Hugging Face's logo

RWKV
/
rwkv-raven-14b

Text Generation
Transformers
PyTorch
rwkv
Inference Endpoints
Model card Files Community
4
ybelkada commited on
Commit
307ac98
•
1 Parent(s): aa97689

Upload RwkvForCausalLM

Browse files
Files changed (33) hide show
  1. config.json +21 -0
  2. generation_config.json +6 -0
  3. pytorch_model-00001-of-00030.bin +3 -0
  4. pytorch_model-00002-of-00030.bin +3 -0
  5. pytorch_model-00003-of-00030.bin +3 -0
  6. pytorch_model-00004-of-00030.bin +3 -0
  7. pytorch_model-00005-of-00030.bin +3 -0
  8. pytorch_model-00006-of-00030.bin +3 -0
  9. pytorch_model-00007-of-00030.bin +3 -0
  10. pytorch_model-00008-of-00030.bin +3 -0
  11. pytorch_model-00009-of-00030.bin +3 -0
  12. pytorch_model-00010-of-00030.bin +3 -0
  13. pytorch_model-00011-of-00030.bin +3 -0
  14. pytorch_model-00012-of-00030.bin +3 -0
  15. pytorch_model-00013-of-00030.bin +3 -0
  16. pytorch_model-00014-of-00030.bin +3 -0
  17. pytorch_model-00015-of-00030.bin +3 -0
  18. pytorch_model-00016-of-00030.bin +3 -0
  19. pytorch_model-00017-of-00030.bin +3 -0
  20. pytorch_model-00018-of-00030.bin +3 -0
  21. pytorch_model-00019-of-00030.bin +3 -0
  22. pytorch_model-00020-of-00030.bin +3 -0
  23. pytorch_model-00021-of-00030.bin +3 -0
  24. pytorch_model-00022-of-00030.bin +3 -0
  25. pytorch_model-00023-of-00030.bin +3 -0
  26. pytorch_model-00024-of-00030.bin +3 -0
  27. pytorch_model-00025-of-00030.bin +3 -0
  28. pytorch_model-00026-of-00030.bin +3 -0
  29. pytorch_model-00027-of-00030.bin +3 -0
  30. pytorch_model-00028-of-00030.bin +3 -0
  31. pytorch_model-00029-of-00030.bin +3 -0
  32. pytorch_model-00030-of-00030.bin +3 -0
  33. pytorch_model.bin.index.json +733 -0
config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/home/younes/rwkv/rwkv-4-raven-14b",
3
+ "architectures": [
4
+ "RwkvForCausalLM"
5
+ ],
6
+ "attention_hidden_size": 5120,
7
+ "bos_token_id": 0,
8
+ "context_length": 1024,
9
+ "eos_token_id": 0,
10
+ "hidden_size": 5120,
11
+ "intermediate_size": 20480,
12
+ "layer_norm_epsilon": 1e-05,
13
+ "model_type": "rwkv",
14
+ "num_hidden_layers": 40,
15
+ "rescale_every": 6,
16
+ "tie_word_embeddings": false,
17
+ "torch_dtype": "float32",
18
+ "transformers_version": "4.29.0.dev0",
19
+ "use_cache": true,
20
+ "vocab_size": 50277
21
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "eos_token_id": 0,
5
+ "transformers_version": "4.29.0.dev0"
6
+ }
pytorch_model-00001-of-00030.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16ee6ae4452c45b5c0c7c5a371b204f438fa0d83e4affb338f97d95ef6599d3f
3
+ size 1973664375
pytorch_model-00002-of-00030.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75642b3af15d41b41cf8ae39cbd2d96f171b3aa033b57a04bc278f9dcb14d07b
3
+ size 1992713835
pytorch_model-00003-of-00030.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d84e0d4a5e8b709b60ca096c827f7ab00e4795f203eece803432d9a042e17a8
3
+ size 1992568429
pytorch_model-00004-of-00030.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dde53813fd6cb15d785ac5aaaec71608821aec616000360dae54353215eaa8ff
3
+ size 1992713835
pytorch_model-00005-of-00030.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a5515eca6ca290cc2c3db25f45c104f509cddb24427cd380bf9c8c1ee29c5bd
3
+ size 1677995629
pytorch_model-00006-of-00030.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be61ce18b5ffbf66dc42ce84f4fb15a3c9b28e60749a60ada5eede6050d0259f
3
+ size 1887668919
pytorch_model-00007-of-00030.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4ccd07980ff029f2782281418b345294e41b009845b40dda763dc89e249e4a2
3
+ size 1992713835
pytorch_model-00008-of-00030.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c4bd3e955aa9d876a71a8624263ea52743effdcea01754b7b8532813cf8bfad
3
+ size 1992568429
pytorch_model-00009-of-00030.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:536b0328bc9f2645c4053d70c55b0cca84a47e49b4b898a68007e912ec8ae79d
3
+ size 1992713899
pytorch_model-00010-of-00030.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b1b658e4a89eacc5581d88553373e538d7626a57996f98868e1179660a44706
3
+ size 1677995629
pytorch_model-00011-of-00030.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1102d5bdad2d49e070926257fd351e1e05ef91f27f8f73dfe2f4482273b9ad7
3
+ size 1887668919
pytorch_model-00012-of-00030.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:413966268bfa4b75ff24df2e425e6f77a51c60f831e8f4881ae91057c6ec450a
3
+ size 1992713899
pytorch_model-00013-of-00030.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6824812195c41a0d2a37e527805cef0c59e65af23911d515e347aefcc95a92fd
3
+ size 1992568429
pytorch_model-00014-of-00030.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b8cb9b1c817fb6e0247ee5221413f9b4de41b6683ee6a60e26822e2b4b2f3b7
3
+ size 1992713899
pytorch_model-00015-of-00030.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:04864570c2bd1b9a1e653c18274c423202dd32b864c8b786a15937a035d44ad3
3
+ size 1677995629
pytorch_model-00016-of-00030.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b6551e6ba64e4942479f346880a49bbfdefed56ac7824a81228f19ce969ff27
3
+ size 1887668919
pytorch_model-00017-of-00030.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49c23e7e631810c2019c908803fe8cf6f8eed62c5352daad73bb1995fc75d435
3
+ size 1992713899
pytorch_model-00018-of-00030.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb094738a562e7f0a3e4fad0d08c3684d8f72c854d29a0afa3be9f036cb5af54
3
+ size 1992568429
pytorch_model-00019-of-00030.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a631fe1e029ea2d0cf05f2f15c1d259bf491667867363217d791d9c6fadbb8a
3
+ size 1992713899
pytorch_model-00020-of-00030.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:891eace99791a3bbccc56146d24f0c13dcb7f4bf35be053afd816a198064be13
3
+ size 1677995629
pytorch_model-00021-of-00030.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5da986f2c7aa737c009eacc981d67eb51a03338b4360ba2c9a6a527e8e210e40
3
+ size 1887668919
pytorch_model-00022-of-00030.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d3b1ed00d10f3e1440d454b40f86d9e6cd09b7f53d44e6d3135dbc102bbeed9
3
+ size 1992713899
pytorch_model-00023-of-00030.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9dd60666601f698647667ec49eda85fdac67c62bf256a180a0cc842812dbf2ff
3
+ size 1992568429
pytorch_model-00024-of-00030.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9519db38b2c5214e00dd294003e6f95ee30e45e0d50e634583077aa771a28248
3
+ size 1992713899
pytorch_model-00025-of-00030.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66af6566e1d465c5ae848401c772d695f624265bd33813fe7b446333c95212a1
3
+ size 1677995629
pytorch_model-00026-of-00030.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:19abb124702f7fd4e2be8522fea10c2a5cf85abdd65f7055d9fd259236cf816d
3
+ size 1887668919
pytorch_model-00027-of-00030.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fca55b351a5104c00c7b8bc0de7dc4a1e52066dcd4ac87fdf47927ce017a5298
3
+ size 1992713899
pytorch_model-00028-of-00030.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed7a190be6f5949c5044566486f6e95d96b64f1bca5f784d7b3999c739415d94
3
+ size 1992568429
pytorch_model-00029-of-00030.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:015439a3ffaca212a6a769135490a94610b3ed5ce29123c9ff0b0b057a6e54bf
3
+ size 1887710427
pytorch_model-00030-of-00030.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:10fb5a59237991911ffe28b8cd50b172418f895ceab8b19f79d84a4c54c220aa
3
+ size 1029673898
pytorch_model.bin.index.json ADDED
@@ -0,0 +1,733 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 56594391040
4
+ },
5
+ "weight_map": {
6
+ "head.weight": "pytorch_model-00030-of-00030.bin",
7
+ "rwkv.blocks.0.attention.key.weight": "pytorch_model-00001-of-00030.bin",
8
+ "rwkv.blocks.0.attention.output.weight": "pytorch_model-00001-of-00030.bin",
9
+ "rwkv.blocks.0.attention.receptance.weight": "pytorch_model-00001-of-00030.bin",
10
+ "rwkv.blocks.0.attention.time_decay": "pytorch_model-00001-of-00030.bin",
11
+ "rwkv.blocks.0.attention.time_first": "pytorch_model-00001-of-00030.bin",
12
+ "rwkv.blocks.0.attention.time_mix_key": "pytorch_model-00001-of-00030.bin",
13
+ "rwkv.blocks.0.attention.time_mix_receptance": "pytorch_model-00001-of-00030.bin",
14
+ "rwkv.blocks.0.attention.time_mix_value": "pytorch_model-00001-of-00030.bin",
15
+ "rwkv.blocks.0.attention.value.weight": "pytorch_model-00001-of-00030.bin",
16
+ "rwkv.blocks.0.feed_forward.key.weight": "pytorch_model-00001-of-00030.bin",
17
+ "rwkv.blocks.0.feed_forward.receptance.weight": "pytorch_model-00001-of-00030.bin",
18
+ "rwkv.blocks.0.feed_forward.time_mix_key": "pytorch_model-00001-of-00030.bin",
19
+ "rwkv.blocks.0.feed_forward.time_mix_receptance": "pytorch_model-00001-of-00030.bin",
20
+ "rwkv.blocks.0.feed_forward.value.weight": "pytorch_model-00002-of-00030.bin",
21
+ "rwkv.blocks.0.ln1.bias": "pytorch_model-00001-of-00030.bin",
22
+ "rwkv.blocks.0.ln1.weight": "pytorch_model-00001-of-00030.bin",
23
+ "rwkv.blocks.0.ln2.bias": "pytorch_model-00001-of-00030.bin",
24
+ "rwkv.blocks.0.ln2.weight": "pytorch_model-00001-of-00030.bin",
25
+ "rwkv.blocks.0.pre_ln.bias": "pytorch_model-00001-of-00030.bin",
26
+ "rwkv.blocks.0.pre_ln.weight": "pytorch_model-00001-of-00030.bin",
27
+ "rwkv.blocks.1.attention.key.weight": "pytorch_model-00002-of-00030.bin",
28
+ "rwkv.blocks.1.attention.output.weight": "pytorch_model-00002-of-00030.bin",
29
+ "rwkv.blocks.1.attention.receptance.weight": "pytorch_model-00002-of-00030.bin",
30
+ "rwkv.blocks.1.attention.time_decay": "pytorch_model-00002-of-00030.bin",
31
+ "rwkv.blocks.1.attention.time_first": "pytorch_model-00002-of-00030.bin",
32
+ "rwkv.blocks.1.attention.time_mix_key": "pytorch_model-00002-of-00030.bin",
33
+ "rwkv.blocks.1.attention.time_mix_receptance": "pytorch_model-00002-of-00030.bin",
34
+ "rwkv.blocks.1.attention.time_mix_value": "pytorch_model-00002-of-00030.bin",
35
+ "rwkv.blocks.1.attention.value.weight": "pytorch_model-00002-of-00030.bin",
36
+ "rwkv.blocks.1.feed_forward.key.weight": "pytorch_model-00002-of-00030.bin",
37
+ "rwkv.blocks.1.feed_forward.receptance.weight": "pytorch_model-00002-of-00030.bin",
38
+ "rwkv.blocks.1.feed_forward.time_mix_key": "pytorch_model-00002-of-00030.bin",
39
+ "rwkv.blocks.1.feed_forward.time_mix_receptance": "pytorch_model-00002-of-00030.bin",
40
+ "rwkv.blocks.1.feed_forward.value.weight": "pytorch_model-00002-of-00030.bin",
41
+ "rwkv.blocks.1.ln1.bias": "pytorch_model-00002-of-00030.bin",
42
+ "rwkv.blocks.1.ln1.weight": "pytorch_model-00002-of-00030.bin",
43
+ "rwkv.blocks.1.ln2.bias": "pytorch_model-00002-of-00030.bin",
44
+ "rwkv.blocks.1.ln2.weight": "pytorch_model-00002-of-00030.bin",
45
+ "rwkv.blocks.10.attention.key.weight": "pytorch_model-00008-of-00030.bin",
46
+ "rwkv.blocks.10.attention.output.weight": "pytorch_model-00008-of-00030.bin",
47
+ "rwkv.blocks.10.attention.receptance.weight": "pytorch_model-00008-of-00030.bin",
48
+ "rwkv.blocks.10.attention.time_decay": "pytorch_model-00008-of-00030.bin",
49
+ "rwkv.blocks.10.attention.time_first": "pytorch_model-00008-of-00030.bin",
50
+ "rwkv.blocks.10.attention.time_mix_key": "pytorch_model-00008-of-00030.bin",
51
+ "rwkv.blocks.10.attention.time_mix_receptance": "pytorch_model-00008-of-00030.bin",
52
+ "rwkv.blocks.10.attention.time_mix_value": "pytorch_model-00008-of-00030.bin",
53
+ "rwkv.blocks.10.attention.value.weight": "pytorch_model-00008-of-00030.bin",
54
+ "rwkv.blocks.10.feed_forward.key.weight": "pytorch_model-00008-of-00030.bin",
55
+ "rwkv.blocks.10.feed_forward.receptance.weight": "pytorch_model-00009-of-00030.bin",
56
+ "rwkv.blocks.10.feed_forward.time_mix_key": "pytorch_model-00008-of-00030.bin",
57
+ "rwkv.blocks.10.feed_forward.time_mix_receptance": "pytorch_model-00008-of-00030.bin",
58
+ "rwkv.blocks.10.feed_forward.value.weight": "pytorch_model-00009-of-00030.bin",
59
+ "rwkv.blocks.10.ln1.bias": "pytorch_model-00008-of-00030.bin",
60
+ "rwkv.blocks.10.ln1.weight": "pytorch_model-00008-of-00030.bin",
61
+ "rwkv.blocks.10.ln2.bias": "pytorch_model-00008-of-00030.bin",
62
+ "rwkv.blocks.10.ln2.weight": "pytorch_model-00008-of-00030.bin",
63
+ "rwkv.blocks.11.attention.key.weight": "pytorch_model-00009-of-00030.bin",
64
+ "rwkv.blocks.11.attention.output.weight": "pytorch_model-00009-of-00030.bin",
65
+ "rwkv.blocks.11.attention.receptance.weight": "pytorch_model-00009-of-00030.bin",
66
+ "rwkv.blocks.11.attention.time_decay": "pytorch_model-00009-of-00030.bin",
67
+ "rwkv.blocks.11.attention.time_first": "pytorch_model-00009-of-00030.bin",
68
+ "rwkv.blocks.11.attention.time_mix_key": "pytorch_model-00009-of-00030.bin",
69
+ "rwkv.blocks.11.attention.time_mix_receptance": "pytorch_model-00009-of-00030.bin",
70
+ "rwkv.blocks.11.attention.time_mix_value": "pytorch_model-00009-of-00030.bin",
71
+ "rwkv.blocks.11.attention.value.weight": "pytorch_model-00009-of-00030.bin",
72
+ "rwkv.blocks.11.feed_forward.key.weight": "pytorch_model-00009-of-00030.bin",
73
+ "rwkv.blocks.11.feed_forward.receptance.weight": "pytorch_model-00009-of-00030.bin",
74
+ "rwkv.blocks.11.feed_forward.time_mix_key": "pytorch_model-00009-of-00030.bin",
75
+ "rwkv.blocks.11.feed_forward.time_mix_receptance": "pytorch_model-00009-of-00030.bin",
76
+ "rwkv.blocks.11.feed_forward.value.weight": "pytorch_model-00009-of-00030.bin",
77
+ "rwkv.blocks.11.ln1.bias": "pytorch_model-00009-of-00030.bin",
78
+ "rwkv.blocks.11.ln1.weight": "pytorch_model-00009-of-00030.bin",
79
+ "rwkv.blocks.11.ln2.bias": "pytorch_model-00009-of-00030.bin",
80
+ "rwkv.blocks.11.ln2.weight": "pytorch_model-00009-of-00030.bin",
81
+ "rwkv.blocks.12.attention.key.weight": "pytorch_model-00009-of-00030.bin",
82
+ "rwkv.blocks.12.attention.output.weight": "pytorch_model-00010-of-00030.bin",
83
+ "rwkv.blocks.12.attention.receptance.weight": "pytorch_model-00010-of-00030.bin",
84
+ "rwkv.blocks.12.attention.time_decay": "pytorch_model-00009-of-00030.bin",
85
+ "rwkv.blocks.12.attention.time_first": "pytorch_model-00009-of-00030.bin",
86
+ "rwkv.blocks.12.attention.time_mix_key": "pytorch_model-00009-of-00030.bin",
87
+ "rwkv.blocks.12.attention.time_mix_receptance": "pytorch_model-00009-of-00030.bin",
88
+ "rwkv.blocks.12.attention.time_mix_value": "pytorch_model-00009-of-00030.bin",
89
+ "rwkv.blocks.12.attention.value.weight": "pytorch_model-00010-of-00030.bin",
90
+ "rwkv.blocks.12.feed_forward.key.weight": "pytorch_model-00010-of-00030.bin",
91
+ "rwkv.blocks.12.feed_forward.receptance.weight": "pytorch_model-00010-of-00030.bin",
92
+ "rwkv.blocks.12.feed_forward.time_mix_key": "pytorch_model-00010-of-00030.bin",
93
+ "rwkv.blocks.12.feed_forward.time_mix_receptance": "pytorch_model-00010-of-00030.bin",
94
+ "rwkv.blocks.12.feed_forward.value.weight": "pytorch_model-00010-of-00030.bin",
95
+ "rwkv.blocks.12.ln1.bias": "pytorch_model-00009-of-00030.bin",
96
+ "rwkv.blocks.12.ln1.weight": "pytorch_model-00009-of-00030.bin",
97
+ "rwkv.blocks.12.ln2.bias": "pytorch_model-00009-of-00030.bin",
98
+ "rwkv.blocks.12.ln2.weight": "pytorch_model-00009-of-00030.bin",
99
+ "rwkv.blocks.13.attention.key.weight": "pytorch_model-00010-of-00030.bin",
100
+ "rwkv.blocks.13.attention.output.weight": "pytorch_model-00010-of-00030.bin",
101
+ "rwkv.blocks.13.attention.receptance.weight": "pytorch_model-00010-of-00030.bin",
102
+ "rwkv.blocks.13.attention.time_decay": "pytorch_model-00010-of-00030.bin",
103
+ "rwkv.blocks.13.attention.time_first": "pytorch_model-00010-of-00030.bin",
104
+ "rwkv.blocks.13.attention.time_mix_key": "pytorch_model-00010-of-00030.bin",
105
+ "rwkv.blocks.13.attention.time_mix_receptance": "pytorch_model-00010-of-00030.bin",
106
+ "rwkv.blocks.13.attention.time_mix_value": "pytorch_model-00010-of-00030.bin",
107
+ "rwkv.blocks.13.attention.value.weight": "pytorch_model-00010-of-00030.bin",
108
+ "rwkv.blocks.13.feed_forward.key.weight": "pytorch_model-00011-of-00030.bin",
109
+ "rwkv.blocks.13.feed_forward.receptance.weight": "pytorch_model-00011-of-00030.bin",
110
+ "rwkv.blocks.13.feed_forward.time_mix_key": "pytorch_model-00010-of-00030.bin",
111
+ "rwkv.blocks.13.feed_forward.time_mix_receptance": "pytorch_model-00010-of-00030.bin",
112
+ "rwkv.blocks.13.feed_forward.value.weight": "pytorch_model-00011-of-00030.bin",
113
+ "rwkv.blocks.13.ln1.bias": "pytorch_model-00010-of-00030.bin",
114
+ "rwkv.blocks.13.ln1.weight": "pytorch_model-00010-of-00030.bin",
115
+ "rwkv.blocks.13.ln2.bias": "pytorch_model-00010-of-00030.bin",
116
+ "rwkv.blocks.13.ln2.weight": "pytorch_model-00010-of-00030.bin",
117
+ "rwkv.blocks.14.attention.key.weight": "pytorch_model-00011-of-00030.bin",
118
+ "rwkv.blocks.14.attention.output.weight": "pytorch_model-00011-of-00030.bin",
119
+ "rwkv.blocks.14.attention.receptance.weight": "pytorch_model-00011-of-00030.bin",
120
+ "rwkv.blocks.14.attention.time_decay": "pytorch_model-00011-of-00030.bin",
121
+ "rwkv.blocks.14.attention.time_first": "pytorch_model-00011-of-00030.bin",
122
+ "rwkv.blocks.14.attention.time_mix_key": "pytorch_model-00011-of-00030.bin",
123
+ "rwkv.blocks.14.attention.time_mix_receptance": "pytorch_model-00011-of-00030.bin",
124
+ "rwkv.blocks.14.attention.time_mix_value": "pytorch_model-00011-of-00030.bin",
125
+ "rwkv.blocks.14.attention.value.weight": "pytorch_model-00011-of-00030.bin",
126
+ "rwkv.blocks.14.feed_forward.key.weight": "pytorch_model-00011-of-00030.bin",
127
+ "rwkv.blocks.14.feed_forward.receptance.weight": "pytorch_model-00011-of-00030.bin",
128
+ "rwkv.blocks.14.feed_forward.time_mix_key": "pytorch_model-00011-of-00030.bin",
129
+ "rwkv.blocks.14.feed_forward.time_mix_receptance": "pytorch_model-00011-of-00030.bin",
130
+ "rwkv.blocks.14.feed_forward.value.weight": "pytorch_model-00012-of-00030.bin",
131
+ "rwkv.blocks.14.ln1.bias": "pytorch_model-00011-of-00030.bin",
132
+ "rwkv.blocks.14.ln1.weight": "pytorch_model-00011-of-00030.bin",
133
+ "rwkv.blocks.14.ln2.bias": "pytorch_model-00011-of-00030.bin",
134
+ "rwkv.blocks.14.ln2.weight": "pytorch_model-00011-of-00030.bin",
135
+ "rwkv.blocks.15.attention.key.weight": "pytorch_model-00012-of-00030.bin",
136
+ "rwkv.blocks.15.attention.output.weight": "pytorch_model-00012-of-00030.bin",
137
+ "rwkv.blocks.15.attention.receptance.weight": "pytorch_model-00012-of-00030.bin",
138
+ "rwkv.blocks.15.attention.time_decay": "pytorch_model-00012-of-00030.bin",
139
+ "rwkv.blocks.15.attention.time_first": "pytorch_model-00012-of-00030.bin",
140
+ "rwkv.blocks.15.attention.time_mix_key": "pytorch_model-00012-of-00030.bin",
141
+ "rwkv.blocks.15.attention.time_mix_receptance": "pytorch_model-00012-of-00030.bin",
142
+ "rwkv.blocks.15.attention.time_mix_value": "pytorch_model-00012-of-00030.bin",
143
+ "rwkv.blocks.15.attention.value.weight": "pytorch_model-00012-of-00030.bin",
144
+ "rwkv.blocks.15.feed_forward.key.weight": "pytorch_model-00012-of-00030.bin",
145
+ "rwkv.blocks.15.feed_forward.receptance.weight": "pytorch_model-00012-of-00030.bin",
146
+ "rwkv.blocks.15.feed_forward.time_mix_key": "pytorch_model-00012-of-00030.bin",
147
+ "rwkv.blocks.15.feed_forward.time_mix_receptance": "pytorch_model-00012-of-00030.bin",
148
+ "rwkv.blocks.15.feed_forward.value.weight": "pytorch_model-00012-of-00030.bin",
149
+ "rwkv.blocks.15.ln1.bias": "pytorch_model-00012-of-00030.bin",
150
+ "rwkv.blocks.15.ln1.weight": "pytorch_model-00012-of-00030.bin",
151
+ "rwkv.blocks.15.ln2.bias": "pytorch_model-00012-of-00030.bin",
152
+ "rwkv.blocks.15.ln2.weight": "pytorch_model-00012-of-00030.bin",
153
+ "rwkv.blocks.16.attention.key.weight": "pytorch_model-00012-of-00030.bin",
154
+ "rwkv.blocks.16.attention.output.weight": "pytorch_model-00013-of-00030.bin",
155
+ "rwkv.blocks.16.attention.receptance.weight": "pytorch_model-00013-of-00030.bin",
156
+ "rwkv.blocks.16.attention.time_decay": "pytorch_model-00012-of-00030.bin",
157
+ "rwkv.blocks.16.attention.time_first": "pytorch_model-00012-of-00030.bin",
158
+ "rwkv.blocks.16.attention.time_mix_key": "pytorch_model-00012-of-00030.bin",
159
+ "rwkv.blocks.16.attention.time_mix_receptance": "pytorch_model-00012-of-00030.bin",
160
+ "rwkv.blocks.16.attention.time_mix_value": "pytorch_model-00012-of-00030.bin",
161
+ "rwkv.blocks.16.attention.value.weight": "pytorch_model-00012-of-00030.bin",
162
+ "rwkv.blocks.16.feed_forward.key.weight": "pytorch_model-00013-of-00030.bin",
163
+ "rwkv.blocks.16.feed_forward.receptance.weight": "pytorch_model-00013-of-00030.bin",
164
+ "rwkv.blocks.16.feed_forward.time_mix_key": "pytorch_model-00013-of-00030.bin",
165
+ "rwkv.blocks.16.feed_forward.time_mix_receptance": "pytorch_model-00013-of-00030.bin",
166
+ "rwkv.blocks.16.feed_forward.value.weight": "pytorch_model-00013-of-00030.bin",
167
+ "rwkv.blocks.16.ln1.bias": "pytorch_model-00012-of-00030.bin",
168
+ "rwkv.blocks.16.ln1.weight": "pytorch_model-00012-of-00030.bin",
169
+ "rwkv.blocks.16.ln2.bias": "pytorch_model-00012-of-00030.bin",
170
+ "rwkv.blocks.16.ln2.weight": "pytorch_model-00012-of-00030.bin",
171
+ "rwkv.blocks.17.attention.key.weight": "pytorch_model-00013-of-00030.bin",
172
+ "rwkv.blocks.17.attention.output.weight": "pytorch_model-00013-of-00030.bin",
173
+ "rwkv.blocks.17.attention.receptance.weight": "pytorch_model-00013-of-00030.bin",
174
+ "rwkv.blocks.17.attention.time_decay": "pytorch_model-00013-of-00030.bin",
175
+ "rwkv.blocks.17.attention.time_first": "pytorch_model-00013-of-00030.bin",
176
+ "rwkv.blocks.17.attention.time_mix_key": "pytorch_model-00013-of-00030.bin",
177
+ "rwkv.blocks.17.attention.time_mix_receptance": "pytorch_model-00013-of-00030.bin",
178
+ "rwkv.blocks.17.attention.time_mix_value": "pytorch_model-00013-of-00030.bin",
179
+ "rwkv.blocks.17.attention.value.weight": "pytorch_model-00013-of-00030.bin",
180
+ "rwkv.blocks.17.feed_forward.key.weight": "pytorch_model-00013-of-00030.bin",
181
+ "rwkv.blocks.17.feed_forward.receptance.weight": "pytorch_model-00014-of-00030.bin",
182
+ "rwkv.blocks.17.feed_forward.time_mix_key": "pytorch_model-00013-of-00030.bin",
183
+ "rwkv.blocks.17.feed_forward.time_mix_receptance": "pytorch_model-00013-of-00030.bin",
184
+ "rwkv.blocks.17.feed_forward.value.weight": "pytorch_model-00014-of-00030.bin",
185
+ "rwkv.blocks.17.ln1.bias": "pytorch_model-00013-of-00030.bin",
186
+ "rwkv.blocks.17.ln1.weight": "pytorch_model-00013-of-00030.bin",
187
+ "rwkv.blocks.17.ln2.bias": "pytorch_model-00013-of-00030.bin",
188
+ "rwkv.blocks.17.ln2.weight": "pytorch_model-00013-of-00030.bin",
189
+ "rwkv.blocks.18.attention.key.weight": "pytorch_model-00014-of-00030.bin",
190
+ "rwkv.blocks.18.attention.output.weight": "pytorch_model-00014-of-00030.bin",
191
+ "rwkv.blocks.18.attention.receptance.weight": "pytorch_model-00014-of-00030.bin",
192
+ "rwkv.blocks.18.attention.time_decay": "pytorch_model-00014-of-00030.bin",
193
+ "rwkv.blocks.18.attention.time_first": "pytorch_model-00014-of-00030.bin",
194
+ "rwkv.blocks.18.attention.time_mix_key": "pytorch_model-00014-of-00030.bin",
195
+ "rwkv.blocks.18.attention.time_mix_receptance": "pytorch_model-00014-of-00030.bin",
196
+ "rwkv.blocks.18.attention.time_mix_value": "pytorch_model-00014-of-00030.bin",
197
+ "rwkv.blocks.18.attention.value.weight": "pytorch_model-00014-of-00030.bin",
198
+ "rwkv.blocks.18.feed_forward.key.weight": "pytorch_model-00014-of-00030.bin",
199
+ "rwkv.blocks.18.feed_forward.receptance.weight": "pytorch_model-00014-of-00030.bin",
200
+ "rwkv.blocks.18.feed_forward.time_mix_key": "pytorch_model-00014-of-00030.bin",
201
+ "rwkv.blocks.18.feed_forward.time_mix_receptance": "pytorch_model-00014-of-00030.bin",
202
+ "rwkv.blocks.18.feed_forward.value.weight": "pytorch_model-00014-of-00030.bin",
203
+ "rwkv.blocks.18.ln1.bias": "pytorch_model-00014-of-00030.bin",
204
+ "rwkv.blocks.18.ln1.weight": "pytorch_model-00014-of-00030.bin",
205
+ "rwkv.blocks.18.ln2.bias": "pytorch_model-00014-of-00030.bin",
206
+ "rwkv.blocks.18.ln2.weight": "pytorch_model-00014-of-00030.bin",
207
+ "rwkv.blocks.19.attention.key.weight": "pytorch_model-00014-of-00030.bin",
208
+ "rwkv.blocks.19.attention.output.weight": "pytorch_model-00015-of-00030.bin",
209
+ "rwkv.blocks.19.attention.receptance.weight": "pytorch_model-00015-of-00030.bin",
210
+ "rwkv.blocks.19.attention.time_decay": "pytorch_model-00014-of-00030.bin",
211
+ "rwkv.blocks.19.attention.time_first": "pytorch_model-00014-of-00030.bin",
212
+ "rwkv.blocks.19.attention.time_mix_key": "pytorch_model-00014-of-00030.bin",
213
+ "rwkv.blocks.19.attention.time_mix_receptance": "pytorch_model-00014-of-00030.bin",
214
+ "rwkv.blocks.19.attention.time_mix_value": "pytorch_model-00014-of-00030.bin",
215
+ "rwkv.blocks.19.attention.value.weight": "pytorch_model-00015-of-00030.bin",
216
+ "rwkv.blocks.19.feed_forward.key.weight": "pytorch_model-00015-of-00030.bin",
217
+ "rwkv.blocks.19.feed_forward.receptance.weight": "pytorch_model-00015-of-00030.bin",
218
+ "rwkv.blocks.19.feed_forward.time_mix_key": "pytorch_model-00015-of-00030.bin",
219
+ "rwkv.blocks.19.feed_forward.time_mix_receptance": "pytorch_model-00015-of-00030.bin",
220
+ "rwkv.blocks.19.feed_forward.value.weight": "pytorch_model-00015-of-00030.bin",
221
+ "rwkv.blocks.19.ln1.bias": "pytorch_model-00014-of-00030.bin",
222
+ "rwkv.blocks.19.ln1.weight": "pytorch_model-00014-of-00030.bin",
223
+ "rwkv.blocks.19.ln2.bias": "pytorch_model-00014-of-00030.bin",
224
+ "rwkv.blocks.19.ln2.weight": "pytorch_model-00014-of-00030.bin",
225
+ "rwkv.blocks.2.attention.key.weight": "pytorch_model-00002-of-00030.bin",
226
+ "rwkv.blocks.2.attention.output.weight": "pytorch_model-00003-of-00030.bin",
227
+ "rwkv.blocks.2.attention.receptance.weight": "pytorch_model-00003-of-00030.bin",
228
+ "rwkv.blocks.2.attention.time_decay": "pytorch_model-00002-of-00030.bin",
229
+ "rwkv.blocks.2.attention.time_first": "pytorch_model-00002-of-00030.bin",
230
+ "rwkv.blocks.2.attention.time_mix_key": "pytorch_model-00002-of-00030.bin",
231
+ "rwkv.blocks.2.attention.time_mix_receptance": "pytorch_model-00002-of-00030.bin",
232
+ "rwkv.blocks.2.attention.time_mix_value": "pytorch_model-00002-of-00030.bin",
233
+ "rwkv.blocks.2.attention.value.weight": "pytorch_model-00002-of-00030.bin",
234
+ "rwkv.blocks.2.feed_forward.key.weight": "pytorch_model-00003-of-00030.bin",
235
+ "rwkv.blocks.2.feed_forward.receptance.weight": "pytorch_model-00003-of-00030.bin",
236
+ "rwkv.blocks.2.feed_forward.time_mix_key": "pytorch_model-00003-of-00030.bin",
237
+ "rwkv.blocks.2.feed_forward.time_mix_receptance": "pytorch_model-00003-of-00030.bin",
238
+ "rwkv.blocks.2.feed_forward.value.weight": "pytorch_model-00003-of-00030.bin",
239
+ "rwkv.blocks.2.ln1.bias": "pytorch_model-00002-of-00030.bin",
240
+ "rwkv.blocks.2.ln1.weight": "pytorch_model-00002-of-00030.bin",
241
+ "rwkv.blocks.2.ln2.bias": "pytorch_model-00002-of-00030.bin",
242
+ "rwkv.blocks.2.ln2.weight": "pytorch_model-00002-of-00030.bin",
243
+ "rwkv.blocks.20.attention.key.weight": "pytorch_model-00015-of-00030.bin",
244
+ "rwkv.blocks.20.attention.output.weight": "pytorch_model-00015-of-00030.bin",
245
+ "rwkv.blocks.20.attention.receptance.weight": "pytorch_model-00015-of-00030.bin",
246
+ "rwkv.blocks.20.attention.time_decay": "pytorch_model-00015-of-00030.bin",
247
+ "rwkv.blocks.20.attention.time_first": "pytorch_model-00015-of-00030.bin",
248
+ "rwkv.blocks.20.attention.time_mix_key": "pytorch_model-00015-of-00030.bin",
249
+ "rwkv.blocks.20.attention.time_mix_receptance": "pytorch_model-00015-of-00030.bin",
250
+ "rwkv.blocks.20.attention.time_mix_value": "pytorch_model-00015-of-00030.bin",
251
+ "rwkv.blocks.20.attention.value.weight": "pytorch_model-00015-of-00030.bin",
252
+ "rwkv.blocks.20.feed_forward.key.weight": "pytorch_model-00016-of-00030.bin",
253
+ "rwkv.blocks.20.feed_forward.receptance.weight": "pytorch_model-00016-of-00030.bin",
254
+ "rwkv.blocks.20.feed_forward.time_mix_key": "pytorch_model-00015-of-00030.bin",
255
+ "rwkv.blocks.20.feed_forward.time_mix_receptance": "pytorch_model-00015-of-00030.bin",
256
+ "rwkv.blocks.20.feed_forward.value.weight": "pytorch_model-00016-of-00030.bin",
257
+ "rwkv.blocks.20.ln1.bias": "pytorch_model-00015-of-00030.bin",
258
+ "rwkv.blocks.20.ln1.weight": "pytorch_model-00015-of-00030.bin",
259
+ "rwkv.blocks.20.ln2.bias": "pytorch_model-00015-of-00030.bin",
260
+ "rwkv.blocks.20.ln2.weight": "pytorch_model-00015-of-00030.bin",
261
+ "rwkv.blocks.21.attention.key.weight": "pytorch_model-00016-of-00030.bin",
262
+ "rwkv.blocks.21.attention.output.weight": "pytorch_model-00016-of-00030.bin",
263
+ "rwkv.blocks.21.attention.receptance.weight": "pytorch_model-00016-of-00030.bin",
264
+ "rwkv.blocks.21.attention.time_decay": "pytorch_model-00016-of-00030.bin",
265
+ "rwkv.blocks.21.attention.time_first": "pytorch_model-00016-of-00030.bin",
266
+ "rwkv.blocks.21.attention.time_mix_key": "pytorch_model-00016-of-00030.bin",
267
+ "rwkv.blocks.21.attention.time_mix_receptance": "pytorch_model-00016-of-00030.bin",
268
+ "rwkv.blocks.21.attention.time_mix_value": "pytorch_model-00016-of-00030.bin",
269
+ "rwkv.blocks.21.attention.value.weight": "pytorch_model-00016-of-00030.bin",
270
+ "rwkv.blocks.21.feed_forward.key.weight": "pytorch_model-00016-of-00030.bin",
271
+ "rwkv.blocks.21.feed_forward.receptance.weight": "pytorch_model-00016-of-00030.bin",
272
+ "rwkv.blocks.21.feed_forward.time_mix_key": "pytorch_model-00016-of-00030.bin",
273
+ "rwkv.blocks.21.feed_forward.time_mix_receptance": "pytorch_model-00016-of-00030.bin",
274
+ "rwkv.blocks.21.feed_forward.value.weight": "pytorch_model-00017-of-00030.bin",
275
+ "rwkv.blocks.21.ln1.bias": "pytorch_model-00016-of-00030.bin",
276
+ "rwkv.blocks.21.ln1.weight": "pytorch_model-00016-of-00030.bin",
277
+ "rwkv.blocks.21.ln2.bias": "pytorch_model-00016-of-00030.bin",
278
+ "rwkv.blocks.21.ln2.weight": "pytorch_model-00016-of-00030.bin",
279
+ "rwkv.blocks.22.attention.key.weight": "pytorch_model-00017-of-00030.bin",
280
+ "rwkv.blocks.22.attention.output.weight": "pytorch_model-00017-of-00030.bin",
281
+ "rwkv.blocks.22.attention.receptance.weight": "pytorch_model-00017-of-00030.bin",
282
+ "rwkv.blocks.22.attention.time_decay": "pytorch_model-00017-of-00030.bin",
283
+ "rwkv.blocks.22.attention.time_first": "pytorch_model-00017-of-00030.bin",
284
+ "rwkv.blocks.22.attention.time_mix_key": "pytorch_model-00017-of-00030.bin",
285
+ "rwkv.blocks.22.attention.time_mix_receptance": "pytorch_model-00017-of-00030.bin",
286
+ "rwkv.blocks.22.attention.time_mix_value": "pytorch_model-00017-of-00030.bin",
287
+ "rwkv.blocks.22.attention.value.weight": "pytorch_model-00017-of-00030.bin",
288
+ "rwkv.blocks.22.feed_forward.key.weight": "pytorch_model-00017-of-00030.bin",
289
+ "rwkv.blocks.22.feed_forward.receptance.weight": "pytorch_model-00017-of-00030.bin",
290
+ "rwkv.blocks.22.feed_forward.time_mix_key": "pytorch_model-00017-of-00030.bin",
291
+ "rwkv.blocks.22.feed_forward.time_mix_receptance": "pytorch_model-00017-of-00030.bin",
292
+ "rwkv.blocks.22.feed_forward.value.weight": "pytorch_model-00017-of-00030.bin",
293
+ "rwkv.blocks.22.ln1.bias": "pytorch_model-00017-of-00030.bin",
294
+ "rwkv.blocks.22.ln1.weight": "pytorch_model-00017-of-00030.bin",
295
+ "rwkv.blocks.22.ln2.bias": "pytorch_model-00017-of-00030.bin",
296
+ "rwkv.blocks.22.ln2.weight": "pytorch_model-00017-of-00030.bin",
297
+ "rwkv.blocks.23.attention.key.weight": "pytorch_model-00017-of-00030.bin",
298
+ "rwkv.blocks.23.attention.output.weight": "pytorch_model-00018-of-00030.bin",
299
+ "rwkv.blocks.23.attention.receptance.weight": "pytorch_model-00018-of-00030.bin",
300
+ "rwkv.blocks.23.attention.time_decay": "pytorch_model-00017-of-00030.bin",
301
+ "rwkv.blocks.23.attention.time_first": "pytorch_model-00017-of-00030.bin",
302
+ "rwkv.blocks.23.attention.time_mix_key": "pytorch_model-00017-of-00030.bin",
303
+ "rwkv.blocks.23.attention.time_mix_receptance": "pytorch_model-00017-of-00030.bin",
304
+ "rwkv.blocks.23.attention.time_mix_value": "pytorch_model-00017-of-00030.bin",
305
+ "rwkv.blocks.23.attention.value.weight": "pytorch_model-00017-of-00030.bin",
306
+ "rwkv.blocks.23.feed_forward.key.weight": "pytorch_model-00018-of-00030.bin",
307
+ "rwkv.blocks.23.feed_forward.receptance.weight": "pytorch_model-00018-of-00030.bin",
308
+ "rwkv.blocks.23.feed_forward.time_mix_key": "pytorch_model-00018-of-00030.bin",
309
+ "rwkv.blocks.23.feed_forward.time_mix_receptance": "pytorch_model-00018-of-00030.bin",
310
+ "rwkv.blocks.23.feed_forward.value.weight": "pytorch_model-00018-of-00030.bin",
311
+ "rwkv.blocks.23.ln1.bias": "pytorch_model-00017-of-00030.bin",
312
+ "rwkv.blocks.23.ln1.weight": "pytorch_model-00017-of-00030.bin",
313
+ "rwkv.blocks.23.ln2.bias": "pytorch_model-00017-of-00030.bin",
314
+ "rwkv.blocks.23.ln2.weight": "pytorch_model-00017-of-00030.bin",
315
+ "rwkv.blocks.24.attention.key.weight": "pytorch_model-00018-of-00030.bin",
316
+ "rwkv.blocks.24.attention.output.weight": "pytorch_model-00018-of-00030.bin",
317
+ "rwkv.blocks.24.attention.receptance.weight": "pytorch_model-00018-of-00030.bin",
318
+ "rwkv.blocks.24.attention.time_decay": "pytorch_model-00018-of-00030.bin",
319
+ "rwkv.blocks.24.attention.time_first": "pytorch_model-00018-of-00030.bin",
320
+ "rwkv.blocks.24.attention.time_mix_key": "pytorch_model-00018-of-00030.bin",
321
+ "rwkv.blocks.24.attention.time_mix_receptance": "pytorch_model-00018-of-00030.bin",
322
+ "rwkv.blocks.24.attention.time_mix_value": "pytorch_model-00018-of-00030.bin",
323
+ "rwkv.blocks.24.attention.value.weight": "pytorch_model-00018-of-00030.bin",
324
+ "rwkv.blocks.24.feed_forward.key.weight": "pytorch_model-00018-of-00030.bin",
325
+ "rwkv.blocks.24.feed_forward.receptance.weight": "pytorch_model-00019-of-00030.bin",
326
+ "rwkv.blocks.24.feed_forward.time_mix_key": "pytorch_model-00018-of-00030.bin",
327
+ "rwkv.blocks.24.feed_forward.time_mix_receptance": "pytorch_model-00018-of-00030.bin",
328
+ "rwkv.blocks.24.feed_forward.value.weight": "pytorch_model-00019-of-00030.bin",
329
+ "rwkv.blocks.24.ln1.bias": "pytorch_model-00018-of-00030.bin",
330
+ "rwkv.blocks.24.ln1.weight": "pytorch_model-00018-of-00030.bin",
331
+ "rwkv.blocks.24.ln2.bias": "pytorch_model-00018-of-00030.bin",
332
+ "rwkv.blocks.24.ln2.weight": "pytorch_model-00018-of-00030.bin",
333
+ "rwkv.blocks.25.attention.key.weight": "pytorch_model-00019-of-00030.bin",
334
+ "rwkv.blocks.25.attention.output.weight": "pytorch_model-00019-of-00030.bin",
335
+ "rwkv.blocks.25.attention.receptance.weight": "pytorch_model-00019-of-00030.bin",
336
+ "rwkv.blocks.25.attention.time_decay": "pytorch_model-00019-of-00030.bin",
337
+ "rwkv.blocks.25.attention.time_first": "pytorch_model-00019-of-00030.bin",
338
+ "rwkv.blocks.25.attention.time_mix_key": "pytorch_model-00019-of-00030.bin",
339
+ "rwkv.blocks.25.attention.time_mix_receptance": "pytorch_model-00019-of-00030.bin",
340
+ "rwkv.blocks.25.attention.time_mix_value": "pytorch_model-00019-of-00030.bin",
341
+ "rwkv.blocks.25.attention.value.weight": "pytorch_model-00019-of-00030.bin",
342
+ "rwkv.blocks.25.feed_forward.key.weight": "pytorch_model-00019-of-00030.bin",
343
+ "rwkv.blocks.25.feed_forward.receptance.weight": "pytorch_model-00019-of-00030.bin",
344
+ "rwkv.blocks.25.feed_forward.time_mix_key": "pytorch_model-00019-of-00030.bin",
345
+ "rwkv.blocks.25.feed_forward.time_mix_receptance": "pytorch_model-00019-of-00030.bin",
346
+ "rwkv.blocks.25.feed_forward.value.weight": "pytorch_model-00019-of-00030.bin",
347
+ "rwkv.blocks.25.ln1.bias": "pytorch_model-00019-of-00030.bin",
348
+ "rwkv.blocks.25.ln1.weight": "pytorch_model-00019-of-00030.bin",
349
+ "rwkv.blocks.25.ln2.bias": "pytorch_model-00019-of-00030.bin",
350
+ "rwkv.blocks.25.ln2.weight": "pytorch_model-00019-of-00030.bin",
351
+ "rwkv.blocks.26.attention.key.weight": "pytorch_model-00019-of-00030.bin",
352
+ "rwkv.blocks.26.attention.output.weight": "pytorch_model-00020-of-00030.bin",
353
+ "rwkv.blocks.26.attention.receptance.weight": "pytorch_model-00020-of-00030.bin",
354
+ "rwkv.blocks.26.attention.time_decay": "pytorch_model-00019-of-00030.bin",
355
+ "rwkv.blocks.26.attention.time_first": "pytorch_model-00019-of-00030.bin",
356
+ "rwkv.blocks.26.attention.time_mix_key": "pytorch_model-00019-of-00030.bin",
357
+ "rwkv.blocks.26.attention.time_mix_receptance": "pytorch_model-00019-of-00030.bin",
358
+ "rwkv.blocks.26.attention.time_mix_value": "pytorch_model-00019-of-00030.bin",
359
+ "rwkv.blocks.26.attention.value.weight": "pytorch_model-00020-of-00030.bin",
360
+ "rwkv.blocks.26.feed_forward.key.weight": "pytorch_model-00020-of-00030.bin",
361
+ "rwkv.blocks.26.feed_forward.receptance.weight": "pytorch_model-00020-of-00030.bin",
362
+ "rwkv.blocks.26.feed_forward.time_mix_key": "pytorch_model-00020-of-00030.bin",
363
+ "rwkv.blocks.26.feed_forward.time_mix_receptance": "pytorch_model-00020-of-00030.bin",
364
+ "rwkv.blocks.26.feed_forward.value.weight": "pytorch_model-00020-of-00030.bin",
365
+ "rwkv.blocks.26.ln1.bias": "pytorch_model-00019-of-00030.bin",
366
+ "rwkv.blocks.26.ln1.weight": "pytorch_model-00019-of-00030.bin",
367
+ "rwkv.blocks.26.ln2.bias": "pytorch_model-00019-of-00030.bin",
368
+ "rwkv.blocks.26.ln2.weight": "pytorch_model-00019-of-00030.bin",
369
+ "rwkv.blocks.27.attention.key.weight": "pytorch_model-00020-of-00030.bin",
370
+ "rwkv.blocks.27.attention.output.weight": "pytorch_model-00020-of-00030.bin",
371
+ "rwkv.blocks.27.attention.receptance.weight": "pytorch_model-00020-of-00030.bin",
372
+ "rwkv.blocks.27.attention.time_decay": "pytorch_model-00020-of-00030.bin",
373
+ "rwkv.blocks.27.attention.time_first": "pytorch_model-00020-of-00030.bin",
374
+ "rwkv.blocks.27.attention.time_mix_key": "pytorch_model-00020-of-00030.bin",
375
+ "rwkv.blocks.27.attention.time_mix_receptance": "pytorch_model-00020-of-00030.bin",
376
+ "rwkv.blocks.27.attention.time_mix_value": "pytorch_model-00020-of-00030.bin",
377
+ "rwkv.blocks.27.attention.value.weight": "pytorch_model-00020-of-00030.bin",
378
+ "rwkv.blocks.27.feed_forward.key.weight": "pytorch_model-00021-of-00030.bin",
379
+ "rwkv.blocks.27.feed_forward.receptance.weight": "pytorch_model-00021-of-00030.bin",
380
+ "rwkv.blocks.27.feed_forward.time_mix_key": "pytorch_model-00020-of-00030.bin",
381
+ "rwkv.blocks.27.feed_forward.time_mix_receptance": "pytorch_model-00020-of-00030.bin",
382
+ "rwkv.blocks.27.feed_forward.value.weight": "pytorch_model-00021-of-00030.bin",
383
+ "rwkv.blocks.27.ln1.bias": "pytorch_model-00020-of-00030.bin",
384
+ "rwkv.blocks.27.ln1.weight": "pytorch_model-00020-of-00030.bin",
385
+ "rwkv.blocks.27.ln2.bias": "pytorch_model-00020-of-00030.bin",
386
+ "rwkv.blocks.27.ln2.weight": "pytorch_model-00020-of-00030.bin",
387
+ "rwkv.blocks.28.attention.key.weight": "pytorch_model-00021-of-00030.bin",
388
+ "rwkv.blocks.28.attention.output.weight": "pytorch_model-00021-of-00030.bin",
389
+ "rwkv.blocks.28.attention.receptance.weight": "pytorch_model-00021-of-00030.bin",
390
+ "rwkv.blocks.28.attention.time_decay": "pytorch_model-00021-of-00030.bin",
391
+ "rwkv.blocks.28.attention.time_first": "pytorch_model-00021-of-00030.bin",
392
+ "rwkv.blocks.28.attention.time_mix_key": "pytorch_model-00021-of-00030.bin",
393
+ "rwkv.blocks.28.attention.time_mix_receptance": "pytorch_model-00021-of-00030.bin",
394
+ "rwkv.blocks.28.attention.time_mix_value": "pytorch_model-00021-of-00030.bin",
395
+ "rwkv.blocks.28.attention.value.weight": "pytorch_model-00021-of-00030.bin",
396
+ "rwkv.blocks.28.feed_forward.key.weight": "pytorch_model-00021-of-00030.bin",
397
+ "rwkv.blocks.28.feed_forward.receptance.weight": "pytorch_model-00021-of-00030.bin",
398
+ "rwkv.blocks.28.feed_forward.time_mix_key": "pytorch_model-00021-of-00030.bin",
399
+ "rwkv.blocks.28.feed_forward.time_mix_receptance": "pytorch_model-00021-of-00030.bin",
400
+ "rwkv.blocks.28.feed_forward.value.weight": "pytorch_model-00022-of-00030.bin",
401
+ "rwkv.blocks.28.ln1.bias": "pytorch_model-00021-of-00030.bin",
402
+ "rwkv.blocks.28.ln1.weight": "pytorch_model-00021-of-00030.bin",
403
+ "rwkv.blocks.28.ln2.bias": "pytorch_model-00021-of-00030.bin",
404
+ "rwkv.blocks.28.ln2.weight": "pytorch_model-00021-of-00030.bin",
405
+ "rwkv.blocks.29.attention.key.weight": "pytorch_model-00022-of-00030.bin",
406
+ "rwkv.blocks.29.attention.output.weight": "pytorch_model-00022-of-00030.bin",
407
+ "rwkv.blocks.29.attention.receptance.weight": "pytorch_model-00022-of-00030.bin",
408
+ "rwkv.blocks.29.attention.time_decay": "pytorch_model-00022-of-00030.bin",
409
+ "rwkv.blocks.29.attention.time_first": "pytorch_model-00022-of-00030.bin",
410
+ "rwkv.blocks.29.attention.time_mix_key": "pytorch_model-00022-of-00030.bin",
411
+ "rwkv.blocks.29.attention.time_mix_receptance": "pytorch_model-00022-of-00030.bin",
412
+ "rwkv.blocks.29.attention.time_mix_value": "pytorch_model-00022-of-00030.bin",
413
+ "rwkv.blocks.29.attention.value.weight": "pytorch_model-00022-of-00030.bin",
414
+ "rwkv.blocks.29.feed_forward.key.weight": "pytorch_model-00022-of-00030.bin",
415
+ "rwkv.blocks.29.feed_forward.receptance.weight": "pytorch_model-00022-of-00030.bin",
416
+ "rwkv.blocks.29.feed_forward.time_mix_key": "pytorch_model-00022-of-00030.bin",
417
+ "rwkv.blocks.29.feed_forward.time_mix_receptance": "pytorch_model-00022-of-00030.bin",
418
+ "rwkv.blocks.29.feed_forward.value.weight": "pytorch_model-00022-of-00030.bin",
419
+ "rwkv.blocks.29.ln1.bias": "pytorch_model-00022-of-00030.bin",
420
+ "rwkv.blocks.29.ln1.weight": "pytorch_model-00022-of-00030.bin",
421
+ "rwkv.blocks.29.ln2.bias": "pytorch_model-00022-of-00030.bin",
422
+ "rwkv.blocks.29.ln2.weight": "pytorch_model-00022-of-00030.bin",
423
+ "rwkv.blocks.3.attention.key.weight": "pytorch_model-00003-of-00030.bin",
424
+ "rwkv.blocks.3.attention.output.weight": "pytorch_model-00003-of-00030.bin",
425
+ "rwkv.blocks.3.attention.receptance.weight": "pytorch_model-00003-of-00030.bin",
426
+ "rwkv.blocks.3.attention.time_decay": "pytorch_model-00003-of-00030.bin",
427
+ "rwkv.blocks.3.attention.time_first": "pytorch_model-00003-of-00030.bin",
428
+ "rwkv.blocks.3.attention.time_mix_key": "pytorch_model-00003-of-00030.bin",
429
+ "rwkv.blocks.3.attention.time_mix_receptance": "pytorch_model-00003-of-00030.bin",
430
+ "rwkv.blocks.3.attention.time_mix_value": "pytorch_model-00003-of-00030.bin",
431
+ "rwkv.blocks.3.attention.value.weight": "pytorch_model-00003-of-00030.bin",
432
+ "rwkv.blocks.3.feed_forward.key.weight": "pytorch_model-00003-of-00030.bin",
433
+ "rwkv.blocks.3.feed_forward.receptance.weight": "pytorch_model-00004-of-00030.bin",
434
+ "rwkv.blocks.3.feed_forward.time_mix_key": "pytorch_model-00003-of-00030.bin",
435
+ "rwkv.blocks.3.feed_forward.time_mix_receptance": "pytorch_model-00003-of-00030.bin",
436
+ "rwkv.blocks.3.feed_forward.value.weight": "pytorch_model-00004-of-00030.bin",
437
+ "rwkv.blocks.3.ln1.bias": "pytorch_model-00003-of-00030.bin",
438
+ "rwkv.blocks.3.ln1.weight": "pytorch_model-00003-of-00030.bin",
439
+ "rwkv.blocks.3.ln2.bias": "pytorch_model-00003-of-00030.bin",
440
+ "rwkv.blocks.3.ln2.weight": "pytorch_model-00003-of-00030.bin",
441
+ "rwkv.blocks.30.attention.key.weight": "pytorch_model-00022-of-00030.bin",
442
+ "rwkv.blocks.30.attention.output.weight": "pytorch_model-00023-of-00030.bin",
443
+ "rwkv.blocks.30.attention.receptance.weight": "pytorch_model-00023-of-00030.bin",
444
+ "rwkv.blocks.30.attention.time_decay": "pytorch_model-00022-of-00030.bin",
445
+ "rwkv.blocks.30.attention.time_first": "pytorch_model-00022-of-00030.bin",
446
+ "rwkv.blocks.30.attention.time_mix_key": "pytorch_model-00022-of-00030.bin",
447
+ "rwkv.blocks.30.attention.time_mix_receptance": "pytorch_model-00022-of-00030.bin",
448
+ "rwkv.blocks.30.attention.time_mix_value": "pytorch_model-00022-of-00030.bin",
449
+ "rwkv.blocks.30.attention.value.weight": "pytorch_model-00022-of-00030.bin",
450
+ "rwkv.blocks.30.feed_forward.key.weight": "pytorch_model-00023-of-00030.bin",
451
+ "rwkv.blocks.30.feed_forward.receptance.weight": "pytorch_model-00023-of-00030.bin",
452
+ "rwkv.blocks.30.feed_forward.time_mix_key": "pytorch_model-00023-of-00030.bin",
453
+ "rwkv.blocks.30.feed_forward.time_mix_receptance": "pytorch_model-00023-of-00030.bin",
454
+ "rwkv.blocks.30.feed_forward.value.weight": "pytorch_model-00023-of-00030.bin",
455
+ "rwkv.blocks.30.ln1.bias": "pytorch_model-00022-of-00030.bin",
456
+ "rwkv.blocks.30.ln1.weight": "pytorch_model-00022-of-00030.bin",
457
+ "rwkv.blocks.30.ln2.bias": "pytorch_model-00022-of-00030.bin",
458
+ "rwkv.blocks.30.ln2.weight": "pytorch_model-00022-of-00030.bin",
459
+ "rwkv.blocks.31.attention.key.weight": "pytorch_model-00023-of-00030.bin",
460
+ "rwkv.blocks.31.attention.output.weight": "pytorch_model-00023-of-00030.bin",
461
+ "rwkv.blocks.31.attention.receptance.weight": "pytorch_model-00023-of-00030.bin",
462
+ "rwkv.blocks.31.attention.time_decay": "pytorch_model-00023-of-00030.bin",
463
+ "rwkv.blocks.31.attention.time_first": "pytorch_model-00023-of-00030.bin",
464
+ "rwkv.blocks.31.attention.time_mix_key": "pytorch_model-00023-of-00030.bin",
465
+ "rwkv.blocks.31.attention.time_mix_receptance": "pytorch_model-00023-of-00030.bin",
466
+ "rwkv.blocks.31.attention.time_mix_value": "pytorch_model-00023-of-00030.bin",
467
+ "rwkv.blocks.31.attention.value.weight": "pytorch_model-00023-of-00030.bin",
468
+ "rwkv.blocks.31.feed_forward.key.weight": "pytorch_model-00023-of-00030.bin",
469
+ "rwkv.blocks.31.feed_forward.receptance.weight": "pytorch_model-00024-of-00030.bin",
470
+ "rwkv.blocks.31.feed_forward.time_mix_key": "pytorch_model-00023-of-00030.bin",
471
+ "rwkv.blocks.31.feed_forward.time_mix_receptance": "pytorch_model-00023-of-00030.bin",
472
+ "rwkv.blocks.31.feed_forward.value.weight": "pytorch_model-00024-of-00030.bin",
473
+ "rwkv.blocks.31.ln1.bias": "pytorch_model-00023-of-00030.bin",
474
+ "rwkv.blocks.31.ln1.weight": "pytorch_model-00023-of-00030.bin",
475
+ "rwkv.blocks.31.ln2.bias": "pytorch_model-00023-of-00030.bin",
476
+ "rwkv.blocks.31.ln2.weight": "pytorch_model-00023-of-00030.bin",
477
+ "rwkv.blocks.32.attention.key.weight": "pytorch_model-00024-of-00030.bin",
478
+ "rwkv.blocks.32.attention.output.weight": "pytorch_model-00024-of-00030.bin",
479
+ "rwkv.blocks.32.attention.receptance.weight": "pytorch_model-00024-of-00030.bin",
480
+ "rwkv.blocks.32.attention.time_decay": "pytorch_model-00024-of-00030.bin",
481
+ "rwkv.blocks.32.attention.time_first": "pytorch_model-00024-of-00030.bin",
482
+ "rwkv.blocks.32.attention.time_mix_key": "pytorch_model-00024-of-00030.bin",
483
+ "rwkv.blocks.32.attention.time_mix_receptance": "pytorch_model-00024-of-00030.bin",
484
+ "rwkv.blocks.32.attention.time_mix_value": "pytorch_model-00024-of-00030.bin",
485
+ "rwkv.blocks.32.attention.value.weight": "pytorch_model-00024-of-00030.bin",
486
+ "rwkv.blocks.32.feed_forward.key.weight": "pytorch_model-00024-of-00030.bin",
487
+ "rwkv.blocks.32.feed_forward.receptance.weight": "pytorch_model-00024-of-00030.bin",
488
+ "rwkv.blocks.32.feed_forward.time_mix_key": "pytorch_model-00024-of-00030.bin",
489
+ "rwkv.blocks.32.feed_forward.time_mix_receptance": "pytorch_model-00024-of-00030.bin",
490
+ "rwkv.blocks.32.feed_forward.value.weight": "pytorch_model-00024-of-00030.bin",
491
+ "rwkv.blocks.32.ln1.bias": "pytorch_model-00024-of-00030.bin",
492
+ "rwkv.blocks.32.ln1.weight": "pytorch_model-00024-of-00030.bin",
493
+ "rwkv.blocks.32.ln2.bias": "pytorch_model-00024-of-00030.bin",
494
+ "rwkv.blocks.32.ln2.weight": "pytorch_model-00024-of-00030.bin",
495
+ "rwkv.blocks.33.attention.key.weight": "pytorch_model-00024-of-00030.bin",
496
+ "rwkv.blocks.33.attention.output.weight": "pytorch_model-00025-of-00030.bin",
497
+ "rwkv.blocks.33.attention.receptance.weight": "pytorch_model-00025-of-00030.bin",
498
+ "rwkv.blocks.33.attention.time_decay": "pytorch_model-00024-of-00030.bin",
499
+ "rwkv.blocks.33.attention.time_first": "pytorch_model-00024-of-00030.bin",
500
+ "rwkv.blocks.33.attention.time_mix_key": "pytorch_model-00024-of-00030.bin",
501
+ "rwkv.blocks.33.attention.time_mix_receptance": "pytorch_model-00024-of-00030.bin",
502
+ "rwkv.blocks.33.attention.time_mix_value": "pytorch_model-00024-of-00030.bin",
503
+ "rwkv.blocks.33.attention.value.weight": "pytorch_model-00025-of-00030.bin",
504
+ "rwkv.blocks.33.feed_forward.key.weight": "pytorch_model-00025-of-00030.bin",
505
+ "rwkv.blocks.33.feed_forward.receptance.weight": "pytorch_model-00025-of-00030.bin",
506
+ "rwkv.blocks.33.feed_forward.time_mix_key": "pytorch_model-00025-of-00030.bin",
507
+ "rwkv.blocks.33.feed_forward.time_mix_receptance": "pytorch_model-00025-of-00030.bin",
508
+ "rwkv.blocks.33.feed_forward.value.weight": "pytorch_model-00025-of-00030.bin",
509
+ "rwkv.blocks.33.ln1.bias": "pytorch_model-00024-of-00030.bin",
510
+ "rwkv.blocks.33.ln1.weight": "pytorch_model-00024-of-00030.bin",
511
+ "rwkv.blocks.33.ln2.bias": "pytorch_model-00024-of-00030.bin",
512
+ "rwkv.blocks.33.ln2.weight": "pytorch_model-00024-of-00030.bin",
513
+ "rwkv.blocks.34.attention.key.weight": "pytorch_model-00025-of-00030.bin",
514
+ "rwkv.blocks.34.attention.output.weight": "pytorch_model-00025-of-00030.bin",
515
+ "rwkv.blocks.34.attention.receptance.weight": "pytorch_model-00025-of-00030.bin",
516
+ "rwkv.blocks.34.attention.time_decay": "pytorch_model-00025-of-00030.bin",
517
+ "rwkv.blocks.34.attention.time_first": "pytorch_model-00025-of-00030.bin",
518
+ "rwkv.blocks.34.attention.time_mix_key": "pytorch_model-00025-of-00030.bin",
519
+ "rwkv.blocks.34.attention.time_mix_receptance": "pytorch_model-00025-of-00030.bin",
520
+ "rwkv.blocks.34.attention.time_mix_value": "pytorch_model-00025-of-00030.bin",
521
+ "rwkv.blocks.34.attention.value.weight": "pytorch_model-00025-of-00030.bin",
522
+ "rwkv.blocks.34.feed_forward.key.weight": "pytorch_model-00026-of-00030.bin",
523
+ "rwkv.blocks.34.feed_forward.receptance.weight": "pytorch_model-00026-of-00030.bin",
524
+ "rwkv.blocks.34.feed_forward.time_mix_key": "pytorch_model-00025-of-00030.bin",
525
+ "rwkv.blocks.34.feed_forward.time_mix_receptance": "pytorch_model-00025-of-00030.bin",
526
+ "rwkv.blocks.34.feed_forward.value.weight": "pytorch_model-00026-of-00030.bin",
527
+ "rwkv.blocks.34.ln1.bias": "pytorch_model-00025-of-00030.bin",
528
+ "rwkv.blocks.34.ln1.weight": "pytorch_model-00025-of-00030.bin",
529
+ "rwkv.blocks.34.ln2.bias": "pytorch_model-00025-of-00030.bin",
530
+ "rwkv.blocks.34.ln2.weight": "pytorch_model-00025-of-00030.bin",
531
+ "rwkv.blocks.35.attention.key.weight": "pytorch_model-00026-of-00030.bin",
532
+ "rwkv.blocks.35.attention.output.weight": "pytorch_model-00026-of-00030.bin",
533
+ "rwkv.blocks.35.attention.receptance.weight": "pytorch_model-00026-of-00030.bin",
534
+ "rwkv.blocks.35.attention.time_decay": "pytorch_model-00026-of-00030.bin",
535
+ "rwkv.blocks.35.attention.time_first": "pytorch_model-00026-of-00030.bin",
536
+ "rwkv.blocks.35.attention.time_mix_key": "pytorch_model-00026-of-00030.bin",
537
+ "rwkv.blocks.35.attention.time_mix_receptance": "pytorch_model-00026-of-00030.bin",
538
+ "rwkv.blocks.35.attention.time_mix_value": "pytorch_model-00026-of-00030.bin",
539
+ "rwkv.blocks.35.attention.value.weight": "pytorch_model-00026-of-00030.bin",
540
+ "rwkv.blocks.35.feed_forward.key.weight": "pytorch_model-00026-of-00030.bin",
541
+ "rwkv.blocks.35.feed_forward.receptance.weight": "pytorch_model-00026-of-00030.bin",
542
+ "rwkv.blocks.35.feed_forward.time_mix_key": "pytorch_model-00026-of-00030.bin",
543
+ "rwkv.blocks.35.feed_forward.time_mix_receptance": "pytorch_model-00026-of-00030.bin",
544
+ "rwkv.blocks.35.feed_forward.value.weight": "pytorch_model-00027-of-00030.bin",
545
+ "rwkv.blocks.35.ln1.bias": "pytorch_model-00026-of-00030.bin",
546
+ "rwkv.blocks.35.ln1.weight": "pytorch_model-00026-of-00030.bin",
547
+ "rwkv.blocks.35.ln2.bias": "pytorch_model-00026-of-00030.bin",
548
+ "rwkv.blocks.35.ln2.weight": "pytorch_model-00026-of-00030.bin",
549
+ "rwkv.blocks.36.attention.key.weight": "pytorch_model-00027-of-00030.bin",
550
+ "rwkv.blocks.36.attention.output.weight": "pytorch_model-00027-of-00030.bin",
551
+ "rwkv.blocks.36.attention.receptance.weight": "pytorch_model-00027-of-00030.bin",
552
+ "rwkv.blocks.36.attention.time_decay": "pytorch_model-00027-of-00030.bin",
553
+ "rwkv.blocks.36.attention.time_first": "pytorch_model-00027-of-00030.bin",
554
+ "rwkv.blocks.36.attention.time_mix_key": "pytorch_model-00027-of-00030.bin",
555
+ "rwkv.blocks.36.attention.time_mix_receptance": "pytorch_model-00027-of-00030.bin",
556
+ "rwkv.blocks.36.attention.time_mix_value": "pytorch_model-00027-of-00030.bin",
557
+ "rwkv.blocks.36.attention.value.weight": "pytorch_model-00027-of-00030.bin",
558
+ "rwkv.blocks.36.feed_forward.key.weight": "pytorch_model-00027-of-00030.bin",
559
+ "rwkv.blocks.36.feed_forward.receptance.weight": "pytorch_model-00027-of-00030.bin",
560
+ "rwkv.blocks.36.feed_forward.time_mix_key": "pytorch_model-00027-of-00030.bin",
561
+ "rwkv.blocks.36.feed_forward.time_mix_receptance": "pytorch_model-00027-of-00030.bin",
562
+ "rwkv.blocks.36.feed_forward.value.weight": "pytorch_model-00027-of-00030.bin",
563
+ "rwkv.blocks.36.ln1.bias": "pytorch_model-00027-of-00030.bin",
564
+ "rwkv.blocks.36.ln1.weight": "pytorch_model-00027-of-00030.bin",
565
+ "rwkv.blocks.36.ln2.bias": "pytorch_model-00027-of-00030.bin",
566
+ "rwkv.blocks.36.ln2.weight": "pytorch_model-00027-of-00030.bin",
567
+ "rwkv.blocks.37.attention.key.weight": "pytorch_model-00027-of-00030.bin",
568
+ "rwkv.blocks.37.attention.output.weight": "pytorch_model-00028-of-00030.bin",
569
+ "rwkv.blocks.37.attention.receptance.weight": "pytorch_model-00028-of-00030.bin",
570
+ "rwkv.blocks.37.attention.time_decay": "pytorch_model-00027-of-00030.bin",
571
+ "rwkv.blocks.37.attention.time_first": "pytorch_model-00027-of-00030.bin",
572
+ "rwkv.blocks.37.attention.time_mix_key": "pytorch_model-00027-of-00030.bin",
573
+ "rwkv.blocks.37.attention.time_mix_receptance": "pytorch_model-00027-of-00030.bin",
574
+ "rwkv.blocks.37.attention.time_mix_value": "pytorch_model-00027-of-00030.bin",
575
+ "rwkv.blocks.37.attention.value.weight": "pytorch_model-00027-of-00030.bin",
576
+ "rwkv.blocks.37.feed_forward.key.weight": "pytorch_model-00028-of-00030.bin",
577
+ "rwkv.blocks.37.feed_forward.receptance.weight": "pytorch_model-00028-of-00030.bin",
578
+ "rwkv.blocks.37.feed_forward.time_mix_key": "pytorch_model-00028-of-00030.bin",
579
+ "rwkv.blocks.37.feed_forward.time_mix_receptance": "pytorch_model-00028-of-00030.bin",
580
+ "rwkv.blocks.37.feed_forward.value.weight": "pytorch_model-00028-of-00030.bin",
581
+ "rwkv.blocks.37.ln1.bias": "pytorch_model-00027-of-00030.bin",
582
+ "rwkv.blocks.37.ln1.weight": "pytorch_model-00027-of-00030.bin",
583
+ "rwkv.blocks.37.ln2.bias": "pytorch_model-00027-of-00030.bin",
584
+ "rwkv.blocks.37.ln2.weight": "pytorch_model-00027-of-00030.bin",
585
+ "rwkv.blocks.38.attention.key.weight": "pytorch_model-00028-of-00030.bin",
586
+ "rwkv.blocks.38.attention.output.weight": "pytorch_model-00028-of-00030.bin",
587
+ "rwkv.blocks.38.attention.receptance.weight": "pytorch_model-00028-of-00030.bin",
588
+ "rwkv.blocks.38.attention.time_decay": "pytorch_model-00028-of-00030.bin",
589
+ "rwkv.blocks.38.attention.time_first": "pytorch_model-00028-of-00030.bin",
590
+ "rwkv.blocks.38.attention.time_mix_key": "pytorch_model-00028-of-00030.bin",
591
+ "rwkv.blocks.38.attention.time_mix_receptance": "pytorch_model-00028-of-00030.bin",
592
+ "rwkv.blocks.38.attention.time_mix_value": "pytorch_model-00028-of-00030.bin",
593
+ "rwkv.blocks.38.attention.value.weight": "pytorch_model-00028-of-00030.bin",
594
+ "rwkv.blocks.38.feed_forward.key.weight": "pytorch_model-00028-of-00030.bin",
595
+ "rwkv.blocks.38.feed_forward.receptance.weight": "pytorch_model-00029-of-00030.bin",
596
+ "rwkv.blocks.38.feed_forward.time_mix_key": "pytorch_model-00028-of-00030.bin",
597
+ "rwkv.blocks.38.feed_forward.time_mix_receptance": "pytorch_model-00028-of-00030.bin",
598
+ "rwkv.blocks.38.feed_forward.value.weight": "pytorch_model-00029-of-00030.bin",
599
+ "rwkv.blocks.38.ln1.bias": "pytorch_model-00028-of-00030.bin",
600
+ "rwkv.blocks.38.ln1.weight": "pytorch_model-00028-of-00030.bin",
601
+ "rwkv.blocks.38.ln2.bias": "pytorch_model-00028-of-00030.bin",
602
+ "rwkv.blocks.38.ln2.weight": "pytorch_model-00028-of-00030.bin",
603
+ "rwkv.blocks.39.attention.key.weight": "pytorch_model-00029-of-00030.bin",
604
+ "rwkv.blocks.39.attention.output.weight": "pytorch_model-00029-of-00030.bin",
605
+ "rwkv.blocks.39.attention.receptance.weight": "pytorch_model-00029-of-00030.bin",
606
+ "rwkv.blocks.39.attention.time_decay": "pytorch_model-00029-of-00030.bin",
607
+ "rwkv.blocks.39.attention.time_first": "pytorch_model-00029-of-00030.bin",
608
+ "rwkv.blocks.39.attention.time_mix_key": "pytorch_model-00029-of-00030.bin",
609
+ "rwkv.blocks.39.attention.time_mix_receptance": "pytorch_model-00029-of-00030.bin",
610
+ "rwkv.blocks.39.attention.time_mix_value": "pytorch_model-00029-of-00030.bin",
611
+ "rwkv.blocks.39.attention.value.weight": "pytorch_model-00029-of-00030.bin",
612
+ "rwkv.blocks.39.feed_forward.key.weight": "pytorch_model-00029-of-00030.bin",
613
+ "rwkv.blocks.39.feed_forward.receptance.weight": "pytorch_model-00029-of-00030.bin",
614
+ "rwkv.blocks.39.feed_forward.time_mix_key": "pytorch_model-00029-of-00030.bin",
615
+ "rwkv.blocks.39.feed_forward.time_mix_receptance": "pytorch_model-00029-of-00030.bin",
616
+ "rwkv.blocks.39.feed_forward.value.weight": "pytorch_model-00029-of-00030.bin",
617
+ "rwkv.blocks.39.ln1.bias": "pytorch_model-00029-of-00030.bin",
618
+ "rwkv.blocks.39.ln1.weight": "pytorch_model-00029-of-00030.bin",
619
+ "rwkv.blocks.39.ln2.bias": "pytorch_model-00029-of-00030.bin",
620
+ "rwkv.blocks.39.ln2.weight": "pytorch_model-00029-of-00030.bin",
621
+ "rwkv.blocks.4.attention.key.weight": "pytorch_model-00004-of-00030.bin",
622
+ "rwkv.blocks.4.attention.output.weight": "pytorch_model-00004-of-00030.bin",
623
+ "rwkv.blocks.4.attention.receptance.weight": "pytorch_model-00004-of-00030.bin",
624
+ "rwkv.blocks.4.attention.time_decay": "pytorch_model-00004-of-00030.bin",
625
+ "rwkv.blocks.4.attention.time_first": "pytorch_model-00004-of-00030.bin",
626
+ "rwkv.blocks.4.attention.time_mix_key": "pytorch_model-00004-of-00030.bin",
627
+ "rwkv.blocks.4.attention.time_mix_receptance": "pytorch_model-00004-of-00030.bin",
628
+ "rwkv.blocks.4.attention.time_mix_value": "pytorch_model-00004-of-00030.bin",
629
+ "rwkv.blocks.4.attention.value.weight": "pytorch_model-00004-of-00030.bin",
630
+ "rwkv.blocks.4.feed_forward.key.weight": "pytorch_model-00004-of-00030.bin",
631
+ "rwkv.blocks.4.feed_forward.receptance.weight": "pytorch_model-00004-of-00030.bin",
632
+ "rwkv.blocks.4.feed_forward.time_mix_key": "pytorch_model-00004-of-00030.bin",
633
+ "rwkv.blocks.4.feed_forward.time_mix_receptance": "pytorch_model-00004-of-00030.bin",
634
+ "rwkv.blocks.4.feed_forward.value.weight": "pytorch_model-00004-of-00030.bin",
635
+ "rwkv.blocks.4.ln1.bias": "pytorch_model-00004-of-00030.bin",
636
+ "rwkv.blocks.4.ln1.weight": "pytorch_model-00004-of-00030.bin",
637
+ "rwkv.blocks.4.ln2.bias": "pytorch_model-00004-of-00030.bin",
638
+ "rwkv.blocks.4.ln2.weight": "pytorch_model-00004-of-00030.bin",
639
+ "rwkv.blocks.5.attention.key.weight": "pytorch_model-00004-of-00030.bin",
640
+ "rwkv.blocks.5.attention.output.weight": "pytorch_model-00005-of-00030.bin",
641
+ "rwkv.blocks.5.attention.receptance.weight": "pytorch_model-00005-of-00030.bin",
642
+ "rwkv.blocks.5.attention.time_decay": "pytorch_model-00004-of-00030.bin",
643
+ "rwkv.blocks.5.attention.time_first": "pytorch_model-00004-of-00030.bin",
644
+ "rwkv.blocks.5.attention.time_mix_key": "pytorch_model-00004-of-00030.bin",
645
+ "rwkv.blocks.5.attention.time_mix_receptance": "pytorch_model-00004-of-00030.bin",
646
+ "rwkv.blocks.5.attention.time_mix_value": "pytorch_model-00004-of-00030.bin",
647
+ "rwkv.blocks.5.attention.value.weight": "pytorch_model-00005-of-00030.bin",
648
+ "rwkv.blocks.5.feed_forward.key.weight": "pytorch_model-00005-of-00030.bin",
649
+ "rwkv.blocks.5.feed_forward.receptance.weight": "pytorch_model-00005-of-00030.bin",
650
+ "rwkv.blocks.5.feed_forward.time_mix_key": "pytorch_model-00005-of-00030.bin",
651
+ "rwkv.blocks.5.feed_forward.time_mix_receptance": "pytorch_model-00005-of-00030.bin",
652
+ "rwkv.blocks.5.feed_forward.value.weight": "pytorch_model-00005-of-00030.bin",
653
+ "rwkv.blocks.5.ln1.bias": "pytorch_model-00004-of-00030.bin",
654
+ "rwkv.blocks.5.ln1.weight": "pytorch_model-00004-of-00030.bin",
655
+ "rwkv.blocks.5.ln2.bias": "pytorch_model-00004-of-00030.bin",
656
+ "rwkv.blocks.5.ln2.weight": "pytorch_model-00004-of-00030.bin",
657
+ "rwkv.blocks.6.attention.key.weight": "pytorch_model-00005-of-00030.bin",
658
+ "rwkv.blocks.6.attention.output.weight": "pytorch_model-00005-of-00030.bin",
659
+ "rwkv.blocks.6.attention.receptance.weight": "pytorch_model-00005-of-00030.bin",
660
+ "rwkv.blocks.6.attention.time_decay": "pytorch_model-00005-of-00030.bin",
661
+ "rwkv.blocks.6.attention.time_first": "pytorch_model-00005-of-00030.bin",
662
+ "rwkv.blocks.6.attention.time_mix_key": "pytorch_model-00005-of-00030.bin",
663
+ "rwkv.blocks.6.attention.time_mix_receptance": "pytorch_model-00005-of-00030.bin",
664
+ "rwkv.blocks.6.attention.time_mix_value": "pytorch_model-00005-of-00030.bin",
665
+ "rwkv.blocks.6.attention.value.weight": "pytorch_model-00005-of-00030.bin",
666
+ "rwkv.blocks.6.feed_forward.key.weight": "pytorch_model-00006-of-00030.bin",
667
+ "rwkv.blocks.6.feed_forward.receptance.weight": "pytorch_model-00006-of-00030.bin",
668
+ "rwkv.blocks.6.feed_forward.time_mix_key": "pytorch_model-00005-of-00030.bin",
669
+ "rwkv.blocks.6.feed_forward.time_mix_receptance": "pytorch_model-00005-of-00030.bin",
670
+ "rwkv.blocks.6.feed_forward.value.weight": "pytorch_model-00006-of-00030.bin",
671
+ "rwkv.blocks.6.ln1.bias": "pytorch_model-00005-of-00030.bin",
672
+ "rwkv.blocks.6.ln1.weight": "pytorch_model-00005-of-00030.bin",
673
+ "rwkv.blocks.6.ln2.bias": "pytorch_model-00005-of-00030.bin",
674
+ "rwkv.blocks.6.ln2.weight": "pytorch_model-00005-of-00030.bin",
675
+ "rwkv.blocks.7.attention.key.weight": "pytorch_model-00006-of-00030.bin",
676
+ "rwkv.blocks.7.attention.output.weight": "pytorch_model-00006-of-00030.bin",
677
+ "rwkv.blocks.7.attention.receptance.weight": "pytorch_model-00006-of-00030.bin",
678
+ "rwkv.blocks.7.attention.time_decay": "pytorch_model-00006-of-00030.bin",
679
+ "rwkv.blocks.7.attention.time_first": "pytorch_model-00006-of-00030.bin",
680
+ "rwkv.blocks.7.attention.time_mix_key": "pytorch_model-00006-of-00030.bin",
681
+ "rwkv.blocks.7.attention.time_mix_receptance": "pytorch_model-00006-of-00030.bin",
682
+ "rwkv.blocks.7.attention.time_mix_value": "pytorch_model-00006-of-00030.bin",
683
+ "rwkv.blocks.7.attention.value.weight": "pytorch_model-00006-of-00030.bin",
684
+ "rwkv.blocks.7.feed_forward.key.weight": "pytorch_model-00006-of-00030.bin",
685
+ "rwkv.blocks.7.feed_forward.receptance.weight": "pytorch_model-00006-of-00030.bin",
686
+ "rwkv.blocks.7.feed_forward.time_mix_key": "pytorch_model-00006-of-00030.bin",
687
+ "rwkv.blocks.7.feed_forward.time_mix_receptance": "pytorch_model-00006-of-00030.bin",
688
+ "rwkv.blocks.7.feed_forward.value.weight": "pytorch_model-00007-of-00030.bin",
689
+ "rwkv.blocks.7.ln1.bias": "pytorch_model-00006-of-00030.bin",
690
+ "rwkv.blocks.7.ln1.weight": "pytorch_model-00006-of-00030.bin",
691
+ "rwkv.blocks.7.ln2.bias": "pytorch_model-00006-of-00030.bin",
692
+ "rwkv.blocks.7.ln2.weight": "pytorch_model-00006-of-00030.bin",
693
+ "rwkv.blocks.8.attention.key.weight": "pytorch_model-00007-of-00030.bin",
694
+ "rwkv.blocks.8.attention.output.weight": "pytorch_model-00007-of-00030.bin",
695
+ "rwkv.blocks.8.attention.receptance.weight": "pytorch_model-00007-of-00030.bin",
696
+ "rwkv.blocks.8.attention.time_decay": "pytorch_model-00007-of-00030.bin",
697
+ "rwkv.blocks.8.attention.time_first": "pytorch_model-00007-of-00030.bin",
698
+ "rwkv.blocks.8.attention.time_mix_key": "pytorch_model-00007-of-00030.bin",
699
+ "rwkv.blocks.8.attention.time_mix_receptance": "pytorch_model-00007-of-00030.bin",
700
+ "rwkv.blocks.8.attention.time_mix_value": "pytorch_model-00007-of-00030.bin",
701
+ "rwkv.blocks.8.attention.value.weight": "pytorch_model-00007-of-00030.bin",
702
+ "rwkv.blocks.8.feed_forward.key.weight": "pytorch_model-00007-of-00030.bin",
703
+ "rwkv.blocks.8.feed_forward.receptance.weight": "pytorch_model-00007-of-00030.bin",
704
+ "rwkv.blocks.8.feed_forward.time_mix_key": "pytorch_model-00007-of-00030.bin",
705
+ "rwkv.blocks.8.feed_forward.time_mix_receptance": "pytorch_model-00007-of-00030.bin",
706
+ "rwkv.blocks.8.feed_forward.value.weight": "pytorch_model-00007-of-00030.bin",
707
+ "rwkv.blocks.8.ln1.bias": "pytorch_model-00007-of-00030.bin",
708
+ "rwkv.blocks.8.ln1.weight": "pytorch_model-00007-of-00030.bin",
709
+ "rwkv.blocks.8.ln2.bias": "pytorch_model-00007-of-00030.bin",
710
+ "rwkv.blocks.8.ln2.weight": "pytorch_model-00007-of-00030.bin",
711
+ "rwkv.blocks.9.attention.key.weight": "pytorch_model-00007-of-00030.bin",
712
+ "rwkv.blocks.9.attention.output.weight": "pytorch_model-00008-of-00030.bin",
713
+ "rwkv.blocks.9.attention.receptance.weight": "pytorch_model-00008-of-00030.bin",
714
+ "rwkv.blocks.9.attention.time_decay": "pytorch_model-00007-of-00030.bin",
715
+ "rwkv.blocks.9.attention.time_first": "pytorch_model-00007-of-00030.bin",
716
+ "rwkv.blocks.9.attention.time_mix_key": "pytorch_model-00007-of-00030.bin",
717
+ "rwkv.blocks.9.attention.time_mix_receptance": "pytorch_model-00007-of-00030.bin",
718
+ "rwkv.blocks.9.attention.time_mix_value": "pytorch_model-00007-of-00030.bin",
719
+ "rwkv.blocks.9.attention.value.weight": "pytorch_model-00007-of-00030.bin",
720
+ "rwkv.blocks.9.feed_forward.key.weight": "pytorch_model-00008-of-00030.bin",
721
+ "rwkv.blocks.9.feed_forward.receptance.weight": "pytorch_model-00008-of-00030.bin",
722
+ "rwkv.blocks.9.feed_forward.time_mix_key": "pytorch_model-00008-of-00030.bin",
723
+ "rwkv.blocks.9.feed_forward.time_mix_receptance": "pytorch_model-00008-of-00030.bin",
724
+ "rwkv.blocks.9.feed_forward.value.weight": "pytorch_model-00008-of-00030.bin",
725
+ "rwkv.blocks.9.ln1.bias": "pytorch_model-00007-of-00030.bin",
726
+ "rwkv.blocks.9.ln1.weight": "pytorch_model-00007-of-00030.bin",
727
+ "rwkv.blocks.9.ln2.bias": "pytorch_model-00007-of-00030.bin",
728
+ "rwkv.blocks.9.ln2.weight": "pytorch_model-00007-of-00030.bin",
729
+ "rwkv.embeddings.weight": "pytorch_model-00001-of-00030.bin",
730
+ "rwkv.ln_out.bias": "pytorch_model-00029-of-00030.bin",
731
+ "rwkv.ln_out.weight": "pytorch_model-00029-of-00030.bin"
732
+ }
733
+ }