mix_receptance": "pytorch_model-00002-of-00002.bin",
268
- "rwkv.blocks.21.attention.time_mix_value": "pytorch_model-00002-of-00002.bin",
269
- "rwkv.blocks.21.attention.value.weight": "pytorch_model-00002-of-00002.bin",
270
- "rwkv.blocks.21.feed_forward.key.weight": "pytorch_model-00002-of-00002.bin",
271
- "rwkv.blocks.21.feed_forward.receptance.weight": "pytorch_model-00002-of-00002.bin",
272
- "rwkv.blocks.21.feed_forward.time_mix_key": "pytorch_model-00002-of-00002.bin",
273
- "rwkv.blocks.21.feed_forward.time_mix_receptance": "pytorch_model-00002-of-00002.bin",
274
- "rwkv.blocks.21.feed_forward.value.weight": "pytorch_model-00002-of-00002.bin",
275
- "rwkv.blocks.21.ln1.bias": "pytorch_model-00002-of-00002.bin",
276
- "rwkv.blocks.21.ln1.weight": "pytorch_model-00002-of-00002.bin",
277
- "rwkv.blocks.21.ln2.bias": "pytorch_model-00002-of-00002.bin",
278
- "rwkv.blocks.21.ln2.weight": "pytorch_model-00002-of-00002.bin",
279
- "rwkv.blocks.22.attention.key.weight": "pytorch_model-00002-of-00002.bin",
280
- "rwkv.blocks.22.attention.output.weight": "pytorch_model-00002-of-00002.bin",
281
- "rwkv.blocks.22.attention.receptance.weight": "pytorch_model-00002-of-00002.bin",
282
- "rwkv.blocks.22.attention.time_decay": "pytorch_model-00002-of-00002.bin",
283
- "rwkv.blocks.22.attention.time_first": "pytorch_model-00002-of-00002.bin",
284
- "rwkv.blocks.22.attention.time_mix_key": "pytorch_model-00002-of-00002.bin",
285
- "rwkv.blocks.22.attention.time_mix_receptance": "pytorch_model-00002-of-00002.bin",
286
- "rwkv.blocks.22.attention.time_mix_value": "pytorch_model-00002-of-00002.bin",
287
- "rwkv.blocks.22.attention.value.weight": "pytorch_model-00002-of-00002.bin",
288
- "rwkv.blocks.22.feed_forward.key.weight": "pytorch_model-00002-of-00002.bin",
289
- "rwkv.blocks.22.feed_forward.receptance.weight": "pytorch_model-00002-of-00002.bin",
290
- "rwkv.blocks.22.feed_forward.time_mix_key": "pytorch_model-00002-of-00002.bin",
291
- "rwkv.blocks.22.feed_forward.time_mix_receptance": "pytorch_model-00002-of-00002.bin",
292
- "rwkv.blocks.22.feed_forward.value.weight": "pytorch_model-00002-of-00002.bin",
293
- "rwkv.blocks.22.ln1.bias": "pytorch_model-00002-of-00002.bin",
294
- "rwkv.blocks.22.ln1.weight": "pytorch_model-00002-of-00002.bin",
295
- "rwkv.blocks.22.ln2.bias": "pytorch_model-00002-of-00002.bin",
296
- "rwkv.blocks.22.ln2.weight": "pytorch_model-00002-of-00002.bin",
297
- "rwkv.blocks.23.attention.key.weight": "pytorch_model-00002-of-00002.bin",
298
- "rwkv.blocks.23.attention.output.weight": "pytorch_model-00002-of-00002.bin",
299
- "rwkv.blocks.23.attention.receptance.weight": "pytorch_model-00002-of-00002.bin",
300
- "rwkv.blocks.23.attention.time_decay": "pytorch_model-00002-of-00002.bin",
301
- "rwkv.blocks.23.attention.time_first": "pytorch_model-00002-of-00002.bin",
302
- "rwkv.blocks.23.attention.time_mix_key": "pytorch_model-00002-of-00002.bin",
303
- "rwkv.blocks.23.attention.time_mix_receptance": "pytorch_model-00002-of-00002.bin",
304
- "rwkv.blocks.23.attention.time_mix_value": "pytorch_model-00002-of-00002.bin",
305
- "rwkv.blocks.23.attention.value.weight": "pytorch_model-00002-of-00002.bin",
306
- "rwkv.blocks.23.feed_forward.key.weight": "pytorch_model-00002-of-00002.bin",
307
- "rwkv.blocks.23.feed_forward.receptance.weight": "pytorch_model-00002-of-00002.bin",
308
- "rwkv.blocks.23.feed_forward.time_mix_key": "pytorch_model-00002-of-00002.bin",
309
- "rwkv.blocks.23.feed_forward.time_mix_receptance": "pytorch_model-00002-of-00002.bin",
310
- "rwkv.blocks.23.feed_forward.value.weight": "pytorch_model-00002-of-00002.bin",
311
- "rwkv.blocks.23.ln1.bias": "pytorch_model-00002-of-00002.bin",
312
- "rwkv.blocks.23.ln1.weight": "pytorch_model-00002-of-00002.bin",
313
- "rwkv.blocks.23.ln2.bias": "pytorch_model-00002-of-00002.bin",
314
- "rwkv.blocks.23.ln2.weight": "pytorch_model-00002-of-00002.bin",
315
- "rwkv.blocks.3.attention.key.weight": "pytorch_model-00001-of-00002.bin",
316
- "rwkv.blocks.3.attention.output.weight": "pytorch_model-00001-of-00002.bin",
317
- "rwkv.blocks.3.attention.receptance.weight": "pytorch_model-00001-of-00002.bin",
318
- "rwkv.blocks.3.attention.time_decay": "pytorch_model-00001-of-00002.bin",
319
- "rwkv.blocks.3.attention.time_first": "pytorch_model-00001-of-00002.bin",
320
- "rwkv.blocks.3.attention.time_mix_key": "pytorch_model-00001-of-00002.bin",
321
- "rwkv.blocks.3.attention.time_mix_receptance": "pytorch_model-00001-of-00002.bin",
322
- "rwkv.blocks.3.attention.time_mix_value": "pytorch_model-00001-of-00002.bin",
323
- "rwkv.blocks.3.attention.value.weight": "pytorch_model-00001-of-00002.bin",
324
- "rwkv.blocks.3.feed_forward.key.weight": "pytorch_model-00001-of-00002.bin",
325
- "rwkv.blocks.3.feed_forward.receptance.weight": "pytorch_model-00001-of-00002.bin",
326
- "rwkv.blocks.3.feed_forward.time_mix_key": "pytorch_model-00001-of-00002.bin",
327
- "rwkv.blocks.3.feed_forward.time_mix_receptance": "pytorch_model-00001-of-00002.bin",
328
- "rwkv.blocks.3.feed_forward.value.weight": "pytorch_model-00001-of-00002.bin",
329
- "rwkv.blocks.3.ln1.bias": "pytorch_model-00001-of-00002.bin",
330
- "rwkv.blocks.3.ln1.weight": "pytorch_model-00001-of-00002.bin",
331
- "rwkv.blocks.3.ln2.bias": "pytorch_model-00001-of-00002.bin",
332
- "rwkv.blocks.3.ln2.weight": "pytorch_model-00001-of-00002.bin",
333
- "rwkv.blocks.4.attention.key.weight": "pytorch_model-00001-of-00002.bin",
334
- "rwkv.blocks.4.attention.output.weight": "pytorch_model-00001-of-00002.bin",
335
- "rwkv.blocks.4.attention.receptance.weight": "pytorch_model-00001-of-00002.bin",
336
- "rwkv.blocks.4.attention.time_decay": "pytorch_model-00001-of-00002.bin",
337
- "rwkv.blocks.4.attention.time_first": "pytorch_model-00001-of-00002.bin",
338
- "rwkv.blocks.4.attention.time_mix_key": "pytorch_model-00001-of-00002.bin",
339
- "rwkv.blocks.4.attention.time_mix_receptance": "pytorch_model-00001-of-00002.bin",
340
- "rwkv.blocks.4.attention.time_mix_value": "pytorch_model-00001-of-00002.bin",
341
- "rwkv.blocks.4.attention.value.weight": "pytorch_model-00001-of-00002.bin",
342
- "rwkv.blocks.4.feed_forward.key.weight": "pytorch_model-00001-of-00002.bin",
343
- "rwkv.blocks.4.feed_forward.receptance.weight": "pytorch_model-00001-of-00002.bin",
344
- "rwkv.blocks.4.feed_forward.time_mix_key": "pytorch_model-00001-of-00002.bin",
345
- "rwkv.blocks.4.feed_forward.time_mix_receptance": "pytorch_model-00001-of-00002.bin",
346
- "rwkv.blocks.4.feed_forward.value.weight": "pytorch_model-00001-of-00002.bin",
347
- "rwkv.blocks.4.ln1.bias": "pytorch_model-00001-of-00002.bin",
348
- "rwkv.blocks.4.ln1.weight": "pytorch_model-00001-of-00002.bin",
349
- "rwkv.blocks.4.ln2.bias": "pytorch_model-00001-of-00002.bin",
350
- "rwkv.blocks.4.ln2.weight": "pytorch_model-00001-of-00002.bin",
351
- "rwkv.blocks.5.attention.key.weight": "pytorch_model-00001-of-00002.bin",
352
- "rwkv.blocks.5.attention.output.weight": "pytorch_model-00001-of-00002.bin",
353
- "rwkv.blocks.5.attention.receptance.weight": "pytorch_model-00001-of-00002.bin",
354
- "rwkv.blocks.5.attention.time_decay": "pytorch_model-00001-of-00002.bin",
355
- "rwkv.blocks.5.attention.time_first": "pytorch_model-00001-of-00002.bin",
356
- "rwkv.blocks.5.attention.time_mix_key": "pytorch_model-00001-of-00002.bin",
357
- "rwkv.blocks.5.attention.time_mix_receptance": "pytorch_model-00001-of-00002.bin",
358
- "rwkv.blocks.5.attention.time_mix_value": "pytorch_model-00001-of-00002.bin",
359
- "rwkv.blocks.5.attention.value.weight": "pytorch_model-00001-of-00002.bin",
360
- "rwkv.blocks.5.feed_forward.key.weight": "pytorch_model-00001-of-00002.bin",
361
- "rwkv.blocks.5.feed_forward.receptance.weight": "pytorch_model-00001-of-00002.bin",
362
- "rwkv.blocks.5.feed_forward.time_mix_key": "pytorch_model-00001-of-00002.bin",
363
- "rwkv.blocks.5.feed_forward.time_mix_receptance": "pytorch_model-00001-of-00002.bin",
364
- "rwkv.blocks.5.feed_forward.value.weight": "pytorch_model-00001-of-00002.bin",
365
- "rwkv.blocks.5.ln1.bias": "pytorch_model-00001-of-00002.bin",
366
- "rwkv.blocks.5.ln1.weight": "pytorch_model-00001-of-00002.bin",
367
- "rwkv.blocks.5.ln2.bias": "pytorch_model-00001-of-00002.bin",
368
- "rwkv.blocks.5.ln2.weight": "pytorch_model-00001-of-00002.bin",
369
- "rwkv.blocks.6.attention.key.weight": "pytorch_model-00001-of-00002.bin",
370
- "rwkv.blocks.6.attention.output.weight": "pytorch_model-00001-of-00002.bin",
371
- "rwkv.blocks.6.attention.receptance.weight": "pytorch_model-00001-of-00002.bin",
372
- "rwkv.blocks.6.attention.time_decay": "pytorch_model-00001-of-00002.bin",
373
- "rwkv.blocks.6.attention.time_first": "pytorch_model-00001-of-00002.bin",
374
- "rwkv.blocks.6.attention.time_mix_key": "pytorch_model-00001-of-00002.bin",
375
- "rwkv.blocks.6.attention.time_mix_receptance": "pytorch_model-00001-of-00002.bin",
376
- "rwkv.blocks.6.attention.time_mix_value": "pytorch_model-00001-of-00002.bin",
377
- "rwkv.blocks.6.attention.value.weight": "pytorch_model-00001-of-00002.bin",
378
- "rwkv.blocks.6.feed_forward.key.weight": "pytorch_model-00001-of-00002.bin",
379
- "rwkv.blocks.6.feed_forward.receptance.weight": "pytorch_model-00001-of-00002.bin",
380
- "rwkv.blocks.6.feed_forward.time_mix_key": "pytorch_model-00001-of-00002.bin",
381
- "rwkv.blocks.6.feed_forward.time_mix_receptance": "pytorch_model-00001-of-00002.bin",
382
- "rwkv.blocks.6.feed_forward.value.weight": "pytorch_model-00001-of-00002.bin",
383
- "rwkv.blocks.6.ln1.bias": "pytorch_model-00001-of-00002.bin",
384
- "rwkv.blocks.6.ln1.weight": "pytorch_model-00001-of-00002.bin",
385
- "rwkv.blocks.6.ln2.bias": "pytorch_model-00001-of-00002.bin",
386
- "rwkv.blocks.6.ln2.weight": "pytorch_model-00001-of-00002.bin",
387
- "rwkv.blocks.7.attention.key.weight": "pytorch_model-00001-of-00002.bin",
388
- "rwkv.blocks.7.attention.output.weight": "pytorch_model-00001-of-00002.bin",
389
- "rwkv.blocks.7.attention.receptance.weight": "pytorch_model-00001-of-00002.bin",
390
- "rwkv.blocks.7.attention.time_decay": "pytorch_model-00001-of-00002.bin",
391
- "rwkv.blocks.7.attention.time_first": "pytorch_model-00001-of-00002.bin",
392
- "rwkv.blocks.7.attention.time_mix_key": "pytorch_model-00001-of-00002.bin",
393
- "rwkv.blocks.7.attention.time_mix_receptance": "pytorch_model-00001-of-00002.bin",
394
- "rwkv.blocks.7.attention.time_mix_value": "pytorch_model-00001-of-00002.bin",
395
- "rwkv.blocks.7.attention.value.weight": "pytorch_model-00001-of-00002.bin",
396
- "rwkv.blocks.7.feed_forward.key.weight": "pytorch_model-00001-of-00002.bin",
397
- "rwkv.blocks.7.feed_forward.receptance.weight": "pytorch_model-00001-of-00002.bin",
398
- "rwkv.blocks.7.feed_forward.time_mix_key": "pytorch_model-00001-of-00002.bin",
399
- "rwkv.blocks.7.feed_forward.time_mix_receptance": "pytorch_model-00001-of-00002.bin",
400
- "rwkv.blocks.7.feed_forward.value.weight": "pytorch_model-00001-of-00002.bin",
401
- "rwkv.blocks.7.ln1.bias": "pytorch_model-00001-of-00002.bin",
402
- "rwkv.blocks.7.ln1.weight": "pytorch_model-00001-of-00002.bin",
403
- "rwkv.blocks.7.ln2.bias": "pytorch_model-00001-of-00002.bin",
404
- "rwkv.blocks.7.ln2.weight": "pytorch_model-00001-of-00002.bin",
405
- "rwkv.blocks.8.attention.key.weight": "pytorch_model-00001-of-00002.bin",
406
- "rwkv.blocks.8.attention.output.weight": "pytorch_model-00001-of-00002.bin",
407
- "rwkv.blocks.8.attention.receptance.weight": "pytorch_model-00001-of-00002.bin",
408
- "rwkv.blocks.8.attention.time_decay": "pytorch_model-00001-of-00002.bin",
409
- "rwkv.blocks.8.attention.time_first": "pytorch_model-00001-of-00002.bin",
410
- "rwkv.blocks.8.attention.time_mix_key": "pytorch_model-00001-of-00002.bin",
411
- "rwkv.blocks.8.attention.time_mix_receptance": "pytorch_model-00001-of-00002.bin",
412
- "rwkv.blocks.8.attention.time_mix_value": "pytorch_model-00001-of-00002.bin",
413
- "rwkv.blocks.8.attention.value.weight": "pytorch_model-00001-of-00002.bin",
414
- "rwkv.blocks.8.feed_forward.key.weight": "pytorch_model-00001-of-00002.bin",
415
- "rwkv.blocks.8.feed_forward.receptance.weight": "pytorch_model-00001-of-00002.bin",
416
- "rwkv.blocks.8.feed_forward.time_mix_key": "pytorch_model-00001-of-00002.bin",
417
- "rwkv.blocks.8.feed_forward.time_mix_receptance": "pytorch_model-00001-of-00002.bin",
418
- "rwkv.blocks.8.feed_forward.value.weight": "pytorch_model-00001-of-00002.bin",
419
- "rwkv.blocks.8.ln1.bias": "pytorch_model-00001-of-00002.bin",
420
- "rwkv.blocks.8.ln1.weight": "pytorch_model-00001-of-00002.bin",
421
- "rwkv.blocks.8.ln2.bias": "pytorch_model-00001-of-00002.bin",
422
- "rwkv.blocks.8.ln2.weight": "pytorch_model-00001-of-00002.bin",
423
- "rwkv.blocks.9.attention.key.weight": "pytorch_model-00001-of-00002.bin",
424
- "rwkv.blocks.9.attention.output.weight": "pytorch_model-00001-of-00002.bin",
425
- "rwkv.blocks.9.attention.receptance.weight": "pytorch_model-00001-of-00002.bin",
426
- "rwkv.blocks.9.attention.time_decay": "pytorch_model-00001-of-00002.bin",
427
- "rwkv.blocks.9.attention.time_first": "pytorch_model-00001-of-00002.bin",
428
- "rwkv.blocks.9.attention.time_mix_key": "pytorch_model-00001-of-00002.bin",
429
- "rwkv.blocks.9.attention.time_mix_receptance": "pytorch_model-00001-of-00002.bin",
430
- "rwkv.blocks.9.attention.time_mix_value": "pytorch_model-00001-of-00002.bin",
431
- "rwkv.blocks.9.attention.value.weight": "pytorch_model-00001-of-00002.bin",
432
- "rwkv.blocks.9.feed_forward.key.weight": "pytorch_model-00001-of-00002.bin",
433
- "rwkv.blocks.9.feed_forward.receptance.weight": "pytorch_model-00001-of-00002.bin",
434
- "rwkv.blocks.9.feed_forward.time_mix_key": "pytorch_model-00001-of-00002.bin",
435
- "rwkv.blocks.9.feed_forward.time_mix_receptance": "pytorch_model-00001-of-00002.bin",
436
- "rwkv.blocks.9.feed_forward.value.weight": "pytorch_model-00001-of-00002.bin",
437
- "rwkv.blocks.9.ln1.bias": "pytorch_model-00001-of-00002.bin",
438
- "rwkv.blocks.9.ln1.weight": "pytorch_model-00001-of-00002.bin",
439
- "rwkv.blocks.9.ln2.bias": "pytorch_model-00001-of-00002.bin",
440
- "rwkv.blocks.9.ln2.weight": "pytorch_model-00001-of-00002.bin",
441
- "rwkv.embeddings.weight": "pytorch_model-00001-of-00002.bin",
442
- "rwkv.ln_out.bias": "pytorch_model-00002-of-00002.bin",
443
- "rwkv.ln_out.weight": "pytorch_model-00002-of-00002.bin"
444
  }
445
  }
 
3
  "total_size": 6088654848
4
  },
5
  "weight_map": {
6
+ "head.weight": "pytorch_model-00007-of-00007.bin",
7
+ "rwkv.blocks.0.attention.key.weight": "pytorch_model-00001-of-00007.bin",
8
+ "rwkv.blocks.0.attention.output.weight": "pytorch_model-00001-of-00007.bin",
9
+ "rwkv.blocks.0.attention.receptance.weight": "pytorch_model-00001-of-00007.bin",
10
+ "rwkv.blocks.0.attention.time_decay": "pytorch_model-00001-of-00007.bin",
11
+ "rwkv.blocks.0.attention.time_first": "pytorch_model-00001-of-00007.bin",
12
+ "rwkv.blocks.0.attention.time_mix_key": "pytorch_model-00001-of-00007.bin",
13
+ "rwkv.blocks.0.attention.time_mix_receptance": "pytorch_model-00001-of-00007.bin",
14
+ "rwkv.blocks.0.attention.time_mix_value": "pytorch_model-00001-of-00007.bin",
15
+ "rwkv.blocks.0.attention.value.weight": "pytorch_model-00001-of-00007.bin",
16
+ "rwkv.blocks.0.feed_forward.key.weight": "pytorch_model-00001-of-00007.bin",
17
+ "rwkv.blocks.0.feed_forward.receptance.weight": "pytorch_model-00001-of-00007.bin",
18
+ "rwkv.blocks.0.feed_forward.time_mix_key": "pytorch_model-00001-of-00007.bin",
19
+ "rwkv.blocks.0.feed_forward.time_mix_receptance": "pytorch_model-00001-of-00007.bin",
20
+ "rwkv.blocks.0.feed_forward.value.weight": "pytorch_model-00001-of-00007.bin",
21
+ "rwkv.blocks.0.ln1.bias": "pytorch_model-00001-of-00007.bin",
22
+ "rwkv.blocks.0.ln1.weight": "pytorch_model-00001-of-00007.bin",
23
+ "rwkv.blocks.0.ln2.bias": "pytorch_model-00001-of-00007.bin",
24
+ "rwkv.blocks.0.ln2.weight": "pytorch_model-00001-of-00007.bin",
25
+ "rwkv.blocks.0.pre_ln.bias": "pytorch_model-00001-of-00007.bin",
26
+ "rwkv.blocks.0.pre_ln.weight": "pytorch_model-00001-of-00007.bin",
27
+ "rwkv.blocks.1.attention.key.weight": "pytorch_model-00001-of-00007.bin",
28
+ "rwkv.blocks.1.attention.output.weight": "pytorch_model-00001-of-00007.bin",
29
+ "rwkv.blocks.1.attention.receptance.weight": "pytorch_model-00001-of-00007.bin",
30
+ "rwkv.blocks.1.attention.time_decay": "pytorch_model-00001-of-00007.bin",
31
+ "rwkv.blocks.1.attention.time_first": "pytorch_model-00001-of-00007.bin",
32
+ "rwkv.blocks.1.attention.time_mix_key": "pytorch_model-00001-of-00007.bin",
33
+ "rwkv.blocks.1.attention.time_mix_receptance": "pytorch_model-00001-of-00007.bin",
34
+ "rwkv.blocks.1.attention.time_mix_value": "pytorch_model-00001-of-00007.bin",
35
+ "rwkv.blocks.1.attention.value.weight": "pytorch_model-00001-of-00007.bin",
36
+ "rwkv.blocks.1.feed_forward.key.weight": "pytorch_model-00001-of-00007.bin",
37
+ "rwkv.blocks.1.feed_forward.receptance.weight": "pytorch_model-00001-of-00007.bin",
38
+ "rwkv.blocks.1.feed_forward.time_mix_key": "pytorch_model-00001-of-00007.bin",
39
+ "rwkv.blocks.1.feed_forward.time_mix_receptance": "pytorch_model-00001-of-00007.bin",
40
+ "rwkv.blocks.1.feed_forward.value.weight": "pytorch_model-00001-of-00007.bin",
41
+ "rwkv.blocks.1.ln1.bias": "pytorch_model-00001-of-00007.bin",
42
+ "rwkv.blocks.1.ln1.weight": "pytorch_model-00001-of-00007.bin",
43
+ "rwkv.blocks.1.ln2.bias": "pytorch_model-00001-of-00007.bin",
44
+ "rwkv.blocks.1.ln2.weight": "pytorch_model-00001-of-00007.bin",
45
+ "rwkv.blocks.10.attention.key.weight": "pytorch_model-00003-of-00007.bin",
46
+ "rwkv.blocks.10.attention.output.weight": "pytorch_model-00003-of-00007.bin",
47
+ "rwkv.blocks.10.attention.receptance.weight": "pytorch_model-00003-of-00007.bin",
48
+ "rwkv.blocks.10.attention.time_decay": "pytorch_model-00003-of-00007.bin",
49
+ "rwkv.blocks.10.attention.time_first": "pytorch_model-00003-of-00007.bin",
50
+ "rwkv.blocks.10.attention.time_mix_key": "pytorch_model-00003-of-00007.bin",
51
+ "rwkv.blocks.10.attention.time_mix_receptance": "pytorch_model-00003-of-00007.bin",
52
+ "rwkv.blocks.10.attention.time_mix_value": "pytorch_model-00003-of-00007.bin",
53
+ "rwkv.blocks.10.attention.value.weight": "pytorch_model-00003-of-00007.bin",
54
+ "rwkv.blocks.10.feed_forward.key.weight": "pytorch_model-00003-of-00007.bin",
55
+ "rwkv.blocks.10.feed_forward.receptance.weight": "pytorch_model-00003-of-00007.bin",
56
+ "rwkv.blocks.10.feed_forward.time_mix_key": "pytorch_model-00003-of-00007.bin",
57
+ "rwkv.blocks.10.feed_forward.time_mix_receptance": "pytorch_model-00003-of-00007.bin",
58
+ "rwkv.blocks.10.feed_forward.value.weight": "pytorch_model-00003-of-00007.bin",
59
+ "rwkv.blocks.10.ln1.bias": "pytorch_model-00003-of-00007.bin",
60
+ "rwkv.blocks.10.ln1.weight": "pytorch_model-00003-of-00007.bin",
61
+ "rwkv.blocks.10.ln2.bias": "pytorch_model-00003-of-00007.bin",
62
+ "rwkv.blocks.10.ln2.weight": "pytorch_model-00003-of-00007.bin",
63
+ "rwkv.blocks.11.attention.key.weight": "pytorch_model-00003-of-00007.bin",
64
+ "rwkv.blocks.11.attention.output.weight": "pytorch_model-00003-of-00007.bin",
65
+ "rwkv.blocks.11.attention.receptance.weight": "pytorch_model-00003-of-00007.bin",
66
+ "rwkv.blocks.11.attention.time_decay": "pytorch_model-00003-of-00007.bin",
67
+ "rwkv.blocks.11.attention.time_first": "pytorch_model-00003-of-00007.bin",
68
+ "rwkv.blocks.11.attention.time_mix_key": "pytorch_model-00003-of-00007.bin",
69
+ "rwkv.blocks.11.attention.time_mix_receptance": "pytorch_model-00003-of-00007.bin",
70
+ "rwkv.blocks.11.attention.time_mix_value": "pytorch_model-00003-of-00007.bin",
71
+ "rwkv.blocks.11.attention.value.weight": "pytorch_model-00003-of-00007.bin",
72
+ "rwkv.blocks.11.feed_forward.key.weight": "pytorch_model-00003-of-00007.bin",
73
+ "rwkv.blocks.11.feed_forward.receptance.weight": "pytorch_model-00003-of-00007.bin",
74
+ "rwkv.blocks.11.feed_forward.time_mix_key": "pytorch_model-00003-of-00007.bin",
75
+ "rwkv.blocks.11.feed_forward.time_mix_receptance": "pytorch_model-00003-of-00007.bin",
76
+ "rwkv.blocks.11.feed_forward.value.weight": "pytorch_model-00004-of-00007.bin",
77
+ "rwkv.blocks.11.ln1.bias": "pytorch_model-00003-of-00007.bin",
78
+ "rwkv.blocks.11.ln1.weight": "pytorch_model-00003-of-00007.bin",
79
+ "rwkv.blocks.11.ln2.bias": "pytorch_model-00003-of-00007.bin",
80
+ "rwkv.blocks.11.ln2.weight": "pytorch_model-00003-of-00007.bin",
81
+ "rwkv.blocks.12.attention.key.weight": "pytorch_model-00004-of-00007.bin",
82
+ "rwkv.blocks.12.attention.output.weight": "pytorch_model-00004-of-00007.bin",
83
+ "rwkv.blocks.12.attention.receptance.weight": "pytorch_model-00004-of-00007.bin",
84
+ "rwkv.blocks.12.attention.time_decay": "pytorch_model-00004-of-00007.bin",
85
+ "rwkv.blocks.12.attention.time_first": "pytorch_model-00004-of-00007.bin",
86
+ "rwkv.blocks.12.attention.time_mix_key": "pytorch_model-00004-of-00007.bin",
87
+ "rwkv.blocks.12.attention.time_mix_receptance": "pytorch_model-00004-of-00007.bin",
88
+ "rwkv.blocks.12.attention.time_mix_value": "pytorch_model-00004-of-00007.bin",
89
+ "rwkv.blocks.12.attention.value.weight": "pytorch_model-00004-of-00007.bin",
90
+ "rwkv.blocks.12.feed_forward.key.weight": "pytorch_model-00004-of-00007.bin",
91
+ "rwkv.blocks.12.feed_forward.receptance.weight": "pytorch_model-00004-of-00007.bin",
92
+ "rwkv.blocks.12.feed_forward.time_mix_key": "pytorch_model-00004-of-00007.bin",
93
+ "rwkv.blocks.12.feed_forward.time_mix_receptance": "pytorch_model-00004-of-00007.bin",
94
+ "rwkv.blocks.12.feed_forward.value.weight": "pytorch_model-00004-of-00007.bin",
95
+ "rwkv.blocks.12.ln1.bias": "pytorch_model-00004-of-00007.bin",
96
+ "rwkv.blocks.12.ln1.weight": "pytorch_model-00004-of-00007.bin",
97
+ "rwkv.blocks.12.ln2.bias": "pytorch_model-00004-of-00007.bin",
98
+ "rwkv.blocks.12.ln2.weight": "pytorch_model-00004-of-00007.bin",
99
+ "rwkv.blocks.13.attention.key.weight": "pytorch_model-00004-of-00007.bin",
100
+ "rwkv.blocks.13.attention.output.weight": "pytorch_model-00004-of-00007.bin",
101
+ "rwkv.blocks.13.attention.receptance.weight": "pytorch_model-00004-of-00007.bin",
102
+ "rwkv.blocks.13.attention.time_decay": "pytorch_model-00004-of-00007.bin",
103
+ "rwkv.blocks.13.attention.time_first": "pytorch_model-00004-of-00007.bin",
104
+ "rwkv.blocks.13.attention.time_mix_key": "pytorch_model-00004-of-00007.bin",
105
+ "rwkv.blocks.13.attention.time_mix_receptance": "pytorch_model-00004-of-00007.bin",
106
+ "rwkv.blocks.13.attention.time_mix_value": "pytorch_model-00004-of-00007.bin",
107
+ "rwkv.blocks.13.attention.value.weight": "pytorch_model-00004-of-00007.bin",
108
+ "rwkv.blocks.13.feed_forward.key.weight": "pytorch_model-00004-of-00007.bin",
109
+ "rwkv.blocks.13.feed_forward.receptance.weight": "pytorch_model-00004-of-00007.bin",
110
+ "rwkv.blocks.13.feed_forward.time_mix_key": "pytorch_model-00004-of-00007.bin",
111
+ "rwkv.blocks.13.feed_forward.time_mix_receptance": "pytorch_model-00004-of-00007.bin",
112
+ "rwkv.blocks.13.feed_forward.value.weight": "pytorch_model-00004-of-00007.bin",
113
+ "rwkv.blocks.13.ln1.bias": "pytorch_model-00004-of-00007.bin",
114
+ "rwkv.blocks.13.ln1.weight": "pytorch_model-00004-of-00007.bin",
115
+ "rwkv.blocks.13.ln2.bias": "pytorch_model-00004-of-00007.bin",
116
+ "rwkv.blocks.13.ln2.weight": "pytorch_model-00004-of-00007.bin",
117
+ "rwkv.blocks.14.attention.key.weight": "pytorch_model-00004-of-00007.bin",
118
+ "rwkv.blocks.14.attention.output.weight": "pytorch_model-00004-of-00007.bin",
119
+ "rwkv.blocks.14.attention.receptance.weight": "pytorch_model-00004-of-00007.bin",
120
+ "rwkv.blocks.14.attention.time_decay": "pytorch_model-00004-of-00007.bin",
121
+ "rwkv.blocks.14.attention.time_first": "pytorch_model-00004-of-00007.bin",
122
+ "rwkv.blocks.14.attention.time_mix_key": "pytorch_model-00004-of-00007.bin",
123
+ "rwkv.blocks.14.attention.time_mix_receptance": "pytorch_model-00004-of-00007.bin",
124
+ "rwkv.blocks.14.attention.time_mix_value": "pytorch_model-00004-of-00007.bin",
125
+ "rwkv.blocks.14.attention.value.weight": "pytorch_model-00004-of-00007.bin",
126
+ "rwkv.blocks.14.feed_forward.key.weight": "pytorch_model-00004-of-00007.bin",
127
+ "rwkv.blocks.14.feed_forward.receptance.weight": "pytorch_model-00004-of-00007.bin",
128
+ "rwkv.blocks.14.feed_forward.time_mix_key": "pytorch_model-00004-of-00007.bin",
129
+ "rwkv.blocks.14.feed_forward.time_mix_receptance": "pytorch_model-00004-of-00007.bin",
130
+ "rwkv.blocks.14.feed_forward.value.weight": "pytorch_model-00004-of-00007.bin",
131
+ "rwkv.blocks.14.ln1.bias": "pytorch_model-00004-of-00007.bin",
132
+ "rwkv.blocks.14.ln1.weight": "pytorch_model-00004-of-00007.bin",
133
+ "rwkv.blocks.14.ln2.bias": "pytorch_model-00004-of-00007.bin",
134
+ "rwkv.blocks.14.ln2.weight": "pytorch_model-00004-of-00007.bin",
135
+ "rwkv.blocks.15.attention.key.weight": "pytorch_model-00004-of-00007.bin",
136
+ "rwkv.blocks.15.attention.output.weight": "pytorch_model-00004-of-00007.bin",
137
+ "rwkv.blocks.15.attention.receptance.weight": "pytorch_model-00004-of-00007.bin",
138
+ "rwkv.blocks.15.attention.time_decay": "pytorch_model-00004-of-00007.bin",
139
+ "rwkv.blocks.15.attention.time_first": "pytorch_model-00004-of-00007.bin",
140
+ "rwkv.blocks.15.attention.time_mix_key": "pytorch_model-00004-of-00007.bin",
141
+ "rwkv.blocks.15.attention.time_mix_receptance": "pytorch_model-00004-of-00007.bin",
142
+ "rwkv.blocks.15.attention.time_mix_value": "pytorch_model-00004-of-00007.bin",
143
+ "rwkv.blocks.15.attention.value.weight": "pytorch_model-00004-of-00007.bin",
144
+ "rwkv.blocks.15.feed_forward.key.weight": "pytorch_model-00004-of-00007.bin",
145
+ "rwkv.blocks.15.feed_forward.receptance.weight": "pytorch_model-00004-of-00007.bin",
146
+ "rwkv.blocks.15.feed_forward.time_mix_key": "pytorch_model-00004-of-00007.bin",
147
+ "rwkv.blocks.15.feed_forward.time_mix_receptance": "pytorch_model-00004-of-00007.bin",
148
+ "rwkv.blocks.15.feed_forward.value.weight": "pytorch_model-00004-of-00007.bin",
149
+ "rwkv.blocks.15.ln1.bias": "pytorch_model-00004-of-00007.bin",
150
+ "rwkv.blocks.15.ln1.weight": "pytorch_model-00004-of-00007.bin",
151
+ "rwkv.blocks.15.ln2.bias": "pytorch_model-00004-of-00007.bin",
152
+ "rwkv.blocks.15.ln2.weight": "pytorch_model-00004-of-00007.bin",
153
+ "rwkv.blocks.16.attention.key.weight": "pytorch_model-00004-of-00007.bin",
154
+ "rwkv.blocks.16.attention.output.weight": "pytorch_model-00005-of-00007.bin",
155
+ "rwkv.blocks.16.attention.receptance.weight": "pytorch_model-00004-of-00007.bin",
156
+ "rwkv.blocks.16.attention.time_decay": "pytorch_model-00004-of-00007.bin",
157
+ "rwkv.blocks.16.attention.time_first": "pytorch_model-00004-of-00007.bin",
158
+ "rwkv.blocks.16.attention.time_mix_key": "pytorch_model-00004-of-00007.bin",
159
+ "rwkv.blocks.16.attention.time_mix_receptance": "pytorch_model-00004-of-00007.bin",
160
+ "rwkv.blocks.16.attention.time_mix_value": "pytorch_model-00004-of-00007.bin",
161
+ "rwkv.blocks.16.attention.value.weight": "pytorch_model-00004-of-00007.bin",
162
+ "rwkv.blocks.16.feed_forward.key.weight": "pytorch_model-00005-of-00007.bin",
163
+ "rwkv.blocks.16.feed_forward.receptance.weight": "pytorch_model-00005-of-00007.bin",
164
+ "rwkv.blocks.16.feed_forward.time_mix_key": "pytorch_model-00005-of-00007.bin",
165
+ "rwkv.blocks.16.feed_forward.time_mix_receptance": "pytorch_model-00005-of-00007.bin",
166
+ "rwkv.blocks.16.feed_forward.value.weight": "pytorch_model-00005-of-00007.bin",
167
+ "rwkv.blocks.16.ln1.bias": "pytorch_model-00004-of-00007.bin",
168
+ "rwkv.blocks.16.ln1.weight": "pytorch_model-00004-of-00007.bin",
169
+ "rwkv.blocks.16.ln2.bias": "pytorch_model-00004-of-00007.bin",
170
+ "rwkv.blocks.16.ln2.weight": "pytorch_model-00004-of-00007.bin",
171
+ "rwkv.blocks.17.attention.key.weight": "pytorch_model-00005-of-00007.bin",
172
+ "rwkv.blocks.17.attention.output.weight": "pytorch_model-00005-of-00007.bin",
173
+ "rwkv.blocks.17.attention.receptance.weight": "pytorch_model-00005-of-00007.bin",
174
+ "rwkv.blocks.17.attention.time_decay": "pytorch_model-00005-of-00007.bin",
175
+ "rwkv.blocks.17.attention.time_first": "pytorch_model-00005-of-00007.bin",
176
+ "rwkv.blocks.17.attention.time_mix_key": "pytorch_model-00005-of-00007.bin",
177
+ "rwkv.blocks.17.attention.time_mix_receptance": "pytorch_model-00005-of-00007.bin",
178
+ "rwkv.blocks.17.attention.time_mix_value": "pytorch_model-00005-of-00007.bin",
179
+ "rwkv.blocks.17.attention.value.weight": "pytorch_model-00005-of-00007.bin",
180
+ "rwkv.blocks.17.feed_forward.key.weight": "pytorch_model-00005-of-00007.bin",
181
+ "rwkv.blocks.17.feed_forward.receptance.weight": "pytorch_model-00005-of-00007.bin",
182
+ "rwkv.blocks.17.feed_forward.time_mix_key": "pytorch_model-00005-of-00007.bin",
183
+ "rwkv.blocks.17.feed_forward.time_mix_receptance": "pytorch_model-00005-of-00007.bin",
184
+ "rwkv.blocks.17.feed_forward.value.weight": "pytorch_model-00005-of-00007.bin",
185
+ "rwkv.blocks.17.ln1.bias": "pytorch_model-00005-of-00007.bin",
186
+ "rwkv.blocks.17.ln1.weight": "pytorch_model-00005-of-00007.bin",
187
+ "rwkv.blocks.17.ln2.bias": "pytorch_model-00005-of-00007.bin",
188
+ "rwkv.blocks.17.ln2.weight": "pytorch_model-00005-of-00007.bin",
189
+ "rwkv.blocks.18.attention.key.weight": "pytorch_model-00005-of-00007.bin",
190
+ "rwkv.blocks.18.attention.output.weight": "pytorch_model-00005-of-00007.bin",
191
+ "rwkv.blocks.18.attention.receptance.weight": "pytorch_model-00005-of-00007.bin",
192
+ "rwkv.blocks.18.attention.time_decay": "pytorch_model-00005-of-00007.bin",
193
+ "rwkv.blocks.18.attention.time_first": "pytorch_model-00005-of-00007.bin",
194
+ "rwkv.blocks.18.attention.time_mix_key": "pytorch_model-00005-of-00007.bin",
195
+ "rwkv.blocks.18.attention.time_mix_receptance": "pytorch_model-00005-of-00007.bin",
196
+ "rwkv.blocks.18.attention.time_mix_value": "pytorch_model-00005-of-00007.bin",
197
+ "rwkv.blocks.18.attention.value.weight": "pytorch_model-00005-of-00007.bin",
198
+ "rwkv.blocks.18.feed_forward.key.weight": "pytorch_model-00005-of-00007.bin",
199
+ "rwkv.blocks.18.feed_forward.receptance.weight": "pytorch_model-00005-of-00007.bin",
200
+ "rwkv.blocks.18.feed_forward.time_mix_key": "pytorch_model-00005-of-00007.bin",
201
+ "rwkv.blocks.18.feed_forward.time_mix_receptance": "pytorch_model-00005-of-00007.bin",
202
+ "rwkv.blocks.18.feed_forward.value.weight": "pytorch_model-00005-of-00007.bin",
203
+ "rwkv.blocks.18.ln1.bias": "pytorch_model-00005-of-00007.bin",
204
+ "rwkv.blocks.18.ln1.weight": "pytorch_model-00005-of-00007.bin",
205
+ "rwkv.blocks.18.ln2.bias": "pytorch_model-00005-of-00007.bin",
206
+ "rwkv.blocks.18.ln2.weight": "pytorch_model-00005-of-00007.bin",
207
+ "rwkv.blocks.19.attention.key.weight": "pytorch_model-00005-of-00007.bin",
208
+ "rwkv.blocks.19.attention.output.weight": "pytorch_model-00005-of-00007.bin",
209
+ "rwkv.blocks.19.attention.receptance.weight": "pytorch_model-00005-of-00007.bin",
210
+ "rwkv.blocks.19.attention.time_decay": "pytorch_model-00005-of-00007.bin",
211
+ "rwkv.blocks.19.attention.time_first": "pytorch_model-00005-of-00007.bin",
212
+ "rwkv.blocks.19.attention.time_mix_key": "pytorch_model-00005-of-00007.bin",
213
+ "rwkv.blocks.19.attention.time_mix_receptance": "pytorch_model-00005-of-00007.bin",
214
+ "rwkv.blocks.19.attention.time_mix_value": "pytorch_model-00005-of-00007.bin",
215
+ "rwkv.blocks.19.attention.value.weight": "pytorch_model-00005-of-00007.bin",
216
+ "rwkv.blocks.19.feed_forward.key.weight": "pytorch_model-00005-of-00007.bin",
217
+ "rwkv.blocks.19.feed_forward.receptance.weight": "pytorch_model-00005-of-00007.bin",
218
+ "rwkv.blocks.19.feed_forward.time_mix_key": "pytorch_model-00005-of-00007.bin",
219
+ "rwkv.blocks.19.feed_forward.time_mix_receptance": "pytorch_model-00005-of-00007.bin",
220
+ "rwkv.blocks.19.feed_forward.value.weight": "pytorch_model-00005-of-00007.bin",
221
+ "rwkv.blocks.19.ln1.bias": "pytorch_model-00005-of-00007.bin",
222
+ "rwkv.blocks.19.ln1.weight": "pytorch_model-00005-of-00007.bin",
223
+ "rwkv.blocks.19.ln2.bias": "pytorch_model-00005-of-00007.bin",
224
+ "rwkv.blocks.19.ln2.weight": "pytorch_model-00005-of-00007.bin",
225
+ "rwkv.blocks.2.attention.key.weight": "pytorch_model-00001-of-00007.bin",
226
+ "rwkv.blocks.2.attention.output.weight": "pytorch_model-00001-of-00007.bin",
227
+ "rwkv.blocks.2.attention.receptance.weight": "pytorch_model-00001-of-00007.bin",
228
+ "rwkv.blocks.2.attention.time_decay": "pytorch_model-00001-of-00007.bin",
229
+ "rwkv.blocks.2.attention.time_first": "pytorch_model-00001-of-00007.bin",
230
+ "rwkv.blocks.2.attention.time_mix_key": "pytorch_model-00001-of-00007.bin",
231
+ "rwkv.blocks.2.attention.time_mix_receptance": "pytorch_model-00001-of-00007.bin",
232
+ "rwkv.blocks.2.attention.time_mix_value": "pytorch_model-00001-of-00007.bin",
233
+ "rwkv.blocks.2.attention.value.weight": "pytorch_model-00001-of-00007.bin",
234
+ "rwkv.blocks.2.feed_forward.key.weight": "pytorch_model-00001-of-00007.bin",
235
+ "rwkv.blocks.2.feed_forward.receptance.weight": "pytorch_model-00002-of-00007.bin",
236
+ "rwkv.blocks.2.feed_forward.time_mix_key": "pytorch_model-00001-of-00007.bin",
237
+ "rwkv.blocks.2.feed_forward.time_mix_receptance": "pytorch_model-00001-of-00007.bin",
238
+ "rwkv.blocks.2.feed_forward.value.weight": "pytorch_model-00002-of-00007.bin",
239
+ "rwkv.blocks.2.ln1.bias": "pytorch_model-00001-of-00007.bin",
240
+ "rwkv.blocks.2.ln1.weight": "pytorch_model-00001-of-00007.bin",
241
+ "rwkv.blocks.2.ln2.bias": "pytorch_model-00001-of-00007.bin",
242
+ "rwkv.blocks.2.ln2.weight": "pytorch_model-00001-of-00007.bin",
243
+ "rwkv.blocks.20.attention.key.weight": "pytorch_model-00005-of-00007.bin",
244
+ "rwkv.blocks.20.attention.output.weight": "pytorch_model-00005-of-00007.bin",
245
+ "rwkv.blocks.20.attention.receptance.weight": "pytorch_model-00005-of-00007.bin",
246
+ "rwkv.blocks.20.attention.time_decay": "pytorch_model-00005-of-00007.bin",
247
+ "rwkv.blocks.20.attention.time_first": "pytorch_model-00005-of-00007.bin",
248
+ "rwkv.blocks.20.attention.time_mix_key": "pytorch_model-00005-of-00007.bin",
249
+ "rwkv.blocks.20.attention.time_mix_receptance": "pytorch_model-00005-of-00007.bin",
250
+ "rwkv.blocks.20.attention.time_mix_value": "pytorch_model-00005-of-00007.bin",
251
+ "rwkv.blocks.20.attention.value.weight": "pytorch_model-00005-of-00007.bin",
252
+ "rwkv.blocks.20.feed_forward.key.weight": "pytorch_model-00005-of-00007.bin",
253
+ "rwkv.blocks.20.feed_forward.receptance.weight": "pytorch_model-00005-of-00007.bin",
254
+ "rwkv.blocks.20.feed_forward.time_mix_key": "pytorch_model-00005-of-00007.bin",
255
+ "rwkv.blocks.20.feed_forward.time_mix_receptance": "pytorch_model-00005-of-00007.bin",
256
+ "rwkv.blocks.20.feed_forward.value.weight": "pytorch_model-00006-of-00007.bin",
257
+ "rwkv.blocks.20.ln1.bias": "pytorch_model-00005-of-00007.bin",
258
+ "rwkv.blocks.20.ln1.weight": "pytorch_model-00005-of-00007.bin",
259
+ "rwkv.blocks.20.ln2.bias": "pytorch_model-00005-of-00007.bin",
260
+ "rwkv.blocks.20.ln2.weight": "pytorch_model-00005-of-00007.bin",
261
+ "rwkv.blocks.21.attention.key.weight": "pytorch_model-00006-of-00007.bin",
262
+ "rwkv.blocks.21.attention.output.weight": "pytorch_model-00006-of-00007.bin",
263
+ "rwkv.blocks.21.attention.receptance.weight": "pytorch_model-00006-of-00007.bin",
264
+ "rwkv.blocks.21.attention.time_decay": "pytorch_model-00006-of-00007.bin",
265
+ "rwkv.blocks.21.attention.time_first": "pytorch_model-00006-of-00007.bin",
266
+ "rwkv.blocks.21.attention.time_mix_key": "pytorch_model-00006-of-00007.bin",
267
+ "rwkv.blocks.21.attention.time_mix_receptance": "pytorch_model-00006-of-00007.bin",
268
+ "rwkv.blocks.21.attention.time_mix_value": "pytorch_model-00006-of-00007.bin",
269
+ "rwkv.blocks.21.attention.value.weight": "pytorch_model-00006-of-00007.bin",
270
+ "rwkv.blocks.21.feed_forward.key.weight": "pytorch_model-00006-of-00007.bin",
271
+ "rwkv.blocks.21.feed_forward.receptance.weight": "pytorch_model-00006-of-00007.bin",
272
+ "rwkv.blocks.21.feed_forward.time_mix_key": "pytorch_model-00006-of-00007.bin",
273
+ "rwkv.blocks.21.feed_forward.time_mix_receptance": "pytorch_model-00006-of-00007.bin",
274
+ "rwkv.blocks.21.feed_forward.value.weight": "pytorch_model-00006-of-00007.bin",
275
+ "rwkv.blocks.21.ln1.bias": "pytorch_model-00006-of-00007.bin",
276
+ "rwkv.blocks.21.ln1.weight": "pytorch_model-00006-of-00007.bin",
277
+ "rwkv.blocks.21.ln2.bias": "pytorch_model-00006-of-00007.bin",
278
+ "rwkv.blocks.21.ln2.weight": "pytorch_model-00006-of-00007.bin",
279
+ "rwkv.blocks.22.attention.key.weight": "pytorch_model-00006-of-00007.bin",
280
+ "rwkv.blocks.22.attention.output.weight": "pytorch_model-00006-of-00007.bin",
281
+ "rwkv.blocks.22.attention.receptance.weight": "pytorch_model-00006-of-00007.bin",
282
+ "rwkv.blocks.22.attention.time_decay": "pytorch_model-00006-of-00007.bin",
283
+ "rwkv.blocks.22.attention.time_first": "pytorch_model-00006-of-00007.bin",
284
+ "rwkv.blocks.22.attention.time_mix_key": "pytorch_model-00006-of-00007.bin",
285
+ "rwkv.blocks.22.attention.time_mix_receptance": "pytorch_model-00006-of-00007.bin",
286
+ "rwkv.blocks.22.attention.time_mix_value": "pytorch_model-00006-of-00007.bin",
287
+ "rwkv.blocks.22.attention.value.weight": "pytorch_model-00006-of-00007.bin",
288
+ "rwkv.blocks.22.feed_forward.key.weight": "pytorch_model-00006-of-00007.bin",
289
+ "rwkv.blocks.22.feed_forward.receptance.weight": "pytorch_model-00006-of-00007.bin",
290
+ "rwkv.blocks.22.feed_forward.time_mix_key": "pytorch_model-00006-of-00007.bin",
291
+ "rwkv.blocks.22.feed_forward.time_mix_receptance": "pytorch_model-00006-of-00007.bin",
292
+ "rwkv.blocks.22.feed_forward.value.weight": "pytorch_model-00006-of-00007.bin",
293
+ "rwkv.blocks.22.ln1.bias": "pytorch_model-00006-of-00007.bin",
294
+ "rwkv.blocks.22.ln1.weight": "pytorch_model-00006-of-00007.bin",
295
+ "rwkv.blocks.22.ln2.bias": "pytorch_model-00006-of-00007.bin",
296
+ "rwkv.blocks.22.ln2.weight": "pytorch_model-00006-of-00007.bin",
297
+ "rwkv.blocks.23.attention.key.weight": "pytorch_model-00006-of-00007.bin",
298
+ "rwkv.blocks.23.attention.output.weight": "pytorch_model-00006-of-00007.bin",
299
+ "rwkv.blocks.23.attention.receptance.weight": "pytorch_model-00006-of-00007.bin",
300
+ "rwkv.blocks.23.attention.time_decay": "pytorch_model-00006-of-00007.bin",
301
+ "rwkv.blocks.23.attention.time_first": "pytorch_model-00006-of-00007.bin",
302
+ "rwkv.blocks.23.attention.time_mix_key": "pytorch_model-00006-of-00007.bin",
303
+ "rwkv.blocks.23.attention.time_mix_receptance": "pytorch_model-00006-of-00007.bin",
304
+ "rwkv.blocks.23.attention.time_mix_value": "pytorch_model-00006-of-00007.bin",
305
+ "rwkv.blocks.23.attention.value.weight": "pytorch_model-00006-of-00007.bin",
306
+ "rwkv.blocks.23.feed_forward.key.weight": "pytorch_model-00006-of-00007.bin",
307
+ "rwkv.blocks.23.feed_forward.receptance.weight": "pytorch_model-00006-of-00007.bin",
308
+ "rwkv.blocks.23.feed_forward.time_mix_key": "pytorch_model-00006-of-00007.bin",
309
+ "rwkv.blocks.23.feed_forward.time_mix_receptance": "pytorch_model-00006-of-00007.bin",
310
+ "rwkv.blocks.23.feed_forward.value.weight": "pytorch_model-00006-of-00007.bin",
311
+ "rwkv.blocks.23.ln1.bias": "pytorch_model-00006-of-00007.bin",
312
+ "rwkv.blocks.23.ln1.weight": "pytorch_model-00006-of-00007.bin",
313
+ "rwkv.blocks.23.ln2.bias": "pytorch_model-00006-of-00007.bin",
314
+ "rwkv.blocks.23.ln2.weight": "pytorch_model-00006-of-00007.bin",
315
+ "rwkv.blocks.3.attention.key.weight": "pytorch_model-00002-of-00007.bin",
316
+ "rwkv.blocks.3.attention.output.weight": "pytorch_model-00002-of-00007.bin",
317
+ "rwkv.blocks.3.attention.receptance.weight": "pytorch_model-00002-of-00007.bin",
318
+ "rwkv.blocks.3.attention.time_decay": "pytorch_model-00002-of-00007.bin",
319
+ "rwkv.blocks.3.attention.time_first": "pytorch_model-00002-of-00007.bin",
320
+ "rwkv.blocks.3.attention.time_mix_key": "pytorch_model-00002-of-00007.bin",
321
+ "rwkv.blocks.3.attention.time_mix_receptance": "pytorch_model-00002-of-00007.bin",
322
+ "rwkv.blocks.3.attention.time_mix_value": "pytorch_model-00002-of-00007.bin",
323
+ "rwkv.blocks.3.attention.value.weight": "pytorch_model-00002-of-00007.bin",
324
+ "rwkv.blocks.3.feed_forward.key.weight": "pytorch_model-00002-of-00007.bin",
325
+ "rwkv.blocks.3.feed_forward.receptance.weight": "pytorch_model-00002-of-00007.bin",
326
+ "rwkv.blocks.3.feed_forward.time_mix_key": "pytorch_model-00002-of-00007.bin",
327
+ "rwkv.blocks.3.feed_forward.time_mix_receptance": "pytorch_model-00002-of-00007.bin",
328
+ "rwkv.blocks.3.feed_forward.value.weight": "pytorch_model-00002-of-00007.bin",
329
+ "rwkv.blocks.3.ln1.bias": "pytorch_model-00002-of-00007.bin",
330
+ "rwkv.blocks.3.ln1.weight": "pytorch_model-00002-of-00007.bin",
331
+ "rwkv.blocks.3.ln2.bias": "pytorch_model-00002-of-00007.bin",
332
+ "rwkv.blocks.3.ln2.weight": "pytorch_model-00002-of-00007.bin",
333
+ "rwkv.blocks.4.attention.key.weight": "pytorch_model-00002-of-00007.bin",
334
+ "rwkv.blocks.4.attention.output.weight": "pytorch_model-00002-of-00007.bin",
335
+ "rwkv.blocks.4.attention.receptance.weight": "pytorch_model-00002-of-00007.bin",
336
+ "rwkv.blocks.4.attention.time_decay": "pytorch_model-00002-of-00007.bin",
337
+ "rwkv.blocks.4.attention.time_first": "pytorch_model-00002-of-00007.bin",
338
+ "rwkv.blocks.4.attention.time_mix_key": "pytorch_model-00002-of-00007.bin",
339
+ "rwkv.blocks.4.attention.time_mix_receptance": "pytorch_model-00002-of-00007.bin",
340
+ "rwkv.blocks.4.attention.time_mix_value": "pytorch_model-00002-of-00007.bin",
341
+ "rwkv.blocks.4.attention.value.weight": "pytorch_model-00002-of-00007.bin",
342
+ "rwkv.blocks.4.feed_forward.key.weight": "pytorch_model-00002-of-00007.bin",
343
+ "rwkv.blocks.4.feed_forward.receptance.weight": "pytorch_model-00002-of-00007.bin",
344
+ "rwkv.blocks.4.feed_forward.time_mix_key": "pytorch_model-00002-of-00007.bin",
345
+ "rwkv.blocks.4.feed_forward.time_mix_receptance": "pytorch_model-00002-of-00007.bin",
346
+ "rwkv.blocks.4.feed_forward.value.weight": "pytorch_model-00002-of-00007.bin",
347
+ "rwkv.blocks.4.ln1.bias": "pytorch_model-00002-of-00007.bin",
348
+ "rwkv.blocks.4.ln1.weight": "pytorch_model-00002-of-00007.bin",
349
+ "rwkv.blocks.4.ln2.bias": "pytorch_model-00002-of-00007.bin",
350
+ "rwkv.blocks.4.ln2.weight": "pytorch_model-00002-of-00007.bin",
351
+ "rwkv.blocks.5.attention.key.weight": "pytorch_model-00002-of-00007.bin",
352
+ "rwkv.blocks.5.attention.output.weight": "pytorch_model-00002-of-00007.bin",
353
+ "rwkv.blocks.5.attention.receptance.weight": "pytorch_model-00002-of-00007.bin",
354
+ "rwkv.blocks.5.attention.time_decay": "pytorch_model-00002-of-00007.bin",
355
+ "rwkv.blocks.5.attention.time_first": "pytorch_model-00002-of-00007.bin",
356
+ "rwkv.blocks.5.attention.time_mix_key": "pytorch_model-00002-of-00007.bin",
357
+ "rwkv.blocks.5.attention.time_mix_receptance": "pytorch_model-00002-of-00007.bin",
358
+ "rwkv.blocks.5.attention.time_mix_value": "pytorch_model-00002-of-00007.bin",
359
+ "rwkv.blocks.5.attention.value.weight": "pytorch_model-00002-of-00007.bin",
360
+ "rwkv.blocks.5.feed_forward.key.weight": "pytorch_model-00002-of-00007.bin",
361
+ "rwkv.blocks.5.feed_forward.receptance.weight": "pytorch_model-00002-of-00007.bin",
362
+ "rwkv.blocks.5.feed_forward.time_mix_key": "pytorch_model-00002-of-00007.bin",
363
+ "rwkv.blocks.5.feed_forward.time_mix_receptance": "pytorch_model-00002-of-00007.bin",
364
+ "rwkv.blocks.5.feed_forward.value.weight": "pytorch_model-00002-of-00007.bin",
365
+ "rwkv.blocks.5.ln1.bias": "pytorch_model-00002-of-00007.bin",
366
+ "rwkv.blocks.5.ln1.weight": "pytorch_model-00002-of-00007.bin",
367
+ "rwkv.blocks.5.ln2.bias": "pytorch_model-00002-of-00007.bin",
368
+ "rwkv.blocks.5.ln2.weight": "pytorch_model-00002-of-00007.bin",
369
+ "rwkv.blocks.6.attention.key.weight": "pytorch_model-00002-of-00007.bin",
370
+ "rwkv.blocks.6.attention.output.weight": "pytorch_model-00002-of-00007.bin",
371
+ "rwkv.blocks.6.attention.receptance.weight": "pytorch_model-00002-of-00007.bin",
372
+ "rwkv.blocks.6.attention.time_decay": "pytorch_model-00002-of-00007.bin",
373
+ "rwkv.blocks.6.attention.time_first": "pytorch_model-00002-of-00007.bin",
374
+ "rwkv.blocks.6.attention.time_mix_key": "pytorch_model-00002-of-00007.bin",
375
+ "rwkv.blocks.6.attention.time_mix_receptance": "pytorch_model-00002-of-00007.bin",
376
+ "rwkv.blocks.6.attention.time_mix_value": "pytorch_model-00002-of-00007.bin",
377
+ "rwkv.blocks.6.attention.value.weight": "pytorch_model-00002-of-00007.bin",
378
+ "rwkv.blocks.6.feed_forward.key.weight": "pytorch_model-00002-of-00007.bin",
379
+ "rwkv.blocks.6.feed_forward.receptance.weight": "pytorch_model-00002-of-00007.bin",
380
+ "rwkv.blocks.6.feed_forward.time_mix_key": "pytorch_model-00002-of-00007.bin",
381
+ "rwkv.blocks.6.feed_forward.time_mix_receptance": "pytorch_model-00002-of-00007.bin",
382
+ "rwkv.blocks.6.feed_forward.value.weight": "pytorch_model-00002-of-00007.bin",
383
+ "rwkv.blocks.6.ln1.bias": "pytorch_model-00002-of-00007.bin",
384
+ "rwkv.blocks.6.ln1.weight": "pytorch_model-00002-of-00007.bin",
385
+ "rwkv.blocks.6.ln2.bias": "pytorch_model-00002-of-00007.bin",
386
+ "rwkv.blocks.6.ln2.weight": "pytorch_model-00002-of-00007.bin",
387
+ "rwkv.blocks.7.attention.key.weight": "pytorch_model-00002-of-00007.bin",
388
+ "rwkv.blocks.7.attention.output.weight": "pytorch_model-00003-of-00007.bin",
389
+ "rwkv.blocks.7.attention.receptance.weight": "pytorch_model-00003-of-00007.bin",
390
+ "rwkv.blocks.7.attention.time_decay": "pytorch_model-00002-of-00007.bin",
391
+ "rwkv.blocks.7.attention.time_first": "pytorch_model-00002-of-00007.bin",
392
+ "rwkv.blocks.7.attention.time_mix_key": "pytorch_model-00002-of-00007.bin",
393
+ "rwkv.blocks.7.attention.time_mix_receptance": "pytorch_model-00002-of-00007.bin",
394
+ "rwkv.blocks.7.attention.time_mix_value": "pytorch_model-00002-of-00007.bin",
395
+ "rwkv.blocks.7.attention.value.weight": "pytorch_model-00002-of-00007.bin",
396
+ "rwkv.blocks.7.feed_forward.key.weight": "pytorch_model-00003-of-00007.bin",
397
+ "rwkv.blocks.7.feed_forward.receptance.weight": "pytorch_model-00003-of-00007.bin",
398
+ "rwkv.blocks.7.feed_forward.time_mix_key": "pytorch_model-00003-of-00007.bin",
399
+ "rwkv.blocks.7.feed_forward.time_mix_receptance": "pytorch_model-00003-of-00007.bin",
400
+ "rwkv.blocks.7.feed_forward.value.weight": "pytorch_model-00003-of-00007.bin",
401
+ "rwkv.blocks.7.ln1.bias": "pytorch_model-00002-of-00007.bin",
402
+ "rwkv.blocks.7.ln1.weight": "pytorch_model-00002-of-00007.bin",
403
+ "rwkv.blocks.7.ln2.bias": "pytorch_model-00002-of-00007.bin",
404
+ "rwkv.blocks.7.ln2.weight": "pytorch_model-00002-of-00007.bin",
405
+ "rwkv.blocks.8.attention.key.weight": "pytorch_model-00003-of-00007.bin",
406
+ "rwkv.blocks.8.attention.output.weight": "pytorch_model-00003-of-00007.bin",
407
+ "rwkv.blocks.8.attention.receptance.weight": "pytorch_model-00003-of-00007.bin",
408
+ "rwkv.blocks.8.attention.time_decay": "pytorch_model-00003-of-00007.bin",
409
+ "rwkv.blocks.8.attention.time_first": "pytorch_model-00003-of-00007.bin",
410
+ "rwkv.blocks.8.attention.time_mix_key": "pytorch_model-00003-of-00007.bin",
411
+ "rwkv.blocks.8.attention.time_mix_receptance": "pytorch_model-00003-of-00007.bin",
412
+ "rwkv.blocks.8.attention.time_mix_value": "pytorch_model-00003-of-00007.bin",
413
+ "rwkv.blocks.8.attention.value.weight": "pytorch_model-00003-of-00007.bin",
414
+ "rwkv.blocks.8.feed_forward.key.weight": "pytorch_model-00003-of-00007.bin",
415
+ "rwkv.blocks.8.feed_forward.receptance.weight": "pytorch_model-00003-of-00007.bin",
416
+ "rwkv.blocks.8.feed_forward.time_mix_key": "pytorch_model-00003-of-00007.bin",
417
+ "rwkv.blocks.8.feed_forward.time_mix_receptance": "pytorch_model-00003-of-00007.bin",
418
+ "rwkv.blocks.8.feed_forward.value.weight": "pytorch_model-00003-of-00007.bin",
419
+ "rwkv.blocks.8.ln1.bias": "pytorch_model-00003-of-00007.bin",
420
+ "rwkv.blocks.8.ln1.weight": "pytorch_model-00003-of-00007.bin",
421
+ "rwkv.blocks.8.ln2.bias": "pytorch_model-00003-of-00007.bin",
422
+ "rwkv.blocks.8.ln2.weight": "pytorch_model-00003-of-00007.bin",
423
+ "rwkv.blocks.9.attention.key.weight": "pytorch_model-00003-of-00007.bin",
424
+ "rwkv.blocks.9.attention.output.weight": "pytorch_model-00003-of-00007.bin",
425
+ "rwkv.blocks.9.attention.receptance.weight": "pytorch_model-00003-of-00007.bin",
426
+ "rwkv.blocks.9.attention.time_decay": "pytorch_model-00003-of-00007.bin",
427
+ "rwkv.blocks.9.attention.time_first": "pytorch_model-00003-of-00007.bin",
428
+ "rwkv.blocks.9.attention.time_mix_key": "pytorch_model-00003-of-00007.bin",
429
+ "rwkv.blocks.9.attention.time_mix_receptance": "pytorch_model-00003-of-00007.bin",
430
+ "rwkv.blocks.9.attention.time_mix_value": "pytorch_model-00003-of-00007.bin",
431
+ "rwkv.blocks.9.attention.value.weight": "pytorch_model-00003-of-00007.bin",
432
+ "rwkv.blocks.9.feed_forward.key.weight": "pytorch_model-00003-of-00007.bin",
433
+ "rwkv.blocks.9.feed_forward.receptance.weight": "pytorch_model-00003-of-00007.bin",
434
+ "rwkv.blocks.9.feed_forward.time_mix_key": "pytorch_model-00003-of-00007.bin",
435
+ "rwkv.blocks.9.feed_forward.time_mix_receptance": "pytorch_model-00003-of-00007.bin",
436
+ "rwkv.blocks.9.feed_forward.value.weight": "pytorch_model-00003-of-00007.bin",
437
+ "rwkv.blocks.9.ln1.bias": "pytorch_model-00003-of-00007.bin",
438
+ "rwkv.blocks.9.ln1.weight": "pytorch_model-00003-of-00007.bin",
439
+ "rwkv.blocks.9.ln2.bias": "pytorch_model-00003-of-00007.bin",
440
+ "rwkv.blocks.9.ln2.weight": "pytorch_model-00003-of-00007.bin",
441
+ "rwkv.embeddings.weight": "pytorch_model-00001-of-00007.bin",
442
+ "rwkv.ln_out.bias": "pytorch_model-00006-of-00007.bin",
443
+ "rwkv.ln_out.weight": "pytorch_model-00006-of-00007.bin"
444
  }
445
  }