beomi commited on
Commit
1d24557
1 Parent(s): 735c370
README.md CHANGED
@@ -1,3 +1,54 @@
1
  ---
2
- license: apache-2.0
 
 
 
 
 
3
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
+ license: mit
3
+ tags:
4
+ - generated_from_trainer
5
+ model-index:
6
+ - name: KoRWKV-6B-koalpaca-v1.1a
7
+ results: []
8
  ---
9
+
10
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
11
+ should probably proofread and complete it, then remove this comment. -->
12
+
13
+ # KoRWKV-6B-koalpaca-v1.1a
14
+
15
+ This model is a fine-tuned version of [beomi/KoRWKV-6B](https://huggingface.co/beomi/KoRWKV-6B) on an unknown dataset.
16
+
17
+ ## Model description
18
+
19
+ More information needed
20
+
21
+ ## Intended uses & limitations
22
+
23
+ More information needed
24
+
25
+ ## Training and evaluation data
26
+
27
+ More information needed
28
+
29
+ ## Training procedure
30
+
31
+ ### Training hyperparameters
32
+
33
+ The following hyperparameters were used during training:
34
+ - learning_rate: 2e-05
35
+ - train_batch_size: 1
36
+ - eval_batch_size: 8
37
+ - seed: 42
38
+ - gradient_accumulation_steps: 8
39
+ - total_train_batch_size: 8
40
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
41
+ - lr_scheduler_type: linear
42
+ - num_epochs: 1.0
43
+ - mixed_precision_training: Native AMP
44
+
45
+ ### Training results
46
+
47
+
48
+
49
+ ### Framework versions
50
+
51
+ - Transformers 4.29.2
52
+ - Pytorch 1.13.1
53
+ - Datasets 2.12.0
54
+ - Tokenizers 0.13.3
all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "train_loss": 2.389765337578156,
4
+ "train_runtime": 86824.1392,
5
+ "train_samples": 3818,
6
+ "train_samples_per_second": 0.044,
7
+ "train_steps_per_second": 0.005
8
+ }
config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "./KoRWKV-6B-koalpaca-v1.1a/",
3
+ "architectures": [
4
+ "RwkvForCausalLM"
5
+ ],
6
+ "attention_hidden_size": 4096,
7
+ "bos_token_id": 0,
8
+ "context_length": 1024,
9
+ "eos_token_id": 0,
10
+ "hidden_size": 4096,
11
+ "intermediate_size": 16384,
12
+ "layer_norm_epsilon": 1e-05,
13
+ "model_type": "rwkv",
14
+ "num_hidden_layers": 28,
15
+ "rescale_every": 6,
16
+ "tie_word_embeddings": false,
17
+ "torch_dtype": "float32",
18
+ "transformers_version": "4.29.2",
19
+ "use_cache": true,
20
+ "vocab_size": 52000
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": "4.29.2"
6
+ }
pytorch_model-00001-of-00003.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:666c3137efc2580d1800333a46349692dadcce9a0db3d58e9e1a5da3f9268942
3
+ size 9846641421
pytorch_model-00002-of-00003.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4328d63de4cda65a0f3a9a29e8b2905724f80606eb366d23e52f3f2842848b16
3
+ size 9934165539
pytorch_model-00003-of-00003.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3b877cd58fb934ea92524e8bc02791847a4142010b443d1fdb14d29ced6dd89
3
+ size 6356048487
pytorch_model.bin.index.json ADDED
@@ -0,0 +1,517 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 26136674304
4
+ },
5
+ "weight_map": {
6
+ "head.weight": "pytorch_model-00003-of-00003.bin",
7
+ "rwkv.blocks.0.attention.key.weight": "pytorch_model-00001-of-00003.bin",
8
+ "rwkv.blocks.0.attention.output.weight": "pytorch_model-00001-of-00003.bin",
9
+ "rwkv.blocks.0.attention.receptance.weight": "pytorch_model-00001-of-00003.bin",
10
+ "rwkv.blocks.0.attention.time_decay": "pytorch_model-00001-of-00003.bin",
11
+ "rwkv.blocks.0.attention.time_first": "pytorch_model-00001-of-00003.bin",
12
+ "rwkv.blocks.0.attention.time_mix_key": "pytorch_model-00001-of-00003.bin",
13
+ "rwkv.blocks.0.attention.time_mix_receptance": "pytorch_model-00001-of-00003.bin",
14
+ "rwkv.blocks.0.attention.time_mix_value": "pytorch_model-00001-of-00003.bin",
15
+ "rwkv.blocks.0.attention.value.weight": "pytorch_model-00001-of-00003.bin",
16
+ "rwkv.blocks.0.feed_forward.key.weight": "pytorch_model-00001-of-00003.bin",
17
+ "rwkv.blocks.0.feed_forward.receptance.weight": "pytorch_model-00001-of-00003.bin",
18
+ "rwkv.blocks.0.feed_forward.time_mix_key": "pytorch_model-00001-of-00003.bin",
19
+ "rwkv.blocks.0.feed_forward.time_mix_receptance": "pytorch_model-00001-of-00003.bin",
20
+ "rwkv.blocks.0.feed_forward.value.weight": "pytorch_model-00001-of-00003.bin",
21
+ "rwkv.blocks.0.ln1.bias": "pytorch_model-00001-of-00003.bin",
22
+ "rwkv.blocks.0.ln1.weight": "pytorch_model-00001-of-00003.bin",
23
+ "rwkv.blocks.0.ln2.bias": "pytorch_model-00001-of-00003.bin",
24
+ "rwkv.blocks.0.ln2.weight": "pytorch_model-00001-of-00003.bin",
25
+ "rwkv.blocks.0.pre_ln.bias": "pytorch_model-00001-of-00003.bin",
26
+ "rwkv.blocks.0.pre_ln.weight": "pytorch_model-00001-of-00003.bin",
27
+ "rwkv.blocks.1.attention.key.weight": "pytorch_model-00001-of-00003.bin",
28
+ "rwkv.blocks.1.attention.output.weight": "pytorch_model-00001-of-00003.bin",
29
+ "rwkv.blocks.1.attention.receptance.weight": "pytorch_model-00001-of-00003.bin",
30
+ "rwkv.blocks.1.attention.time_decay": "pytorch_model-00001-of-00003.bin",
31
+ "rwkv.blocks.1.attention.time_first": "pytorch_model-00001-of-00003.bin",
32
+ "rwkv.blocks.1.attention.time_mix_key": "pytorch_model-00001-of-00003.bin",
33
+ "rwkv.blocks.1.attention.time_mix_receptance": "pytorch_model-00001-of-00003.bin",
34
+ "rwkv.blocks.1.attention.time_mix_value": "pytorch_model-00001-of-00003.bin",
35
+ "rwkv.blocks.1.attention.value.weight": "pytorch_model-00001-of-00003.bin",
36
+ "rwkv.blocks.1.feed_forward.key.weight": "pytorch_model-00001-of-00003.bin",
37
+ "rwkv.blocks.1.feed_forward.receptance.weight": "pytorch_model-00001-of-00003.bin",
38
+ "rwkv.blocks.1.feed_forward.time_mix_key": "pytorch_model-00001-of-00003.bin",
39
+ "rwkv.blocks.1.feed_forward.time_mix_receptance": "pytorch_model-00001-of-00003.bin",
40
+ "rwkv.blocks.1.feed_forward.value.weight": "pytorch_model-00001-of-00003.bin",
41
+ "rwkv.blocks.1.ln1.bias": "pytorch_model-00001-of-00003.bin",
42
+ "rwkv.blocks.1.ln1.weight": "pytorch_model-00001-of-00003.bin",
43
+ "rwkv.blocks.1.ln2.bias": "pytorch_model-00001-of-00003.bin",
44
+ "rwkv.blocks.1.ln2.weight": "pytorch_model-00001-of-00003.bin",
45
+ "rwkv.blocks.10.attention.key.weight": "pytorch_model-00001-of-00003.bin",
46
+ "rwkv.blocks.10.attention.output.weight": "pytorch_model-00001-of-00003.bin",
47
+ "rwkv.blocks.10.attention.receptance.weight": "pytorch_model-00001-of-00003.bin",
48
+ "rwkv.blocks.10.attention.time_decay": "pytorch_model-00001-of-00003.bin",
49
+ "rwkv.blocks.10.attention.time_first": "pytorch_model-00001-of-00003.bin",
50
+ "rwkv.blocks.10.attention.time_mix_key": "pytorch_model-00001-of-00003.bin",
51
+ "rwkv.blocks.10.attention.time_mix_receptance": "pytorch_model-00001-of-00003.bin",
52
+ "rwkv.blocks.10.attention.time_mix_value": "pytorch_model-00001-of-00003.bin",
53
+ "rwkv.blocks.10.attention.value.weight": "pytorch_model-00001-of-00003.bin",
54
+ "rwkv.blocks.10.feed_forward.key.weight": "pytorch_model-00002-of-00003.bin",
55
+ "rwkv.blocks.10.feed_forward.receptance.weight": "pytorch_model-00002-of-00003.bin",
56
+ "rwkv.blocks.10.feed_forward.time_mix_key": "pytorch_model-00001-of-00003.bin",
57
+ "rwkv.blocks.10.feed_forward.time_mix_receptance": "pytorch_model-00001-of-00003.bin",
58
+ "rwkv.blocks.10.feed_forward.value.weight": "pytorch_model-00002-of-00003.bin",
59
+ "rwkv.blocks.10.ln1.bias": "pytorch_model-00001-of-00003.bin",
60
+ "rwkv.blocks.10.ln1.weight": "pytorch_model-00001-of-00003.bin",
61
+ "rwkv.blocks.10.ln2.bias": "pytorch_model-00001-of-00003.bin",
62
+ "rwkv.blocks.10.ln2.weight": "pytorch_model-00001-of-00003.bin",
63
+ "rwkv.blocks.11.attention.key.weight": "pytorch_model-00002-of-00003.bin",
64
+ "rwkv.blocks.11.attention.output.weight": "pytorch_model-00002-of-00003.bin",
65
+ "rwkv.blocks.11.attention.receptance.weight": "pytorch_model-00002-of-00003.bin",
66
+ "rwkv.blocks.11.attention.time_decay": "pytorch_model-00002-of-00003.bin",
67
+ "rwkv.blocks.11.attention.time_first": "pytorch_model-00002-of-00003.bin",
68
+ "rwkv.blocks.11.attention.time_mix_key": "pytorch_model-00002-of-00003.bin",
69
+ "rwkv.blocks.11.attention.time_mix_receptance": "pytorch_model-00002-of-00003.bin",
70
+ "rwkv.blocks.11.attention.time_mix_value": "pytorch_model-00002-of-00003.bin",
71
+ "rwkv.blocks.11.attention.value.weight": "pytorch_model-00002-of-00003.bin",
72
+ "rwkv.blocks.11.feed_forward.key.weight": "pytorch_model-00002-of-00003.bin",
73
+ "rwkv.blocks.11.feed_forward.receptance.weight": "pytorch_model-00002-of-00003.bin",
74
+ "rwkv.blocks.11.feed_forward.time_mix_key": "pytorch_model-00002-of-00003.bin",
75
+ "rwkv.blocks.11.feed_forward.time_mix_receptance": "pytorch_model-00002-of-00003.bin",
76
+ "rwkv.blocks.11.feed_forward.value.weight": "pytorch_model-00002-of-00003.bin",
77
+ "rwkv.blocks.11.ln1.bias": "pytorch_model-00002-of-00003.bin",
78
+ "rwkv.blocks.11.ln1.weight": "pytorch_model-00002-of-00003.bin",
79
+ "rwkv.blocks.11.ln2.bias": "pytorch_model-00002-of-00003.bin",
80
+ "rwkv.blocks.11.ln2.weight": "pytorch_model-00002-of-00003.bin",
81
+ "rwkv.blocks.12.attention.key.weight": "pytorch_model-00002-of-00003.bin",
82
+ "rwkv.blocks.12.attention.output.weight": "pytorch_model-00002-of-00003.bin",
83
+ "rwkv.blocks.12.attention.receptance.weight": "pytorch_model-00002-of-00003.bin",
84
+ "rwkv.blocks.12.attention.time_decay": "pytorch_model-00002-of-00003.bin",
85
+ "rwkv.blocks.12.attention.time_first": "pytorch_model-00002-of-00003.bin",
86
+ "rwkv.blocks.12.attention.time_mix_key": "pytorch_model-00002-of-00003.bin",
87
+ "rwkv.blocks.12.attention.time_mix_receptance": "pytorch_model-00002-of-00003.bin",
88
+ "rwkv.blocks.12.attention.time_mix_value": "pytorch_model-00002-of-00003.bin",
89
+ "rwkv.blocks.12.attention.value.weight": "pytorch_model-00002-of-00003.bin",
90
+ "rwkv.blocks.12.feed_forward.key.weight": "pytorch_model-00002-of-00003.bin",
91
+ "rwkv.blocks.12.feed_forward.receptance.weight": "pytorch_model-00002-of-00003.bin",
92
+ "rwkv.blocks.12.feed_forward.time_mix_key": "pytorch_model-00002-of-00003.bin",
93
+ "rwkv.blocks.12.feed_forward.time_mix_receptance": "pytorch_model-00002-of-00003.bin",
94
+ "rwkv.blocks.12.feed_forward.value.weight": "pytorch_model-00002-of-00003.bin",
95
+ "rwkv.blocks.12.ln1.bias": "pytorch_model-00002-of-00003.bin",
96
+ "rwkv.blocks.12.ln1.weight": "pytorch_model-00002-of-00003.bin",
97
+ "rwkv.blocks.12.ln2.bias": "pytorch_model-00002-of-00003.bin",
98
+ "rwkv.blocks.12.ln2.weight": "pytorch_model-00002-of-00003.bin",
99
+ "rwkv.blocks.13.attention.key.weight": "pytorch_model-00002-of-00003.bin",
100
+ "rwkv.blocks.13.attention.output.weight": "pytorch_model-00002-of-00003.bin",
101
+ "rwkv.blocks.13.attention.receptance.weight": "pytorch_model-00002-of-00003.bin",
102
+ "rwkv.blocks.13.attention.time_decay": "pytorch_model-00002-of-00003.bin",
103
+ "rwkv.blocks.13.attention.time_first": "pytorch_model-00002-of-00003.bin",
104
+ "rwkv.blocks.13.attention.time_mix_key": "pytorch_model-00002-of-00003.bin",
105
+ "rwkv.blocks.13.attention.time_mix_receptance": "pytorch_model-00002-of-00003.bin",
106
+ "rwkv.blocks.13.attention.time_mix_value": "pytorch_model-00002-of-00003.bin",
107
+ "rwkv.blocks.13.attention.value.weight": "pytorch_model-00002-of-00003.bin",
108
+ "rwkv.blocks.13.feed_forward.key.weight": "pytorch_model-00002-of-00003.bin",
109
+ "rwkv.blocks.13.feed_forward.receptance.weight": "pytorch_model-00002-of-00003.bin",
110
+ "rwkv.blocks.13.feed_forward.time_mix_key": "pytorch_model-00002-of-00003.bin",
111
+ "rwkv.blocks.13.feed_forward.time_mix_receptance": "pytorch_model-00002-of-00003.bin",
112
+ "rwkv.blocks.13.feed_forward.value.weight": "pytorch_model-00002-of-00003.bin",
113
+ "rwkv.blocks.13.ln1.bias": "pytorch_model-00002-of-00003.bin",
114
+ "rwkv.blocks.13.ln1.weight": "pytorch_model-00002-of-00003.bin",
115
+ "rwkv.blocks.13.ln2.bias": "pytorch_model-00002-of-00003.bin",
116
+ "rwkv.blocks.13.ln2.weight": "pytorch_model-00002-of-00003.bin",
117
+ "rwkv.blocks.14.attention.key.weight": "pytorch_model-00002-of-00003.bin",
118
+ "rwkv.blocks.14.attention.output.weight": "pytorch_model-00002-of-00003.bin",
119
+ "rwkv.blocks.14.attention.receptance.weight": "pytorch_model-00002-of-00003.bin",
120
+ "rwkv.blocks.14.attention.time_decay": "pytorch_model-00002-of-00003.bin",
121
+ "rwkv.blocks.14.attention.time_first": "pytorch_model-00002-of-00003.bin",
122
+ "rwkv.blocks.14.attention.time_mix_key": "pytorch_model-00002-of-00003.bin",
123
+ "rwkv.blocks.14.attention.time_mix_receptance": "pytorch_model-00002-of-00003.bin",
124
+ "rwkv.blocks.14.attention.time_mix_value": "pytorch_model-00002-of-00003.bin",
125
+ "rwkv.blocks.14.attention.value.weight": "pytorch_model-00002-of-00003.bin",
126
+ "rwkv.blocks.14.feed_forward.key.weight": "pytorch_model-00002-of-00003.bin",
127
+ "rwkv.blocks.14.feed_forward.receptance.weight": "pytorch_model-00002-of-00003.bin",
128
+ "rwkv.blocks.14.feed_forward.time_mix_key": "pytorch_model-00002-of-00003.bin",
129
+ "rwkv.blocks.14.feed_forward.time_mix_receptance": "pytorch_model-00002-of-00003.bin",
130
+ "rwkv.blocks.14.feed_forward.value.weight": "pytorch_model-00002-of-00003.bin",
131
+ "rwkv.blocks.14.ln1.bias": "pytorch_model-00002-of-00003.bin",
132
+ "rwkv.blocks.14.ln1.weight": "pytorch_model-00002-of-00003.bin",
133
+ "rwkv.blocks.14.ln2.bias": "pytorch_model-00002-of-00003.bin",
134
+ "rwkv.blocks.14.ln2.weight": "pytorch_model-00002-of-00003.bin",
135
+ "rwkv.blocks.15.attention.key.weight": "pytorch_model-00002-of-00003.bin",
136
+ "rwkv.blocks.15.attention.output.weight": "pytorch_model-00002-of-00003.bin",
137
+ "rwkv.blocks.15.attention.receptance.weight": "pytorch_model-00002-of-00003.bin",
138
+ "rwkv.blocks.15.attention.time_decay": "pytorch_model-00002-of-00003.bin",
139
+ "rwkv.blocks.15.attention.time_first": "pytorch_model-00002-of-00003.bin",
140
+ "rwkv.blocks.15.attention.time_mix_key": "pytorch_model-00002-of-00003.bin",
141
+ "rwkv.blocks.15.attention.time_mix_receptance": "pytorch_model-00002-of-00003.bin",
142
+ "rwkv.blocks.15.attention.time_mix_value": "pytorch_model-00002-of-00003.bin",
143
+ "rwkv.blocks.15.attention.value.weight": "pytorch_model-00002-of-00003.bin",
144
+ "rwkv.blocks.15.feed_forward.key.weight": "pytorch_model-00002-of-00003.bin",
145
+ "rwkv.blocks.15.feed_forward.receptance.weight": "pytorch_model-00002-of-00003.bin",
146
+ "rwkv.blocks.15.feed_forward.time_mix_key": "pytorch_model-00002-of-00003.bin",
147
+ "rwkv.blocks.15.feed_forward.time_mix_receptance": "pytorch_model-00002-of-00003.bin",
148
+ "rwkv.blocks.15.feed_forward.value.weight": "pytorch_model-00002-of-00003.bin",
149
+ "rwkv.blocks.15.ln1.bias": "pytorch_model-00002-of-00003.bin",
150
+ "rwkv.blocks.15.ln1.weight": "pytorch_model-00002-of-00003.bin",
151
+ "rwkv.blocks.15.ln2.bias": "pytorch_model-00002-of-00003.bin",
152
+ "rwkv.blocks.15.ln2.weight": "pytorch_model-00002-of-00003.bin",
153
+ "rwkv.blocks.16.attention.key.weight": "pytorch_model-00002-of-00003.bin",
154
+ "rwkv.blocks.16.attention.output.weight": "pytorch_model-00002-of-00003.bin",
155
+ "rwkv.blocks.16.attention.receptance.weight": "pytorch_model-00002-of-00003.bin",
156
+ "rwkv.blocks.16.attention.time_decay": "pytorch_model-00002-of-00003.bin",
157
+ "rwkv.blocks.16.attention.time_first": "pytorch_model-00002-of-00003.bin",
158
+ "rwkv.blocks.16.attention.time_mix_key": "pytorch_model-00002-of-00003.bin",
159
+ "rwkv.blocks.16.attention.time_mix_receptance": "pytorch_model-00002-of-00003.bin",
160
+ "rwkv.blocks.16.attention.time_mix_value": "pytorch_model-00002-of-00003.bin",
161
+ "rwkv.blocks.16.attention.value.weight": "pytorch_model-00002-of-00003.bin",
162
+ "rwkv.blocks.16.feed_forward.key.weight": "pytorch_model-00002-of-00003.bin",
163
+ "rwkv.blocks.16.feed_forward.receptance.weight": "pytorch_model-00002-of-00003.bin",
164
+ "rwkv.blocks.16.feed_forward.time_mix_key": "pytorch_model-00002-of-00003.bin",
165
+ "rwkv.blocks.16.feed_forward.time_mix_receptance": "pytorch_model-00002-of-00003.bin",
166
+ "rwkv.blocks.16.feed_forward.value.weight": "pytorch_model-00002-of-00003.bin",
167
+ "rwkv.blocks.16.ln1.bias": "pytorch_model-00002-of-00003.bin",
168
+ "rwkv.blocks.16.ln1.weight": "pytorch_model-00002-of-00003.bin",
169
+ "rwkv.blocks.16.ln2.bias": "pytorch_model-00002-of-00003.bin",
170
+ "rwkv.blocks.16.ln2.weight": "pytorch_model-00002-of-00003.bin",
171
+ "rwkv.blocks.17.attention.key.weight": "pytorch_model-00002-of-00003.bin",
172
+ "rwkv.blocks.17.attention.output.weight": "pytorch_model-00002-of-00003.bin",
173
+ "rwkv.blocks.17.attention.receptance.weight": "pytorch_model-00002-of-00003.bin",
174
+ "rwkv.blocks.17.attention.time_decay": "pytorch_model-00002-of-00003.bin",
175
+ "rwkv.blocks.17.attention.time_first": "pytorch_model-00002-of-00003.bin",
176
+ "rwkv.blocks.17.attention.time_mix_key": "pytorch_model-00002-of-00003.bin",
177
+ "rwkv.blocks.17.attention.time_mix_receptance": "pytorch_model-00002-of-00003.bin",
178
+ "rwkv.blocks.17.attention.time_mix_value": "pytorch_model-00002-of-00003.bin",
179
+ "rwkv.blocks.17.attention.value.weight": "pytorch_model-00002-of-00003.bin",
180
+ "rwkv.blocks.17.feed_forward.key.weight": "pytorch_model-00002-of-00003.bin",
181
+ "rwkv.blocks.17.feed_forward.receptance.weight": "pytorch_model-00002-of-00003.bin",
182
+ "rwkv.blocks.17.feed_forward.time_mix_key": "pytorch_model-00002-of-00003.bin",
183
+ "rwkv.blocks.17.feed_forward.time_mix_receptance": "pytorch_model-00002-of-00003.bin",
184
+ "rwkv.blocks.17.feed_forward.value.weight": "pytorch_model-00002-of-00003.bin",
185
+ "rwkv.blocks.17.ln1.bias": "pytorch_model-00002-of-00003.bin",
186
+ "rwkv.blocks.17.ln1.weight": "pytorch_model-00002-of-00003.bin",
187
+ "rwkv.blocks.17.ln2.bias": "pytorch_model-00002-of-00003.bin",
188
+ "rwkv.blocks.17.ln2.weight": "pytorch_model-00002-of-00003.bin",
189
+ "rwkv.blocks.18.attention.key.weight": "pytorch_model-00002-of-00003.bin",
190
+ "rwkv.blocks.18.attention.output.weight": "pytorch_model-00002-of-00003.bin",
191
+ "rwkv.blocks.18.attention.receptance.weight": "pytorch_model-00002-of-00003.bin",
192
+ "rwkv.blocks.18.attention.time_decay": "pytorch_model-00002-of-00003.bin",
193
+ "rwkv.blocks.18.attention.time_first": "pytorch_model-00002-of-00003.bin",
194
+ "rwkv.blocks.18.attention.time_mix_key": "pytorch_model-00002-of-00003.bin",
195
+ "rwkv.blocks.18.attention.time_mix_receptance": "pytorch_model-00002-of-00003.bin",
196
+ "rwkv.blocks.18.attention.time_mix_value": "pytorch_model-00002-of-00003.bin",
197
+ "rwkv.blocks.18.attention.value.weight": "pytorch_model-00002-of-00003.bin",
198
+ "rwkv.blocks.18.feed_forward.key.weight": "pytorch_model-00002-of-00003.bin",
199
+ "rwkv.blocks.18.feed_forward.receptance.weight": "pytorch_model-00002-of-00003.bin",
200
+ "rwkv.blocks.18.feed_forward.time_mix_key": "pytorch_model-00002-of-00003.bin",
201
+ "rwkv.blocks.18.feed_forward.time_mix_receptance": "pytorch_model-00002-of-00003.bin",
202
+ "rwkv.blocks.18.feed_forward.value.weight": "pytorch_model-00002-of-00003.bin",
203
+ "rwkv.blocks.18.ln1.bias": "pytorch_model-00002-of-00003.bin",
204
+ "rwkv.blocks.18.ln1.weight": "pytorch_model-00002-of-00003.bin",
205
+ "rwkv.blocks.18.ln2.bias": "pytorch_model-00002-of-00003.bin",
206
+ "rwkv.blocks.18.ln2.weight": "pytorch_model-00002-of-00003.bin",
207
+ "rwkv.blocks.19.attention.key.weight": "pytorch_model-00002-of-00003.bin",
208
+ "rwkv.blocks.19.attention.output.weight": "pytorch_model-00002-of-00003.bin",
209
+ "rwkv.blocks.19.attention.receptance.weight": "pytorch_model-00002-of-00003.bin",
210
+ "rwkv.blocks.19.attention.time_decay": "pytorch_model-00002-of-00003.bin",
211
+ "rwkv.blocks.19.attention.time_first": "pytorch_model-00002-of-00003.bin",
212
+ "rwkv.blocks.19.attention.time_mix_key": "pytorch_model-00002-of-00003.bin",
213
+ "rwkv.blocks.19.attention.time_mix_receptance": "pytorch_model-00002-of-00003.bin",
214
+ "rwkv.blocks.19.attention.time_mix_value": "pytorch_model-00002-of-00003.bin",
215
+ "rwkv.blocks.19.attention.value.weight": "pytorch_model-00002-of-00003.bin",
216
+ "rwkv.blocks.19.feed_forward.key.weight": "pytorch_model-00002-of-00003.bin",
217
+ "rwkv.blocks.19.feed_forward.receptance.weight": "pytorch_model-00002-of-00003.bin",
218
+ "rwkv.blocks.19.feed_forward.time_mix_key": "pytorch_model-00002-of-00003.bin",
219
+ "rwkv.blocks.19.feed_forward.time_mix_receptance": "pytorch_model-00002-of-00003.bin",
220
+ "rwkv.blocks.19.feed_forward.value.weight": "pytorch_model-00002-of-00003.bin",
221
+ "rwkv.blocks.19.ln1.bias": "pytorch_model-00002-of-00003.bin",
222
+ "rwkv.blocks.19.ln1.weight": "pytorch_model-00002-of-00003.bin",
223
+ "rwkv.blocks.19.ln2.bias": "pytorch_model-00002-of-00003.bin",
224
+ "rwkv.blocks.19.ln2.weight": "pytorch_model-00002-of-00003.bin",
225
+ "rwkv.blocks.2.attention.key.weight": "pytorch_model-00001-of-00003.bin",
226
+ "rwkv.blocks.2.attention.output.weight": "pytorch_model-00001-of-00003.bin",
227
+ "rwkv.blocks.2.attention.receptance.weight": "pytorch_model-00001-of-00003.bin",
228
+ "rwkv.blocks.2.attention.time_decay": "pytorch_model-00001-of-00003.bin",
229
+ "rwkv.blocks.2.attention.time_first": "pytorch_model-00001-of-00003.bin",
230
+ "rwkv.blocks.2.attention.time_mix_key": "pytorch_model-00001-of-00003.bin",
231
+ "rwkv.blocks.2.attention.time_mix_receptance": "pytorch_model-00001-of-00003.bin",
232
+ "rwkv.blocks.2.attention.time_mix_value": "pytorch_model-00001-of-00003.bin",
233
+ "rwkv.blocks.2.attention.value.weight": "pytorch_model-00001-of-00003.bin",
234
+ "rwkv.blocks.2.feed_forward.key.weight": "pytorch_model-00001-of-00003.bin",
235
+ "rwkv.blocks.2.feed_forward.receptance.weight": "pytorch_model-00001-of-00003.bin",
236
+ "rwkv.blocks.2.feed_forward.time_mix_key": "pytorch_model-00001-of-00003.bin",
237
+ "rwkv.blocks.2.feed_forward.time_mix_receptance": "pytorch_model-00001-of-00003.bin",
238
+ "rwkv.blocks.2.feed_forward.value.weight": "pytorch_model-00001-of-00003.bin",
239
+ "rwkv.blocks.2.ln1.bias": "pytorch_model-00001-of-00003.bin",
240
+ "rwkv.blocks.2.ln1.weight": "pytorch_model-00001-of-00003.bin",
241
+ "rwkv.blocks.2.ln2.bias": "pytorch_model-00001-of-00003.bin",
242
+ "rwkv.blocks.2.ln2.weight": "pytorch_model-00001-of-00003.bin",
243
+ "rwkv.blocks.20.attention.key.weight": "pytorch_model-00002-of-00003.bin",
244
+ "rwkv.blocks.20.attention.output.weight": "pytorch_model-00002-of-00003.bin",
245
+ "rwkv.blocks.20.attention.receptance.weight": "pytorch_model-00002-of-00003.bin",
246
+ "rwkv.blocks.20.attention.time_decay": "pytorch_model-00002-of-00003.bin",
247
+ "rwkv.blocks.20.attention.time_first": "pytorch_model-00002-of-00003.bin",
248
+ "rwkv.blocks.20.attention.time_mix_key": "pytorch_model-00002-of-00003.bin",
249
+ "rwkv.blocks.20.attention.time_mix_receptance": "pytorch_model-00002-of-00003.bin",
250
+ "rwkv.blocks.20.attention.time_mix_value": "pytorch_model-00002-of-00003.bin",
251
+ "rwkv.blocks.20.attention.value.weight": "pytorch_model-00002-of-00003.bin",
252
+ "rwkv.blocks.20.feed_forward.key.weight": "pytorch_model-00002-of-00003.bin",
253
+ "rwkv.blocks.20.feed_forward.receptance.weight": "pytorch_model-00002-of-00003.bin",
254
+ "rwkv.blocks.20.feed_forward.time_mix_key": "pytorch_model-00002-of-00003.bin",
255
+ "rwkv.blocks.20.feed_forward.time_mix_receptance": "pytorch_model-00002-of-00003.bin",
256
+ "rwkv.blocks.20.feed_forward.value.weight": "pytorch_model-00002-of-00003.bin",
257
+ "rwkv.blocks.20.ln1.bias": "pytorch_model-00002-of-00003.bin",
258
+ "rwkv.blocks.20.ln1.weight": "pytorch_model-00002-of-00003.bin",
259
+ "rwkv.blocks.20.ln2.bias": "pytorch_model-00002-of-00003.bin",
260
+ "rwkv.blocks.20.ln2.weight": "pytorch_model-00002-of-00003.bin",
261
+ "rwkv.blocks.21.attention.key.weight": "pytorch_model-00002-of-00003.bin",
262
+ "rwkv.blocks.21.attention.output.weight": "pytorch_model-00002-of-00003.bin",
263
+ "rwkv.blocks.21.attention.receptance.weight": "pytorch_model-00002-of-00003.bin",
264
+ "rwkv.blocks.21.attention.time_decay": "pytorch_model-00002-of-00003.bin",
265
+ "rwkv.blocks.21.attention.time_first": "pytorch_model-00002-of-00003.bin",
266
+ "rwkv.blocks.21.attention.time_mix_key": "pytorch_model-00002-of-00003.bin",
267
+ "rwkv.blocks.21.attention.time_mix_receptance": "pytorch_model-00002-of-00003.bin",
268
+ "rwkv.blocks.21.attention.time_mix_value": "pytorch_model-00002-of-00003.bin",
269
+ "rwkv.blocks.21.attention.value.weight": "pytorch_model-00002-of-00003.bin",
270
+ "rwkv.blocks.21.feed_forward.key.weight": "pytorch_model-00002-of-00003.bin",
271
+ "rwkv.blocks.21.feed_forward.receptance.weight": "pytorch_model-00002-of-00003.bin",
272
+ "rwkv.blocks.21.feed_forward.time_mix_key": "pytorch_model-00002-of-00003.bin",
273
+ "rwkv.blocks.21.feed_forward.time_mix_receptance": "pytorch_model-00002-of-00003.bin",
274
+ "rwkv.blocks.21.feed_forward.value.weight": "pytorch_model-00003-of-00003.bin",
275
+ "rwkv.blocks.21.ln1.bias": "pytorch_model-00002-of-00003.bin",
276
+ "rwkv.blocks.21.ln1.weight": "pytorch_model-00002-of-00003.bin",
277
+ "rwkv.blocks.21.ln2.bias": "pytorch_model-00002-of-00003.bin",
278
+ "rwkv.blocks.21.ln2.weight": "pytorch_model-00002-of-00003.bin",
279
+ "rwkv.blocks.22.attention.key.weight": "pytorch_model-00003-of-00003.bin",
280
+ "rwkv.blocks.22.attention.output.weight": "pytorch_model-00003-of-00003.bin",
281
+ "rwkv.blocks.22.attention.receptance.weight": "pytorch_model-00003-of-00003.bin",
282
+ "rwkv.blocks.22.attention.time_decay": "pytorch_model-00003-of-00003.bin",
283
+ "rwkv.blocks.22.attention.time_first": "pytorch_model-00003-of-00003.bin",
284
+ "rwkv.blocks.22.attention.time_mix_key": "pytorch_model-00003-of-00003.bin",
285
+ "rwkv.blocks.22.attention.time_mix_receptance": "pytorch_model-00003-of-00003.bin",
286
+ "rwkv.blocks.22.attention.time_mix_value": "pytorch_model-00003-of-00003.bin",
287
+ "rwkv.blocks.22.attention.value.weight": "pytorch_model-00003-of-00003.bin",
288
+ "rwkv.blocks.22.feed_forward.key.weight": "pytorch_model-00003-of-00003.bin",
289
+ "rwkv.blocks.22.feed_forward.receptance.weight": "pytorch_model-00003-of-00003.bin",
290
+ "rwkv.blocks.22.feed_forward.time_mix_key": "pytorch_model-00003-of-00003.bin",
291
+ "rwkv.blocks.22.feed_forward.time_mix_receptance": "pytorch_model-00003-of-00003.bin",
292
+ "rwkv.blocks.22.feed_forward.value.weight": "pytorch_model-00003-of-00003.bin",
293
+ "rwkv.blocks.22.ln1.bias": "pytorch_model-00003-of-00003.bin",
294
+ "rwkv.blocks.22.ln1.weight": "pytorch_model-00003-of-00003.bin",
295
+ "rwkv.blocks.22.ln2.bias": "pytorch_model-00003-of-00003.bin",
296
+ "rwkv.blocks.22.ln2.weight": "pytorch_model-00003-of-00003.bin",
297
+ "rwkv.blocks.23.attention.key.weight": "pytorch_model-00003-of-00003.bin",
298
+ "rwkv.blocks.23.attention.output.weight": "pytorch_model-00003-of-00003.bin",
299
+ "rwkv.blocks.23.attention.receptance.weight": "pytorch_model-00003-of-00003.bin",
300
+ "rwkv.blocks.23.attention.time_decay": "pytorch_model-00003-of-00003.bin",
301
+ "rwkv.blocks.23.attention.time_first": "pytorch_model-00003-of-00003.bin",
302
+ "rwkv.blocks.23.attention.time_mix_key": "pytorch_model-00003-of-00003.bin",
303
+ "rwkv.blocks.23.attention.time_mix_receptance": "pytorch_model-00003-of-00003.bin",
304
+ "rwkv.blocks.23.attention.time_mix_value": "pytorch_model-00003-of-00003.bin",
305
+ "rwkv.blocks.23.attention.value.weight": "pytorch_model-00003-of-00003.bin",
306
+ "rwkv.blocks.23.feed_forward.key.weight": "pytorch_model-00003-of-00003.bin",
307
+ "rwkv.blocks.23.feed_forward.receptance.weight": "pytorch_model-00003-of-00003.bin",
308
+ "rwkv.blocks.23.feed_forward.time_mix_key": "pytorch_model-00003-of-00003.bin",
309
+ "rwkv.blocks.23.feed_forward.time_mix_receptance": "pytorch_model-00003-of-00003.bin",
310
+ "rwkv.blocks.23.feed_forward.value.weight": "pytorch_model-00003-of-00003.bin",
311
+ "rwkv.blocks.23.ln1.bias": "pytorch_model-00003-of-00003.bin",
312
+ "rwkv.blocks.23.ln1.weight": "pytorch_model-00003-of-00003.bin",
313
+ "rwkv.blocks.23.ln2.bias": "pytorch_model-00003-of-00003.bin",
314
+ "rwkv.blocks.23.ln2.weight": "pytorch_model-00003-of-00003.bin",
315
+ "rwkv.blocks.24.attention.key.weight": "pytorch_model-00003-of-00003.bin",
316
+ "rwkv.blocks.24.attention.output.weight": "pytorch_model-00003-of-00003.bin",
317
+ "rwkv.blocks.24.attention.receptance.weight": "pytorch_model-00003-of-00003.bin",
318
+ "rwkv.blocks.24.attention.time_decay": "pytorch_model-00003-of-00003.bin",
319
+ "rwkv.blocks.24.attention.time_first": "pytorch_model-00003-of-00003.bin",
320
+ "rwkv.blocks.24.attention.time_mix_key": "pytorch_model-00003-of-00003.bin",
321
+ "rwkv.blocks.24.attention.time_mix_receptance": "pytorch_model-00003-of-00003.bin",
322
+ "rwkv.blocks.24.attention.time_mix_value": "pytorch_model-00003-of-00003.bin",
323
+ "rwkv.blocks.24.attention.value.weight": "pytorch_model-00003-of-00003.bin",
324
+ "rwkv.blocks.24.feed_forward.key.weight": "pytorch_model-00003-of-00003.bin",
325
+ "rwkv.blocks.24.feed_forward.receptance.weight": "pytorch_model-00003-of-00003.bin",
326
+ "rwkv.blocks.24.feed_forward.time_mix_key": "pytorch_model-00003-of-00003.bin",
327
+ "rwkv.blocks.24.feed_forward.time_mix_receptance": "pytorch_model-00003-of-00003.bin",
328
+ "rwkv.blocks.24.feed_forward.value.weight": "pytorch_model-00003-of-00003.bin",
329
+ "rwkv.blocks.24.ln1.bias": "pytorch_model-00003-of-00003.bin",
330
+ "rwkv.blocks.24.ln1.weight": "pytorch_model-00003-of-00003.bin",
331
+ "rwkv.blocks.24.ln2.bias": "pytorch_model-00003-of-00003.bin",
332
+ "rwkv.blocks.24.ln2.weight": "pytorch_model-00003-of-00003.bin",
333
+ "rwkv.blocks.25.attention.key.weight": "pytorch_model-00003-of-00003.bin",
334
+ "rwkv.blocks.25.attention.output.weight": "pytorch_model-00003-of-00003.bin",
335
+ "rwkv.blocks.25.attention.receptance.weight": "pytorch_model-00003-of-00003.bin",
336
+ "rwkv.blocks.25.attention.time_decay": "pytorch_model-00003-of-00003.bin",
337
+ "rwkv.blocks.25.attention.time_first": "pytorch_model-00003-of-00003.bin",
338
+ "rwkv.blocks.25.attention.time_mix_key": "pytorch_model-00003-of-00003.bin",
339
+ "rwkv.blocks.25.attention.time_mix_receptance": "pytorch_model-00003-of-00003.bin",
340
+ "rwkv.blocks.25.attention.time_mix_value": "pytorch_model-00003-of-00003.bin",
341
+ "rwkv.blocks.25.attention.value.weight": "pytorch_model-00003-of-00003.bin",
342
+ "rwkv.blocks.25.feed_forward.key.weight": "pytorch_model-00003-of-00003.bin",
343
+ "rwkv.blocks.25.feed_forward.receptance.weight": "pytorch_model-00003-of-00003.bin",
344
+ "rwkv.blocks.25.feed_forward.time_mix_key": "pytorch_model-00003-of-00003.bin",
345
+ "rwkv.blocks.25.feed_forward.time_mix_receptance": "pytorch_model-00003-of-00003.bin",
346
+ "rwkv.blocks.25.feed_forward.value.weight": "pytorch_model-00003-of-00003.bin",
347
+ "rwkv.blocks.25.ln1.bias": "pytorch_model-00003-of-00003.bin",
348
+ "rwkv.blocks.25.ln1.weight": "pytorch_model-00003-of-00003.bin",
349
+ "rwkv.blocks.25.ln2.bias": "pytorch_model-00003-of-00003.bin",
350
+ "rwkv.blocks.25.ln2.weight": "pytorch_model-00003-of-00003.bin",
351
+ "rwkv.blocks.26.attention.key.weight": "pytorch_model-00003-of-00003.bin",
352
+ "rwkv.blocks.26.attention.output.weight": "pytorch_model-00003-of-00003.bin",
353
+ "rwkv.blocks.26.attention.receptance.weight": "pytorch_model-00003-of-00003.bin",
354
+ "rwkv.blocks.26.attention.time_decay": "pytorch_model-00003-of-00003.bin",
355
+ "rwkv.blocks.26.attention.time_first": "pytorch_model-00003-of-00003.bin",
356
+ "rwkv.blocks.26.attention.time_mix_key": "pytorch_model-00003-of-00003.bin",
357
+ "rwkv.blocks.26.attention.time_mix_receptance": "pytorch_model-00003-of-00003.bin",
358
+ "rwkv.blocks.26.attention.time_mix_value": "pytorch_model-00003-of-00003.bin",
359
+ "rwkv.blocks.26.attention.value.weight": "pytorch_model-00003-of-00003.bin",
360
+ "rwkv.blocks.26.feed_forward.key.weight": "pytorch_model-00003-of-00003.bin",
361
+ "rwkv.blocks.26.feed_forward.receptance.weight": "pytorch_model-00003-of-00003.bin",
362
+ "rwkv.blocks.26.feed_forward.time_mix_key": "pytorch_model-00003-of-00003.bin",
363
+ "rwkv.blocks.26.feed_forward.time_mix_receptance": "pytorch_model-00003-of-00003.bin",
364
+ "rwkv.blocks.26.feed_forward.value.weight": "pytorch_model-00003-of-00003.bin",
365
+ "rwkv.blocks.26.ln1.bias": "pytorch_model-00003-of-00003.bin",
366
+ "rwkv.blocks.26.ln1.weight": "pytorch_model-00003-of-00003.bin",
367
+ "rwkv.blocks.26.ln2.bias": "pytorch_model-00003-of-00003.bin",
368
+ "rwkv.blocks.26.ln2.weight": "pytorch_model-00003-of-00003.bin",
369
+ "rwkv.blocks.27.attention.key.weight": "pytorch_model-00003-of-00003.bin",
370
+ "rwkv.blocks.27.attention.output.weight": "pytorch_model-00003-of-00003.bin",
371
+ "rwkv.blocks.27.attention.receptance.weight": "pytorch_model-00003-of-00003.bin",
372
+ "rwkv.blocks.27.attention.time_decay": "pytorch_model-00003-of-00003.bin",
373
+ "rwkv.blocks.27.attention.time_first": "pytorch_model-00003-of-00003.bin",
374
+ "rwkv.blocks.27.attention.time_mix_key": "pytorch_model-00003-of-00003.bin",
375
+ "rwkv.blocks.27.attention.time_mix_receptance": "pytorch_model-00003-of-00003.bin",
376
+ "rwkv.blocks.27.attention.time_mix_value": "pytorch_model-00003-of-00003.bin",
377
+ "rwkv.blocks.27.attention.value.weight": "pytorch_model-00003-of-00003.bin",
378
+ "rwkv.blocks.27.feed_forward.key.weight": "pytorch_model-00003-of-00003.bin",
379
+ "rwkv.blocks.27.feed_forward.receptance.weight": "pytorch_model-00003-of-00003.bin",
380
+ "rwkv.blocks.27.feed_forward.time_mix_key": "pytorch_model-00003-of-00003.bin",
381
+ "rwkv.blocks.27.feed_forward.time_mix_receptance": "pytorch_model-00003-of-00003.bin",
382
+ "rwkv.blocks.27.feed_forward.value.weight": "pytorch_model-00003-of-00003.bin",
383
+ "rwkv.blocks.27.ln1.bias": "pytorch_model-00003-of-00003.bin",
384
+ "rwkv.blocks.27.ln1.weight": "pytorch_model-00003-of-00003.bin",
385
+ "rwkv.blocks.27.ln2.bias": "pytorch_model-00003-of-00003.bin",
386
+ "rwkv.blocks.27.ln2.weight": "pytorch_model-00003-of-00003.bin",
387
+ "rwkv.blocks.3.attention.key.weight": "pytorch_model-00001-of-00003.bin",
388
+ "rwkv.blocks.3.attention.output.weight": "pytorch_model-00001-of-00003.bin",
389
+ "rwkv.blocks.3.attention.receptance.weight": "pytorch_model-00001-of-00003.bin",
390
+ "rwkv.blocks.3.attention.time_decay": "pytorch_model-00001-of-00003.bin",
391
+ "rwkv.blocks.3.attention.time_first": "pytorch_model-00001-of-00003.bin",
392
+ "rwkv.blocks.3.attention.time_mix_key": "pytorch_model-00001-of-00003.bin",
393
+ "rwkv.blocks.3.attention.time_mix_receptance": "pytorch_model-00001-of-00003.bin",
394
+ "rwkv.blocks.3.attention.time_mix_value": "pytorch_model-00001-of-00003.bin",
395
+ "rwkv.blocks.3.attention.value.weight": "pytorch_model-00001-of-00003.bin",
396
+ "rwkv.blocks.3.feed_forward.key.weight": "pytorch_model-00001-of-00003.bin",
397
+ "rwkv.blocks.3.feed_forward.receptance.weight": "pytorch_model-00001-of-00003.bin",
398
+ "rwkv.blocks.3.feed_forward.time_mix_key": "pytorch_model-00001-of-00003.bin",
399
+ "rwkv.blocks.3.feed_forward.time_mix_receptance": "pytorch_model-00001-of-00003.bin",
400
+ "rwkv.blocks.3.feed_forward.value.weight": "pytorch_model-00001-of-00003.bin",
401
+ "rwkv.blocks.3.ln1.bias": "pytorch_model-00001-of-00003.bin",
402
+ "rwkv.blocks.3.ln1.weight": "pytorch_model-00001-of-00003.bin",
403
+ "rwkv.blocks.3.ln2.bias": "pytorch_model-00001-of-00003.bin",
404
+ "rwkv.blocks.3.ln2.weight": "pytorch_model-00001-of-00003.bin",
405
+ "rwkv.blocks.4.attention.key.weight": "pytorch_model-00001-of-00003.bin",
406
+ "rwkv.blocks.4.attention.output.weight": "pytorch_model-00001-of-00003.bin",
407
+ "rwkv.blocks.4.attention.receptance.weight": "pytorch_model-00001-of-00003.bin",
408
+ "rwkv.blocks.4.attention.time_decay": "pytorch_model-00001-of-00003.bin",
409
+ "rwkv.blocks.4.attention.time_first": "pytorch_model-00001-of-00003.bin",
410
+ "rwkv.blocks.4.attention.time_mix_key": "pytorch_model-00001-of-00003.bin",
411
+ "rwkv.blocks.4.attention.time_mix_receptance": "pytorch_model-00001-of-00003.bin",
412
+ "rwkv.blocks.4.attention.time_mix_value": "pytorch_model-00001-of-00003.bin",
413
+ "rwkv.blocks.4.attention.value.weight": "pytorch_model-00001-of-00003.bin",
414
+ "rwkv.blocks.4.feed_forward.key.weight": "pytorch_model-00001-of-00003.bin",
415
+ "rwkv.blocks.4.feed_forward.receptance.weight": "pytorch_model-00001-of-00003.bin",
416
+ "rwkv.blocks.4.feed_forward.time_mix_key": "pytorch_model-00001-of-00003.bin",
417
+ "rwkv.blocks.4.feed_forward.time_mix_receptance": "pytorch_model-00001-of-00003.bin",
418
+ "rwkv.blocks.4.feed_forward.value.weight": "pytorch_model-00001-of-00003.bin",
419
+ "rwkv.blocks.4.ln1.bias": "pytorch_model-00001-of-00003.bin",
420
+ "rwkv.blocks.4.ln1.weight": "pytorch_model-00001-of-00003.bin",
421
+ "rwkv.blocks.4.ln2.bias": "pytorch_model-00001-of-00003.bin",
422
+ "rwkv.blocks.4.ln2.weight": "pytorch_model-00001-of-00003.bin",
423
+ "rwkv.blocks.5.attention.key.weight": "pytorch_model-00001-of-00003.bin",
424
+ "rwkv.blocks.5.attention.output.weight": "pytorch_model-00001-of-00003.bin",
425
+ "rwkv.blocks.5.attention.receptance.weight": "pytorch_model-00001-of-00003.bin",
426
+ "rwkv.blocks.5.attention.time_decay": "pytorch_model-00001-of-00003.bin",
427
+ "rwkv.blocks.5.attention.time_first": "pytorch_model-00001-of-00003.bin",
428
+ "rwkv.blocks.5.attention.time_mix_key": "pytorch_model-00001-of-00003.bin",
429
+ "rwkv.blocks.5.attention.time_mix_receptance": "pytorch_model-00001-of-00003.bin",
430
+ "rwkv.blocks.5.attention.time_mix_value": "pytorch_model-00001-of-00003.bin",
431
+ "rwkv.blocks.5.attention.value.weight": "pytorch_model-00001-of-00003.bin",
432
+ "rwkv.blocks.5.feed_forward.key.weight": "pytorch_model-00001-of-00003.bin",
433
+ "rwkv.blocks.5.feed_forward.receptance.weight": "pytorch_model-00001-of-00003.bin",
434
+ "rwkv.blocks.5.feed_forward.time_mix_key": "pytorch_model-00001-of-00003.bin",
435
+ "rwkv.blocks.5.feed_forward.time_mix_receptance": "pytorch_model-00001-of-00003.bin",
436
+ "rwkv.blocks.5.feed_forward.value.weight": "pytorch_model-00001-of-00003.bin",
437
+ "rwkv.blocks.5.ln1.bias": "pytorch_model-00001-of-00003.bin",
438
+ "rwkv.blocks.5.ln1.weight": "pytorch_model-00001-of-00003.bin",
439
+ "rwkv.blocks.5.ln2.bias": "pytorch_model-00001-of-00003.bin",
440
+ "rwkv.blocks.5.ln2.weight": "pytorch_model-00001-of-00003.bin",
441
+ "rwkv.blocks.6.attention.key.weight": "pytorch_model-00001-of-00003.bin",
442
+ "rwkv.blocks.6.attention.output.weight": "pytorch_model-00001-of-00003.bin",
443
+ "rwkv.blocks.6.attention.receptance.weight": "pytorch_model-00001-of-00003.bin",
444
+ "rwkv.blocks.6.attention.time_decay": "pytorch_model-00001-of-00003.bin",
445
+ "rwkv.blocks.6.attention.time_first": "pytorch_model-00001-of-00003.bin",
446
+ "rwkv.blocks.6.attention.time_mix_key": "pytorch_model-00001-of-00003.bin",
447
+ "rwkv.blocks.6.attention.time_mix_receptance": "pytorch_model-00001-of-00003.bin",
448
+ "rwkv.blocks.6.attention.time_mix_value": "pytorch_model-00001-of-00003.bin",
449
+ "rwkv.blocks.6.attention.value.weight": "pytorch_model-00001-of-00003.bin",
450
+ "rwkv.blocks.6.feed_forward.key.weight": "pytorch_model-00001-of-00003.bin",
451
+ "rwkv.blocks.6.feed_forward.receptance.weight": "pytorch_model-00001-of-00003.bin",
452
+ "rwkv.blocks.6.feed_forward.time_mix_key": "pytorch_model-00001-of-00003.bin",
453
+ "rwkv.blocks.6.feed_forward.time_mix_receptance": "pytorch_model-00001-of-00003.bin",
454
+ "rwkv.blocks.6.feed_forward.value.weight": "pytorch_model-00001-of-00003.bin",
455
+ "rwkv.blocks.6.ln1.bias": "pytorch_model-00001-of-00003.bin",
456
+ "rwkv.blocks.6.ln1.weight": "pytorch_model-00001-of-00003.bin",
457
+ "rwkv.blocks.6.ln2.bias": "pytorch_model-00001-of-00003.bin",
458
+ "rwkv.blocks.6.ln2.weight": "pytorch_model-00001-of-00003.bin",
459
+ "rwkv.blocks.7.attention.key.weight": "pytorch_model-00001-of-00003.bin",
460
+ "rwkv.blocks.7.attention.output.weight": "pytorch_model-00001-of-00003.bin",
461
+ "rwkv.blocks.7.attention.receptance.weight": "pytorch_model-00001-of-00003.bin",
462
+ "rwkv.blocks.7.attention.time_decay": "pytorch_model-00001-of-00003.bin",
463
+ "rwkv.blocks.7.attention.time_first": "pytorch_model-00001-of-00003.bin",
464
+ "rwkv.blocks.7.attention.time_mix_key": "pytorch_model-00001-of-00003.bin",
465
+ "rwkv.blocks.7.attention.time_mix_receptance": "pytorch_model-00001-of-00003.bin",
466
+ "rwkv.blocks.7.attention.time_mix_value": "pytorch_model-00001-of-00003.bin",
467
+ "rwkv.blocks.7.attention.value.weight": "pytorch_model-00001-of-00003.bin",
468
+ "rwkv.blocks.7.feed_forward.key.weight": "pytorch_model-00001-of-00003.bin",
469
+ "rwkv.blocks.7.feed_forward.receptance.weight": "pytorch_model-00001-of-00003.bin",
470
+ "rwkv.blocks.7.feed_forward.time_mix_key": "pytorch_model-00001-of-00003.bin",
471
+ "rwkv.blocks.7.feed_forward.time_mix_receptance": "pytorch_model-00001-of-00003.bin",
472
+ "rwkv.blocks.7.feed_forward.value.weight": "pytorch_model-00001-of-00003.bin",
473
+ "rwkv.blocks.7.ln1.bias": "pytorch_model-00001-of-00003.bin",
474
+ "rwkv.blocks.7.ln1.weight": "pytorch_model-00001-of-00003.bin",
475
+ "rwkv.blocks.7.ln2.bias": "pytorch_model-00001-of-00003.bin",
476
+ "rwkv.blocks.7.ln2.weight": "pytorch_model-00001-of-00003.bin",
477
+ "rwkv.blocks.8.attention.key.weight": "pytorch_model-00001-of-00003.bin",
478
+ "rwkv.blocks.8.attention.output.weight": "pytorch_model-00001-of-00003.bin",
479
+ "rwkv.blocks.8.attention.receptance.weight": "pytorch_model-00001-of-00003.bin",
480
+ "rwkv.blocks.8.attention.time_decay": "pytorch_model-00001-of-00003.bin",
481
+ "rwkv.blocks.8.attention.time_first": "pytorch_model-00001-of-00003.bin",
482
+ "rwkv.blocks.8.attention.time_mix_key": "pytorch_model-00001-of-00003.bin",
483
+ "rwkv.blocks.8.attention.time_mix_receptance": "pytorch_model-00001-of-00003.bin",
484
+ "rwkv.blocks.8.attention.time_mix_value": "pytorch_model-00001-of-00003.bin",
485
+ "rwkv.blocks.8.attention.value.weight": "pytorch_model-00001-of-00003.bin",
486
+ "rwkv.blocks.8.feed_forward.key.weight": "pytorch_model-00001-of-00003.bin",
487
+ "rwkv.blocks.8.feed_forward.receptance.weight": "pytorch_model-00001-of-00003.bin",
488
+ "rwkv.blocks.8.feed_forward.time_mix_key": "pytorch_model-00001-of-00003.bin",
489
+ "rwkv.blocks.8.feed_forward.time_mix_receptance": "pytorch_model-00001-of-00003.bin",
490
+ "rwkv.blocks.8.feed_forward.value.weight": "pytorch_model-00001-of-00003.bin",
491
+ "rwkv.blocks.8.ln1.bias": "pytorch_model-00001-of-00003.bin",
492
+ "rwkv.blocks.8.ln1.weight": "pytorch_model-00001-of-00003.bin",
493
+ "rwkv.blocks.8.ln2.bias": "pytorch_model-00001-of-00003.bin",
494
+ "rwkv.blocks.8.ln2.weight": "pytorch_model-00001-of-00003.bin",
495
+ "rwkv.blocks.9.attention.key.weight": "pytorch_model-00001-of-00003.bin",
496
+ "rwkv.blocks.9.attention.output.weight": "pytorch_model-00001-of-00003.bin",
497
+ "rwkv.blocks.9.attention.receptance.weight": "pytorch_model-00001-of-00003.bin",
498
+ "rwkv.blocks.9.attention.time_decay": "pytorch_model-00001-of-00003.bin",
499
+ "rwkv.blocks.9.attention.time_first": "pytorch_model-00001-of-00003.bin",
500
+ "rwkv.blocks.9.attention.time_mix_key": "pytorch_model-00001-of-00003.bin",
501
+ "rwkv.blocks.9.attention.time_mix_receptance": "pytorch_model-00001-of-00003.bin",
502
+ "rwkv.blocks.9.attention.time_mix_value": "pytorch_model-00001-of-00003.bin",
503
+ "rwkv.blocks.9.attention.value.weight": "pytorch_model-00001-of-00003.bin",
504
+ "rwkv.blocks.9.feed_forward.key.weight": "pytorch_model-00001-of-00003.bin",
505
+ "rwkv.blocks.9.feed_forward.receptance.weight": "pytorch_model-00001-of-00003.bin",
506
+ "rwkv.blocks.9.feed_forward.time_mix_key": "pytorch_model-00001-of-00003.bin",
507
+ "rwkv.blocks.9.feed_forward.time_mix_receptance": "pytorch_model-00001-of-00003.bin",
508
+ "rwkv.blocks.9.feed_forward.value.weight": "pytorch_model-00001-of-00003.bin",
509
+ "rwkv.blocks.9.ln1.bias": "pytorch_model-00001-of-00003.bin",
510
+ "rwkv.blocks.9.ln1.weight": "pytorch_model-00001-of-00003.bin",
511
+ "rwkv.blocks.9.ln2.bias": "pytorch_model-00001-of-00003.bin",
512
+ "rwkv.blocks.9.ln2.weight": "pytorch_model-00001-of-00003.bin",
513
+ "rwkv.embeddings.weight": "pytorch_model-00001-of-00003.bin",
514
+ "rwkv.ln_out.bias": "pytorch_model-00003-of-00003.bin",
515
+ "rwkv.ln_out.weight": "pytorch_model-00003-of-00003.bin"
516
+ }
517
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<|sep|>",
3
+ "eos_token": "<|endoftext|>",
4
+ "pad_token": "<|endoftext|>"
5
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<|sep|>",
3
+ "clean_up_tokenization_spaces": true,
4
+ "eos_token": "<|endoftext|>",
5
+ "model_max_length": 1000000000000000019884624838656,
6
+ "pad_token": "<|endoftext|>",
7
+ "tokenizer_class": "PreTrainedTokenizerFast"
8
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "train_loss": 2.389765337578156,
4
+ "train_runtime": 86824.1392,
5
+ "train_samples": 3818,
6
+ "train_samples_per_second": 0.044,
7
+ "train_steps_per_second": 0.005
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.9994761655316919,
5
+ "global_step": 477,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.0,
12
+ "learning_rate": 1.9958071278825996e-05,
13
+ "loss": 2.9192,
14
+ "step": 1
15
+ },
16
+ {
17
+ "epoch": 1.0,
18
+ "step": 477,
19
+ "total_flos": 1.482031706973143e+17,
20
+ "train_loss": 2.389765337578156,
21
+ "train_runtime": 86824.1392,
22
+ "train_samples_per_second": 0.044,
23
+ "train_steps_per_second": 0.005
24
+ }
25
+ ],
26
+ "max_steps": 477,
27
+ "num_train_epochs": 1,
28
+ "total_flos": 1.482031706973143e+17,
29
+ "trial_name": null,
30
+ "trial_params": null
31
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7cb70b974e99bb8eab14d103cd4310fdb78bc492046313b35a4e160406e538a7
3
+ size 3963