patrickvonplaten commited on
Commit
eeec07f
1 Parent(s): e339731
README.md CHANGED
@@ -1,3 +1,61 @@
1
- ---
2
- license: apache-2.0
3
- ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ # Unofficial port of the 20B model from Unifying Language Learning Paradigms
3
+
4
+ requires transformers==4.20
5
+
6
+
7
+
8
+ # Loading the model
9
+
10
+ ```python
11
+ from transformers import T5ForConditionalGeneration, AutoTokenizer
12
+ model = T5ForConditionalGeneration.from_pretrained("Seledorn/ul2", low_cpu_mem_usage=True, torch_dtype=torch.bfloat16)
13
+ tokenizer = AutoTokenizer.from_pretrained("Seledorn/ul2")
14
+ ```
15
+ # Example usage
16
+
17
+
18
+ ```python
19
+ inps = ["""
20
+ Mr. and Mrs. Dursley, of number four, Privet Drive, <extra_id_0> the last people you'd expect to be involved in anything strange or mysterious, because they just didn't hold with such nonsense.
21
+
22
+ Mr. Dursley was the director of a firm called Grunnings, which made drills. He was a big, <extra_id_1>. Mrs. Dursley was thin and blonde and had nearly twice the usual amount of neck, which came in very useful as she spent so much of her time craning over garden fences, spying on the neighbours. The Dursleys had a small son called Dudley and in their opinion there was no finer boy anywhere.
23
+
24
+ The Dursleys had everything they wanted, but they also had a secret, and their greatest fear was that somebody would discover it. They didn't think they could bear it if anyone found out about the Potters. Mrs. Potter was Mrs. Dursley's sister, but they hadn't met for several years; in fact, Mrs. Dursley pretended she didn't have a sister, because her sister and her good-for-nothing husband were as unDursleyish as it was possible to be. The Dursleys shuddered to think what the neighbours would say if the Potters arrived in the street. The Dursleys knew that the Potters had a small son, too, but they had never even seen him. This boy was another good reason for keeping the Potters away; they didn't want Dudley mixing with a child like that."""
25
+ ]
26
+
27
+ Note use `[NLG]` for X-denoisers, `[NLU]` for R-denoisers and `[S2S]` for S-Denoisers.
28
+
29
+
30
+ model.cuda()
31
+ model.eval()
32
+
33
+ with torch.no_grad():
34
+ for inp in inps:
35
+ inputs = tokenizer(inp, return_tensors="pt").input_ids
36
+
37
+ inputs_ = inputs.cuda()
38
+ outputs = model.generate(inputs_, max_length = 200, do_sample=True, temperature = 0.9, num_return_sequences=4)
39
+ for output in outputs:
40
+ out = tokenizer.decode(output)
41
+
42
+ inps = re.split(pattern, inp)
43
+ outs = re.split(pattern, out)
44
+
45
+ l = [z for (x,y) in zip(inps, outs[1:len(inps)]+ [""]) for z in (x,"*"+y+"*" if y != "" else "")]
46
+ print("".join(l))
47
+ print("-------------------------------")
48
+ ```
49
+
50
+
51
+ Example output
52
+
53
+ Mr. and Mrs. Dursley, of number four, Privet Drive, **were** the last people you'd expect to be involved in anything strange or mysterious, because they just didn't hold with such nonsense.
54
+
55
+ Mr. Dursley was the director of a firm called Grunnings, which made drills. He was a big, **solid man with a short, brown beard, an enormous head full of brains and a round, fat face. He had a voice, too, that was so deep that it was nearly always accompanied by a slight tremor..**. Mrs. Dursley was thin and blonde and had nearly twice the usual amount of neck, which came in very useful as she spent so much of her time craning over garden fences, spying on the neighbours. The Dursleys had a small son called Dudley and in their opinion there was no finer boy anywhere.
56
+
57
+ The Dursleys had everything they wanted, but they also had a secret, and their greatest fear was that somebody would discover it. They didn't think they could bear it if anyone found out about the Potters. Mrs. Potter was Mrs. Dursley's sister, but they hadn't met for several years; in fact, Mrs. Dursley pretended she didn't have a sister, because her sister and her good-for-nothing husband were as unDursleyish as it was possible to be. The Dursleys shuddered to think what the neighbours would say if the Potters arrived in the street. The Dursleys knew that the Potters had a small son, too, but they had never even seen him. This boy was another good reason for keeping the Potters away; they didn't want Dudley mixing with a child like that.
58
+
59
+ Where bold is the completion of the model.
60
+
61
+
added_tokens.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"[new_id_17]": 32117, "[new_id_20]": 32120, "[new_id_13]": 32113, "[new_id_2]": 32102, "[new_id_16]": 32116, "[new_id_7]": 32107, "[new_id_5]": 32105, "[new_id_1]": 32101, "[new_id_15]": 32115, "[new_id_12]": 32112, "[new_id_0]": 32100, "[new_id_11]": 32111, "[new_id_25]": 32125, "[new_id_24]": 32124, "[new_id_10]": 32110, "[new_id_27]": 32127, "[new_id_23]": 32123, "[new_id_14]": 32114, "[new_id_22]": 32122, "[new_id_21]": 32121, "[new_id_19]": 32119, "[new_id_3]": 32103, "[new_id_4]": 32104, "[new_id_18]": 32118, "[new_id_9]": 32109, "[new_id_8]": 32108, "[new_id_26]": 32126, "[new_id_6]": 32106}
config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "ul2_model",
3
+ "architectures": [
4
+ "T5ForConditionalGeneration"
5
+ ],
6
+ "d_ff": 16384,
7
+ "d_kv": 256,
8
+ "d_model": 4096,
9
+ "decoder_start_token_id": 0,
10
+ "dense_act_fn": "silu",
11
+ "dropout_rate": 0.1,
12
+ "eos_token_id": 1,
13
+ "feed_forward_proj": "gated-silu",
14
+ "initializer_factor": 1.0,
15
+ "is_encoder_decoder": true,
16
+ "is_gated_act": true,
17
+ "layer_norm_epsilon": 1e-06,
18
+ "model_type": "t5",
19
+ "n_positions": 512,
20
+ "num_decoder_layers": 32,
21
+ "num_heads": 16,
22
+ "num_layers": 32,
23
+ "output_past": true,
24
+ "pad_token_id": 0,
25
+ "relative_attention_max_distance": 128,
26
+ "relative_attention_num_buckets": 32,
27
+ "torch_dtype": "bfloat16",
28
+ "transformers_version": "4.20.0.dev0",
29
+ "use_cache": true,
30
+ "vocab_size": 32128
31
+ }
pytorch_model-00001-of-00004.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6226f933c6950d796635e243250c47fca09411a8a540903064708301b7ab8b64
3
+ size 9658776767
pytorch_model-00002-of-00004.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:289235de6beafb7c9cbf145f8b54e183bb7cb681c74438807250584c1606fe6f
3
+ size 9927240513
pytorch_model-00003-of-00004.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83c197cfd5d5a61ee159ea101a22e3fa61861a0d94ee19cabb49648a34061a2f
3
+ size 9932552699
pytorch_model-00004-of-00004.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e2c3713a749f368d6d5465a6bf38d524de7f192b9794e20dbc43d094bac3d36
3
+ size 9927298907
pytorch_model.bin.index.json ADDED
@@ -0,0 +1,751 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 39708805120
4
+ },
5
+ "weight_map": {
6
+ "decoder.block.0.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00004.bin",
7
+ "decoder.block.0.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00004.bin",
8
+ "decoder.block.0.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00004.bin",
9
+ "decoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "pytorch_model-00002-of-00004.bin",
10
+ "decoder.block.0.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00004.bin",
11
+ "decoder.block.0.layer.0.layer_norm.weight": "pytorch_model-00002-of-00004.bin",
12
+ "decoder.block.0.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00004.bin",
13
+ "decoder.block.0.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00004.bin",
14
+ "decoder.block.0.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00004.bin",
15
+ "decoder.block.0.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00004.bin",
16
+ "decoder.block.0.layer.1.layer_norm.weight": "pytorch_model-00002-of-00004.bin",
17
+ "decoder.block.0.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00004.bin",
18
+ "decoder.block.0.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00004.bin",
19
+ "decoder.block.0.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00004.bin",
20
+ "decoder.block.0.layer.2.layer_norm.weight": "pytorch_model-00002-of-00004.bin",
21
+ "decoder.block.1.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00004.bin",
22
+ "decoder.block.1.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00004.bin",
23
+ "decoder.block.1.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00004.bin",
24
+ "decoder.block.1.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00004.bin",
25
+ "decoder.block.1.layer.0.layer_norm.weight": "pytorch_model-00002-of-00004.bin",
26
+ "decoder.block.1.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00004.bin",
27
+ "decoder.block.1.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00004.bin",
28
+ "decoder.block.1.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00004.bin",
29
+ "decoder.block.1.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00004.bin",
30
+ "decoder.block.1.layer.1.layer_norm.weight": "pytorch_model-00002-of-00004.bin",
31
+ "decoder.block.1.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00004.bin",
32
+ "decoder.block.1.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00004.bin",
33
+ "decoder.block.1.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00004.bin",
34
+ "decoder.block.1.layer.2.layer_norm.weight": "pytorch_model-00002-of-00004.bin",
35
+ "decoder.block.10.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00004.bin",
36
+ "decoder.block.10.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00004.bin",
37
+ "decoder.block.10.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00004.bin",
38
+ "decoder.block.10.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00004.bin",
39
+ "decoder.block.10.layer.0.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
40
+ "decoder.block.10.layer.1.EncDecAttention.k.weight": "pytorch_model-00003-of-00004.bin",
41
+ "decoder.block.10.layer.1.EncDecAttention.o.weight": "pytorch_model-00003-of-00004.bin",
42
+ "decoder.block.10.layer.1.EncDecAttention.q.weight": "pytorch_model-00003-of-00004.bin",
43
+ "decoder.block.10.layer.1.EncDecAttention.v.weight": "pytorch_model-00003-of-00004.bin",
44
+ "decoder.block.10.layer.1.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
45
+ "decoder.block.10.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00003-of-00004.bin",
46
+ "decoder.block.10.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00003-of-00004.bin",
47
+ "decoder.block.10.layer.2.DenseReluDense.wo.weight": "pytorch_model-00003-of-00004.bin",
48
+ "decoder.block.10.layer.2.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
49
+ "decoder.block.11.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00004.bin",
50
+ "decoder.block.11.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00004.bin",
51
+ "decoder.block.11.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00004.bin",
52
+ "decoder.block.11.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00004.bin",
53
+ "decoder.block.11.layer.0.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
54
+ "decoder.block.11.layer.1.EncDecAttention.k.weight": "pytorch_model-00003-of-00004.bin",
55
+ "decoder.block.11.layer.1.EncDecAttention.o.weight": "pytorch_model-00003-of-00004.bin",
56
+ "decoder.block.11.layer.1.EncDecAttention.q.weight": "pytorch_model-00003-of-00004.bin",
57
+ "decoder.block.11.layer.1.EncDecAttention.v.weight": "pytorch_model-00003-of-00004.bin",
58
+ "decoder.block.11.layer.1.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
59
+ "decoder.block.11.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00003-of-00004.bin",
60
+ "decoder.block.11.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00003-of-00004.bin",
61
+ "decoder.block.11.layer.2.DenseReluDense.wo.weight": "pytorch_model-00003-of-00004.bin",
62
+ "decoder.block.11.layer.2.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
63
+ "decoder.block.12.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00004.bin",
64
+ "decoder.block.12.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00004.bin",
65
+ "decoder.block.12.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00004.bin",
66
+ "decoder.block.12.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00004.bin",
67
+ "decoder.block.12.layer.0.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
68
+ "decoder.block.12.layer.1.EncDecAttention.k.weight": "pytorch_model-00003-of-00004.bin",
69
+ "decoder.block.12.layer.1.EncDecAttention.o.weight": "pytorch_model-00003-of-00004.bin",
70
+ "decoder.block.12.layer.1.EncDecAttention.q.weight": "pytorch_model-00003-of-00004.bin",
71
+ "decoder.block.12.layer.1.EncDecAttention.v.weight": "pytorch_model-00003-of-00004.bin",
72
+ "decoder.block.12.layer.1.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
73
+ "decoder.block.12.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00003-of-00004.bin",
74
+ "decoder.block.12.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00003-of-00004.bin",
75
+ "decoder.block.12.layer.2.DenseReluDense.wo.weight": "pytorch_model-00003-of-00004.bin",
76
+ "decoder.block.12.layer.2.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
77
+ "decoder.block.13.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00004.bin",
78
+ "decoder.block.13.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00004.bin",
79
+ "decoder.block.13.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00004.bin",
80
+ "decoder.block.13.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00004.bin",
81
+ "decoder.block.13.layer.0.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
82
+ "decoder.block.13.layer.1.EncDecAttention.k.weight": "pytorch_model-00003-of-00004.bin",
83
+ "decoder.block.13.layer.1.EncDecAttention.o.weight": "pytorch_model-00003-of-00004.bin",
84
+ "decoder.block.13.layer.1.EncDecAttention.q.weight": "pytorch_model-00003-of-00004.bin",
85
+ "decoder.block.13.layer.1.EncDecAttention.v.weight": "pytorch_model-00003-of-00004.bin",
86
+ "decoder.block.13.layer.1.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
87
+ "decoder.block.13.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00003-of-00004.bin",
88
+ "decoder.block.13.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00003-of-00004.bin",
89
+ "decoder.block.13.layer.2.DenseReluDense.wo.weight": "pytorch_model-00003-of-00004.bin",
90
+ "decoder.block.13.layer.2.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
91
+ "decoder.block.14.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00004.bin",
92
+ "decoder.block.14.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00004.bin",
93
+ "decoder.block.14.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00004.bin",
94
+ "decoder.block.14.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00004.bin",
95
+ "decoder.block.14.layer.0.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
96
+ "decoder.block.14.layer.1.EncDecAttention.k.weight": "pytorch_model-00003-of-00004.bin",
97
+ "decoder.block.14.layer.1.EncDecAttention.o.weight": "pytorch_model-00003-of-00004.bin",
98
+ "decoder.block.14.layer.1.EncDecAttention.q.weight": "pytorch_model-00003-of-00004.bin",
99
+ "decoder.block.14.layer.1.EncDecAttention.v.weight": "pytorch_model-00003-of-00004.bin",
100
+ "decoder.block.14.layer.1.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
101
+ "decoder.block.14.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00003-of-00004.bin",
102
+ "decoder.block.14.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00003-of-00004.bin",
103
+ "decoder.block.14.layer.2.DenseReluDense.wo.weight": "pytorch_model-00003-of-00004.bin",
104
+ "decoder.block.14.layer.2.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
105
+ "decoder.block.15.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00004.bin",
106
+ "decoder.block.15.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00004.bin",
107
+ "decoder.block.15.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00004.bin",
108
+ "decoder.block.15.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00004.bin",
109
+ "decoder.block.15.layer.0.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
110
+ "decoder.block.15.layer.1.EncDecAttention.k.weight": "pytorch_model-00003-of-00004.bin",
111
+ "decoder.block.15.layer.1.EncDecAttention.o.weight": "pytorch_model-00003-of-00004.bin",
112
+ "decoder.block.15.layer.1.EncDecAttention.q.weight": "pytorch_model-00003-of-00004.bin",
113
+ "decoder.block.15.layer.1.EncDecAttention.v.weight": "pytorch_model-00003-of-00004.bin",
114
+ "decoder.block.15.layer.1.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
115
+ "decoder.block.15.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00003-of-00004.bin",
116
+ "decoder.block.15.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00003-of-00004.bin",
117
+ "decoder.block.15.layer.2.DenseReluDense.wo.weight": "pytorch_model-00003-of-00004.bin",
118
+ "decoder.block.15.layer.2.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
119
+ "decoder.block.16.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00004.bin",
120
+ "decoder.block.16.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00004.bin",
121
+ "decoder.block.16.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00004.bin",
122
+ "decoder.block.16.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00004.bin",
123
+ "decoder.block.16.layer.0.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
124
+ "decoder.block.16.layer.1.EncDecAttention.k.weight": "pytorch_model-00003-of-00004.bin",
125
+ "decoder.block.16.layer.1.EncDecAttention.o.weight": "pytorch_model-00003-of-00004.bin",
126
+ "decoder.block.16.layer.1.EncDecAttention.q.weight": "pytorch_model-00003-of-00004.bin",
127
+ "decoder.block.16.layer.1.EncDecAttention.v.weight": "pytorch_model-00003-of-00004.bin",
128
+ "decoder.block.16.layer.1.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
129
+ "decoder.block.16.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00003-of-00004.bin",
130
+ "decoder.block.16.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00003-of-00004.bin",
131
+ "decoder.block.16.layer.2.DenseReluDense.wo.weight": "pytorch_model-00003-of-00004.bin",
132
+ "decoder.block.16.layer.2.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
133
+ "decoder.block.17.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00004.bin",
134
+ "decoder.block.17.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00004.bin",
135
+ "decoder.block.17.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00004.bin",
136
+ "decoder.block.17.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00004.bin",
137
+ "decoder.block.17.layer.0.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
138
+ "decoder.block.17.layer.1.EncDecAttention.k.weight": "pytorch_model-00003-of-00004.bin",
139
+ "decoder.block.17.layer.1.EncDecAttention.o.weight": "pytorch_model-00003-of-00004.bin",
140
+ "decoder.block.17.layer.1.EncDecAttention.q.weight": "pytorch_model-00003-of-00004.bin",
141
+ "decoder.block.17.layer.1.EncDecAttention.v.weight": "pytorch_model-00003-of-00004.bin",
142
+ "decoder.block.17.layer.1.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
143
+ "decoder.block.17.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00003-of-00004.bin",
144
+ "decoder.block.17.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00004-of-00004.bin",
145
+ "decoder.block.17.layer.2.DenseReluDense.wo.weight": "pytorch_model-00004-of-00004.bin",
146
+ "decoder.block.17.layer.2.layer_norm.weight": "pytorch_model-00004-of-00004.bin",
147
+ "decoder.block.18.layer.0.SelfAttention.k.weight": "pytorch_model-00004-of-00004.bin",
148
+ "decoder.block.18.layer.0.SelfAttention.o.weight": "pytorch_model-00004-of-00004.bin",
149
+ "decoder.block.18.layer.0.SelfAttention.q.weight": "pytorch_model-00004-of-00004.bin",
150
+ "decoder.block.18.layer.0.SelfAttention.v.weight": "pytorch_model-00004-of-00004.bin",
151
+ "decoder.block.18.layer.0.layer_norm.weight": "pytorch_model-00004-of-00004.bin",
152
+ "decoder.block.18.layer.1.EncDecAttention.k.weight": "pytorch_model-00004-of-00004.bin",
153
+ "decoder.block.18.layer.1.EncDecAttention.o.weight": "pytorch_model-00004-of-00004.bin",
154
+ "decoder.block.18.layer.1.EncDecAttention.q.weight": "pytorch_model-00004-of-00004.bin",
155
+ "decoder.block.18.layer.1.EncDecAttention.v.weight": "pytorch_model-00004-of-00004.bin",
156
+ "decoder.block.18.layer.1.layer_norm.weight": "pytorch_model-00004-of-00004.bin",
157
+ "decoder.block.18.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00004-of-00004.bin",
158
+ "decoder.block.18.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00004-of-00004.bin",
159
+ "decoder.block.18.layer.2.DenseReluDense.wo.weight": "pytorch_model-00004-of-00004.bin",
160
+ "decoder.block.18.layer.2.layer_norm.weight": "pytorch_model-00004-of-00004.bin",
161
+ "decoder.block.19.layer.0.SelfAttention.k.weight": "pytorch_model-00004-of-00004.bin",
162
+ "decoder.block.19.layer.0.SelfAttention.o.weight": "pytorch_model-00004-of-00004.bin",
163
+ "decoder.block.19.layer.0.SelfAttention.q.weight": "pytorch_model-00004-of-00004.bin",
164
+ "decoder.block.19.layer.0.SelfAttention.v.weight": "pytorch_model-00004-of-00004.bin",
165
+ "decoder.block.19.layer.0.layer_norm.weight": "pytorch_model-00004-of-00004.bin",
166
+ "decoder.block.19.layer.1.EncDecAttention.k.weight": "pytorch_model-00004-of-00004.bin",
167
+ "decoder.block.19.layer.1.EncDecAttention.o.weight": "pytorch_model-00004-of-00004.bin",
168
+ "decoder.block.19.layer.1.EncDecAttention.q.weight": "pytorch_model-00004-of-00004.bin",
169
+ "decoder.block.19.layer.1.EncDecAttention.v.weight": "pytorch_model-00004-of-00004.bin",
170
+ "decoder.block.19.layer.1.layer_norm.weight": "pytorch_model-00004-of-00004.bin",
171
+ "decoder.block.19.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00004-of-00004.bin",
172
+ "decoder.block.19.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00004-of-00004.bin",
173
+ "decoder.block.19.layer.2.DenseReluDense.wo.weight": "pytorch_model-00004-of-00004.bin",
174
+ "decoder.block.19.layer.2.layer_norm.weight": "pytorch_model-00004-of-00004.bin",
175
+ "decoder.block.2.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00004.bin",
176
+ "decoder.block.2.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00004.bin",
177
+ "decoder.block.2.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00004.bin",
178
+ "decoder.block.2.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00004.bin",
179
+ "decoder.block.2.layer.0.layer_norm.weight": "pytorch_model-00002-of-00004.bin",
180
+ "decoder.block.2.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00004.bin",
181
+ "decoder.block.2.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00004.bin",
182
+ "decoder.block.2.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00004.bin",
183
+ "decoder.block.2.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00004.bin",
184
+ "decoder.block.2.layer.1.layer_norm.weight": "pytorch_model-00002-of-00004.bin",
185
+ "decoder.block.2.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00004.bin",
186
+ "decoder.block.2.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00004.bin",
187
+ "decoder.block.2.layer.2.DenseReluDense.wo.weight": "pytorch_model-00003-of-00004.bin",
188
+ "decoder.block.2.layer.2.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
189
+ "decoder.block.20.layer.0.SelfAttention.k.weight": "pytorch_model-00004-of-00004.bin",
190
+ "decoder.block.20.layer.0.SelfAttention.o.weight": "pytorch_model-00004-of-00004.bin",
191
+ "decoder.block.20.layer.0.SelfAttention.q.weight": "pytorch_model-00004-of-00004.bin",
192
+ "decoder.block.20.layer.0.SelfAttention.v.weight": "pytorch_model-00004-of-00004.bin",
193
+ "decoder.block.20.layer.0.layer_norm.weight": "pytorch_model-00004-of-00004.bin",
194
+ "decoder.block.20.layer.1.EncDecAttention.k.weight": "pytorch_model-00004-of-00004.bin",
195
+ "decoder.block.20.layer.1.EncDecAttention.o.weight": "pytorch_model-00004-of-00004.bin",
196
+ "decoder.block.20.layer.1.EncDecAttention.q.weight": "pytorch_model-00004-of-00004.bin",
197
+ "decoder.block.20.layer.1.EncDecAttention.v.weight": "pytorch_model-00004-of-00004.bin",
198
+ "decoder.block.20.layer.1.layer_norm.weight": "pytorch_model-00004-of-00004.bin",
199
+ "decoder.block.20.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00004-of-00004.bin",
200
+ "decoder.block.20.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00004-of-00004.bin",
201
+ "decoder.block.20.layer.2.DenseReluDense.wo.weight": "pytorch_model-00004-of-00004.bin",
202
+ "decoder.block.20.layer.2.layer_norm.weight": "pytorch_model-00004-of-00004.bin",
203
+ "decoder.block.21.layer.0.SelfAttention.k.weight": "pytorch_model-00004-of-00004.bin",
204
+ "decoder.block.21.layer.0.SelfAttention.o.weight": "pytorch_model-00004-of-00004.bin",
205
+ "decoder.block.21.layer.0.SelfAttention.q.weight": "pytorch_model-00004-of-00004.bin",
206
+ "decoder.block.21.layer.0.SelfAttention.v.weight": "pytorch_model-00004-of-00004.bin",
207
+ "decoder.block.21.layer.0.layer_norm.weight": "pytorch_model-00004-of-00004.bin",
208
+ "decoder.block.21.layer.1.EncDecAttention.k.weight": "pytorch_model-00004-of-00004.bin",
209
+ "decoder.block.21.layer.1.EncDecAttention.o.weight": "pytorch_model-00004-of-00004.bin",
210
+ "decoder.block.21.layer.1.EncDecAttention.q.weight": "pytorch_model-00004-of-00004.bin",
211
+ "decoder.block.21.layer.1.EncDecAttention.v.weight": "pytorch_model-00004-of-00004.bin",
212
+ "decoder.block.21.layer.1.layer_norm.weight": "pytorch_model-00004-of-00004.bin",
213
+ "decoder.block.21.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00004-of-00004.bin",
214
+ "decoder.block.21.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00004-of-00004.bin",
215
+ "decoder.block.21.layer.2.DenseReluDense.wo.weight": "pytorch_model-00004-of-00004.bin",
216
+ "decoder.block.21.layer.2.layer_norm.weight": "pytorch_model-00004-of-00004.bin",
217
+ "decoder.block.22.layer.0.SelfAttention.k.weight": "pytorch_model-00004-of-00004.bin",
218
+ "decoder.block.22.layer.0.SelfAttention.o.weight": "pytorch_model-00004-of-00004.bin",
219
+ "decoder.block.22.layer.0.SelfAttention.q.weight": "pytorch_model-00004-of-00004.bin",
220
+ "decoder.block.22.layer.0.SelfAttention.v.weight": "pytorch_model-00004-of-00004.bin",
221
+ "decoder.block.22.layer.0.layer_norm.weight": "pytorch_model-00004-of-00004.bin",
222
+ "decoder.block.22.layer.1.EncDecAttention.k.weight": "pytorch_model-00004-of-00004.bin",
223
+ "decoder.block.22.layer.1.EncDecAttention.o.weight": "pytorch_model-00004-of-00004.bin",
224
+ "decoder.block.22.layer.1.EncDecAttention.q.weight": "pytorch_model-00004-of-00004.bin",
225
+ "decoder.block.22.layer.1.EncDecAttention.v.weight": "pytorch_model-00004-of-00004.bin",
226
+ "decoder.block.22.layer.1.layer_norm.weight": "pytorch_model-00004-of-00004.bin",
227
+ "decoder.block.22.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00004-of-00004.bin",
228
+ "decoder.block.22.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00004-of-00004.bin",
229
+ "decoder.block.22.layer.2.DenseReluDense.wo.weight": "pytorch_model-00004-of-00004.bin",
230
+ "decoder.block.22.layer.2.layer_norm.weight": "pytorch_model-00004-of-00004.bin",
231
+ "decoder.block.23.layer.0.SelfAttention.k.weight": "pytorch_model-00004-of-00004.bin",
232
+ "decoder.block.23.layer.0.SelfAttention.o.weight": "pytorch_model-00004-of-00004.bin",
233
+ "decoder.block.23.layer.0.SelfAttention.q.weight": "pytorch_model-00004-of-00004.bin",
234
+ "decoder.block.23.layer.0.SelfAttention.v.weight": "pytorch_model-00004-of-00004.bin",
235
+ "decoder.block.23.layer.0.layer_norm.weight": "pytorch_model-00004-of-00004.bin",
236
+ "decoder.block.23.layer.1.EncDecAttention.k.weight": "pytorch_model-00004-of-00004.bin",
237
+ "decoder.block.23.layer.1.EncDecAttention.o.weight": "pytorch_model-00004-of-00004.bin",
238
+ "decoder.block.23.layer.1.EncDecAttention.q.weight": "pytorch_model-00004-of-00004.bin",
239
+ "decoder.block.23.layer.1.EncDecAttention.v.weight": "pytorch_model-00004-of-00004.bin",
240
+ "decoder.block.23.layer.1.layer_norm.weight": "pytorch_model-00004-of-00004.bin",
241
+ "decoder.block.23.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00004-of-00004.bin",
242
+ "decoder.block.23.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00004-of-00004.bin",
243
+ "decoder.block.23.layer.2.DenseReluDense.wo.weight": "pytorch_model-00004-of-00004.bin",
244
+ "decoder.block.23.layer.2.layer_norm.weight": "pytorch_model-00004-of-00004.bin",
245
+ "decoder.block.24.layer.0.SelfAttention.k.weight": "pytorch_model-00004-of-00004.bin",
246
+ "decoder.block.24.layer.0.SelfAttention.o.weight": "pytorch_model-00004-of-00004.bin",
247
+ "decoder.block.24.layer.0.SelfAttention.q.weight": "pytorch_model-00004-of-00004.bin",
248
+ "decoder.block.24.layer.0.SelfAttention.v.weight": "pytorch_model-00004-of-00004.bin",
249
+ "decoder.block.24.layer.0.layer_norm.weight": "pytorch_model-00004-of-00004.bin",
250
+ "decoder.block.24.layer.1.EncDecAttention.k.weight": "pytorch_model-00004-of-00004.bin",
251
+ "decoder.block.24.layer.1.EncDecAttention.o.weight": "pytorch_model-00004-of-00004.bin",
252
+ "decoder.block.24.layer.1.EncDecAttention.q.weight": "pytorch_model-00004-of-00004.bin",
253
+ "decoder.block.24.layer.1.EncDecAttention.v.weight": "pytorch_model-00004-of-00004.bin",
254
+ "decoder.block.24.layer.1.layer_norm.weight": "pytorch_model-00004-of-00004.bin",
255
+ "decoder.block.24.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00004-of-00004.bin",
256
+ "decoder.block.24.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00004-of-00004.bin",
257
+ "decoder.block.24.layer.2.DenseReluDense.wo.weight": "pytorch_model-00004-of-00004.bin",
258
+ "decoder.block.24.layer.2.layer_norm.weight": "pytorch_model-00004-of-00004.bin",
259
+ "decoder.block.25.layer.0.SelfAttention.k.weight": "pytorch_model-00004-of-00004.bin",
260
+ "decoder.block.25.layer.0.SelfAttention.o.weight": "pytorch_model-00004-of-00004.bin",
261
+ "decoder.block.25.layer.0.SelfAttention.q.weight": "pytorch_model-00004-of-00004.bin",
262
+ "decoder.block.25.layer.0.SelfAttention.v.weight": "pytorch_model-00004-of-00004.bin",
263
+ "decoder.block.25.layer.0.layer_norm.weight": "pytorch_model-00004-of-00004.bin",
264
+ "decoder.block.25.layer.1.EncDecAttention.k.weight": "pytorch_model-00004-of-00004.bin",
265
+ "decoder.block.25.layer.1.EncDecAttention.o.weight": "pytorch_model-00004-of-00004.bin",
266
+ "decoder.block.25.layer.1.EncDecAttention.q.weight": "pytorch_model-00004-of-00004.bin",
267
+ "decoder.block.25.layer.1.EncDecAttention.v.weight": "pytorch_model-00004-of-00004.bin",
268
+ "decoder.block.25.layer.1.layer_norm.weight": "pytorch_model-00004-of-00004.bin",
269
+ "decoder.block.25.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00004-of-00004.bin",
270
+ "decoder.block.25.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00004-of-00004.bin",
271
+ "decoder.block.25.layer.2.DenseReluDense.wo.weight": "pytorch_model-00004-of-00004.bin",
272
+ "decoder.block.25.layer.2.layer_norm.weight": "pytorch_model-00004-of-00004.bin",
273
+ "decoder.block.26.layer.0.SelfAttention.k.weight": "pytorch_model-00004-of-00004.bin",
274
+ "decoder.block.26.layer.0.SelfAttention.o.weight": "pytorch_model-00004-of-00004.bin",
275
+ "decoder.block.26.layer.0.SelfAttention.q.weight": "pytorch_model-00004-of-00004.bin",
276
+ "decoder.block.26.layer.0.SelfAttention.v.weight": "pytorch_model-00004-of-00004.bin",
277
+ "decoder.block.26.layer.0.layer_norm.weight": "pytorch_model-00004-of-00004.bin",
278
+ "decoder.block.26.layer.1.EncDecAttention.k.weight": "pytorch_model-00004-of-00004.bin",
279
+ "decoder.block.26.layer.1.EncDecAttention.o.weight": "pytorch_model-00004-of-00004.bin",
280
+ "decoder.block.26.layer.1.EncDecAttention.q.weight": "pytorch_model-00004-of-00004.bin",
281
+ "decoder.block.26.layer.1.EncDecAttention.v.weight": "pytorch_model-00004-of-00004.bin",
282
+ "decoder.block.26.layer.1.layer_norm.weight": "pytorch_model-00004-of-00004.bin",
283
+ "decoder.block.26.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00004-of-00004.bin",
284
+ "decoder.block.26.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00004-of-00004.bin",
285
+ "decoder.block.26.layer.2.DenseReluDense.wo.weight": "pytorch_model-00004-of-00004.bin",
286
+ "decoder.block.26.layer.2.layer_norm.weight": "pytorch_model-00004-of-00004.bin",
287
+ "decoder.block.27.layer.0.SelfAttention.k.weight": "pytorch_model-00004-of-00004.bin",
288
+ "decoder.block.27.layer.0.SelfAttention.o.weight": "pytorch_model-00004-of-00004.bin",
289
+ "decoder.block.27.layer.0.SelfAttention.q.weight": "pytorch_model-00004-of-00004.bin",
290
+ "decoder.block.27.layer.0.SelfAttention.v.weight": "pytorch_model-00004-of-00004.bin",
291
+ "decoder.block.27.layer.0.layer_norm.weight": "pytorch_model-00004-of-00004.bin",
292
+ "decoder.block.27.layer.1.EncDecAttention.k.weight": "pytorch_model-00004-of-00004.bin",
293
+ "decoder.block.27.layer.1.EncDecAttention.o.weight": "pytorch_model-00004-of-00004.bin",
294
+ "decoder.block.27.layer.1.EncDecAttention.q.weight": "pytorch_model-00004-of-00004.bin",
295
+ "decoder.block.27.layer.1.EncDecAttention.v.weight": "pytorch_model-00004-of-00004.bin",
296
+ "decoder.block.27.layer.1.layer_norm.weight": "pytorch_model-00004-of-00004.bin",
297
+ "decoder.block.27.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00004-of-00004.bin",
298
+ "decoder.block.27.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00004-of-00004.bin",
299
+ "decoder.block.27.layer.2.DenseReluDense.wo.weight": "pytorch_model-00004-of-00004.bin",
300
+ "decoder.block.27.layer.2.layer_norm.weight": "pytorch_model-00004-of-00004.bin",
301
+ "decoder.block.28.layer.0.SelfAttention.k.weight": "pytorch_model-00004-of-00004.bin",
302
+ "decoder.block.28.layer.0.SelfAttention.o.weight": "pytorch_model-00004-of-00004.bin",
303
+ "decoder.block.28.layer.0.SelfAttention.q.weight": "pytorch_model-00004-of-00004.bin",
304
+ "decoder.block.28.layer.0.SelfAttention.v.weight": "pytorch_model-00004-of-00004.bin",
305
+ "decoder.block.28.layer.0.layer_norm.weight": "pytorch_model-00004-of-00004.bin",
306
+ "decoder.block.28.layer.1.EncDecAttention.k.weight": "pytorch_model-00004-of-00004.bin",
307
+ "decoder.block.28.layer.1.EncDecAttention.o.weight": "pytorch_model-00004-of-00004.bin",
308
+ "decoder.block.28.layer.1.EncDecAttention.q.weight": "pytorch_model-00004-of-00004.bin",
309
+ "decoder.block.28.layer.1.EncDecAttention.v.weight": "pytorch_model-00004-of-00004.bin",
310
+ "decoder.block.28.layer.1.layer_norm.weight": "pytorch_model-00004-of-00004.bin",
311
+ "decoder.block.28.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00004-of-00004.bin",
312
+ "decoder.block.28.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00004-of-00004.bin",
313
+ "decoder.block.28.layer.2.DenseReluDense.wo.weight": "pytorch_model-00004-of-00004.bin",
314
+ "decoder.block.28.layer.2.layer_norm.weight": "pytorch_model-00004-of-00004.bin",
315
+ "decoder.block.29.layer.0.SelfAttention.k.weight": "pytorch_model-00004-of-00004.bin",
316
+ "decoder.block.29.layer.0.SelfAttention.o.weight": "pytorch_model-00004-of-00004.bin",
317
+ "decoder.block.29.layer.0.SelfAttention.q.weight": "pytorch_model-00004-of-00004.bin",
318
+ "decoder.block.29.layer.0.SelfAttention.v.weight": "pytorch_model-00004-of-00004.bin",
319
+ "decoder.block.29.layer.0.layer_norm.weight": "pytorch_model-00004-of-00004.bin",
320
+ "decoder.block.29.layer.1.EncDecAttention.k.weight": "pytorch_model-00004-of-00004.bin",
321
+ "decoder.block.29.layer.1.EncDecAttention.o.weight": "pytorch_model-00004-of-00004.bin",
322
+ "decoder.block.29.layer.1.EncDecAttention.q.weight": "pytorch_model-00004-of-00004.bin",
323
+ "decoder.block.29.layer.1.EncDecAttention.v.weight": "pytorch_model-00004-of-00004.bin",
324
+ "decoder.block.29.layer.1.layer_norm.weight": "pytorch_model-00004-of-00004.bin",
325
+ "decoder.block.29.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00004-of-00004.bin",
326
+ "decoder.block.29.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00004-of-00004.bin",
327
+ "decoder.block.29.layer.2.DenseReluDense.wo.weight": "pytorch_model-00004-of-00004.bin",
328
+ "decoder.block.29.layer.2.layer_norm.weight": "pytorch_model-00004-of-00004.bin",
329
+ "decoder.block.3.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00004.bin",
330
+ "decoder.block.3.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00004.bin",
331
+ "decoder.block.3.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00004.bin",
332
+ "decoder.block.3.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00004.bin",
333
+ "decoder.block.3.layer.0.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
334
+ "decoder.block.3.layer.1.EncDecAttention.k.weight": "pytorch_model-00003-of-00004.bin",
335
+ "decoder.block.3.layer.1.EncDecAttention.o.weight": "pytorch_model-00003-of-00004.bin",
336
+ "decoder.block.3.layer.1.EncDecAttention.q.weight": "pytorch_model-00003-of-00004.bin",
337
+ "decoder.block.3.layer.1.EncDecAttention.v.weight": "pytorch_model-00003-of-00004.bin",
338
+ "decoder.block.3.layer.1.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
339
+ "decoder.block.3.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00003-of-00004.bin",
340
+ "decoder.block.3.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00003-of-00004.bin",
341
+ "decoder.block.3.layer.2.DenseReluDense.wo.weight": "pytorch_model-00003-of-00004.bin",
342
+ "decoder.block.3.layer.2.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
343
+ "decoder.block.30.layer.0.SelfAttention.k.weight": "pytorch_model-00004-of-00004.bin",
344
+ "decoder.block.30.layer.0.SelfAttention.o.weight": "pytorch_model-00004-of-00004.bin",
345
+ "decoder.block.30.layer.0.SelfAttention.q.weight": "pytorch_model-00004-of-00004.bin",
346
+ "decoder.block.30.layer.0.SelfAttention.v.weight": "pytorch_model-00004-of-00004.bin",
347
+ "decoder.block.30.layer.0.layer_norm.weight": "pytorch_model-00004-of-00004.bin",
348
+ "decoder.block.30.layer.1.EncDecAttention.k.weight": "pytorch_model-00004-of-00004.bin",
349
+ "decoder.block.30.layer.1.EncDecAttention.o.weight": "pytorch_model-00004-of-00004.bin",
350
+ "decoder.block.30.layer.1.EncDecAttention.q.weight": "pytorch_model-00004-of-00004.bin",
351
+ "decoder.block.30.layer.1.EncDecAttention.v.weight": "pytorch_model-00004-of-00004.bin",
352
+ "decoder.block.30.layer.1.layer_norm.weight": "pytorch_model-00004-of-00004.bin",
353
+ "decoder.block.30.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00004-of-00004.bin",
354
+ "decoder.block.30.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00004-of-00004.bin",
355
+ "decoder.block.30.layer.2.DenseReluDense.wo.weight": "pytorch_model-00004-of-00004.bin",
356
+ "decoder.block.30.layer.2.layer_norm.weight": "pytorch_model-00004-of-00004.bin",
357
+ "decoder.block.31.layer.0.SelfAttention.k.weight": "pytorch_model-00004-of-00004.bin",
358
+ "decoder.block.31.layer.0.SelfAttention.o.weight": "pytorch_model-00004-of-00004.bin",
359
+ "decoder.block.31.layer.0.SelfAttention.q.weight": "pytorch_model-00004-of-00004.bin",
360
+ "decoder.block.31.layer.0.SelfAttention.v.weight": "pytorch_model-00004-of-00004.bin",
361
+ "decoder.block.31.layer.0.layer_norm.weight": "pytorch_model-00004-of-00004.bin",
362
+ "decoder.block.31.layer.1.EncDecAttention.k.weight": "pytorch_model-00004-of-00004.bin",
363
+ "decoder.block.31.layer.1.EncDecAttention.o.weight": "pytorch_model-00004-of-00004.bin",
364
+ "decoder.block.31.layer.1.EncDecAttention.q.weight": "pytorch_model-00004-of-00004.bin",
365
+ "decoder.block.31.layer.1.EncDecAttention.v.weight": "pytorch_model-00004-of-00004.bin",
366
+ "decoder.block.31.layer.1.layer_norm.weight": "pytorch_model-00004-of-00004.bin",
367
+ "decoder.block.31.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00004-of-00004.bin",
368
+ "decoder.block.31.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00004-of-00004.bin",
369
+ "decoder.block.31.layer.2.DenseReluDense.wo.weight": "pytorch_model-00004-of-00004.bin",
370
+ "decoder.block.31.layer.2.layer_norm.weight": "pytorch_model-00004-of-00004.bin",
371
+ "decoder.block.4.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00004.bin",
372
+ "decoder.block.4.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00004.bin",
373
+ "decoder.block.4.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00004.bin",
374
+ "decoder.block.4.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00004.bin",
375
+ "decoder.block.4.layer.0.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
376
+ "decoder.block.4.layer.1.EncDecAttention.k.weight": "pytorch_model-00003-of-00004.bin",
377
+ "decoder.block.4.layer.1.EncDecAttention.o.weight": "pytorch_model-00003-of-00004.bin",
378
+ "decoder.block.4.layer.1.EncDecAttention.q.weight": "pytorch_model-00003-of-00004.bin",
379
+ "decoder.block.4.layer.1.EncDecAttention.v.weight": "pytorch_model-00003-of-00004.bin",
380
+ "decoder.block.4.layer.1.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
381
+ "decoder.block.4.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00003-of-00004.bin",
382
+ "decoder.block.4.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00003-of-00004.bin",
383
+ "decoder.block.4.layer.2.DenseReluDense.wo.weight": "pytorch_model-00003-of-00004.bin",
384
+ "decoder.block.4.layer.2.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
385
+ "decoder.block.5.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00004.bin",
386
+ "decoder.block.5.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00004.bin",
387
+ "decoder.block.5.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00004.bin",
388
+ "decoder.block.5.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00004.bin",
389
+ "decoder.block.5.layer.0.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
390
+ "decoder.block.5.layer.1.EncDecAttention.k.weight": "pytorch_model-00003-of-00004.bin",
391
+ "decoder.block.5.layer.1.EncDecAttention.o.weight": "pytorch_model-00003-of-00004.bin",
392
+ "decoder.block.5.layer.1.EncDecAttention.q.weight": "pytorch_model-00003-of-00004.bin",
393
+ "decoder.block.5.layer.1.EncDecAttention.v.weight": "pytorch_model-00003-of-00004.bin",
394
+ "decoder.block.5.layer.1.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
395
+ "decoder.block.5.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00003-of-00004.bin",
396
+ "decoder.block.5.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00003-of-00004.bin",
397
+ "decoder.block.5.layer.2.DenseReluDense.wo.weight": "pytorch_model-00003-of-00004.bin",
398
+ "decoder.block.5.layer.2.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
399
+ "decoder.block.6.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00004.bin",
400
+ "decoder.block.6.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00004.bin",
401
+ "decoder.block.6.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00004.bin",
402
+ "decoder.block.6.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00004.bin",
403
+ "decoder.block.6.layer.0.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
404
+ "decoder.block.6.layer.1.EncDecAttention.k.weight": "pytorch_model-00003-of-00004.bin",
405
+ "decoder.block.6.layer.1.EncDecAttention.o.weight": "pytorch_model-00003-of-00004.bin",
406
+ "decoder.block.6.layer.1.EncDecAttention.q.weight": "pytorch_model-00003-of-00004.bin",
407
+ "decoder.block.6.layer.1.EncDecAttention.v.weight": "pytorch_model-00003-of-00004.bin",
408
+ "decoder.block.6.layer.1.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
409
+ "decoder.block.6.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00003-of-00004.bin",
410
+ "decoder.block.6.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00003-of-00004.bin",
411
+ "decoder.block.6.layer.2.DenseReluDense.wo.weight": "pytorch_model-00003-of-00004.bin",
412
+ "decoder.block.6.layer.2.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
413
+ "decoder.block.7.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00004.bin",
414
+ "decoder.block.7.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00004.bin",
415
+ "decoder.block.7.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00004.bin",
416
+ "decoder.block.7.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00004.bin",
417
+ "decoder.block.7.layer.0.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
418
+ "decoder.block.7.layer.1.EncDecAttention.k.weight": "pytorch_model-00003-of-00004.bin",
419
+ "decoder.block.7.layer.1.EncDecAttention.o.weight": "pytorch_model-00003-of-00004.bin",
420
+ "decoder.block.7.layer.1.EncDecAttention.q.weight": "pytorch_model-00003-of-00004.bin",
421
+ "decoder.block.7.layer.1.EncDecAttention.v.weight": "pytorch_model-00003-of-00004.bin",
422
+ "decoder.block.7.layer.1.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
423
+ "decoder.block.7.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00003-of-00004.bin",
424
+ "decoder.block.7.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00003-of-00004.bin",
425
+ "decoder.block.7.layer.2.DenseReluDense.wo.weight": "pytorch_model-00003-of-00004.bin",
426
+ "decoder.block.7.layer.2.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
427
+ "decoder.block.8.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00004.bin",
428
+ "decoder.block.8.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00004.bin",
429
+ "decoder.block.8.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00004.bin",
430
+ "decoder.block.8.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00004.bin",
431
+ "decoder.block.8.layer.0.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
432
+ "decoder.block.8.layer.1.EncDecAttention.k.weight": "pytorch_model-00003-of-00004.bin",
433
+ "decoder.block.8.layer.1.EncDecAttention.o.weight": "pytorch_model-00003-of-00004.bin",
434
+ "decoder.block.8.layer.1.EncDecAttention.q.weight": "pytorch_model-00003-of-00004.bin",
435
+ "decoder.block.8.layer.1.EncDecAttention.v.weight": "pytorch_model-00003-of-00004.bin",
436
+ "decoder.block.8.layer.1.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
437
+ "decoder.block.8.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00003-of-00004.bin",
438
+ "decoder.block.8.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00003-of-00004.bin",
439
+ "decoder.block.8.layer.2.DenseReluDense.wo.weight": "pytorch_model-00003-of-00004.bin",
440
+ "decoder.block.8.layer.2.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
441
+ "decoder.block.9.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00004.bin",
442
+ "decoder.block.9.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00004.bin",
443
+ "decoder.block.9.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00004.bin",
444
+ "decoder.block.9.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00004.bin",
445
+ "decoder.block.9.layer.0.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
446
+ "decoder.block.9.layer.1.EncDecAttention.k.weight": "pytorch_model-00003-of-00004.bin",
447
+ "decoder.block.9.layer.1.EncDecAttention.o.weight": "pytorch_model-00003-of-00004.bin",
448
+ "decoder.block.9.layer.1.EncDecAttention.q.weight": "pytorch_model-00003-of-00004.bin",
449
+ "decoder.block.9.layer.1.EncDecAttention.v.weight": "pytorch_model-00003-of-00004.bin",
450
+ "decoder.block.9.layer.1.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
451
+ "decoder.block.9.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00003-of-00004.bin",
452
+ "decoder.block.9.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00003-of-00004.bin",
453
+ "decoder.block.9.layer.2.DenseReluDense.wo.weight": "pytorch_model-00003-of-00004.bin",
454
+ "decoder.block.9.layer.2.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
455
+ "decoder.embed_tokens.weight": "pytorch_model-00002-of-00004.bin",
456
+ "decoder.final_layer_norm.weight": "pytorch_model-00004-of-00004.bin",
457
+ "encoder.block.0.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00004.bin",
458
+ "encoder.block.0.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00004.bin",
459
+ "encoder.block.0.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00004.bin",
460
+ "encoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "pytorch_model-00001-of-00004.bin",
461
+ "encoder.block.0.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00004.bin",
462
+ "encoder.block.0.layer.0.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
463
+ "encoder.block.0.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00004.bin",
464
+ "encoder.block.0.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00004.bin",
465
+ "encoder.block.0.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00004.bin",
466
+ "encoder.block.0.layer.1.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
467
+ "encoder.block.1.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00004.bin",
468
+ "encoder.block.1.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00004.bin",
469
+ "encoder.block.1.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00004.bin",
470
+ "encoder.block.1.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00004.bin",
471
+ "encoder.block.1.layer.0.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
472
+ "encoder.block.1.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00004.bin",
473
+ "encoder.block.1.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00004.bin",
474
+ "encoder.block.1.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00004.bin",
475
+ "encoder.block.1.layer.1.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
476
+ "encoder.block.10.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00004.bin",
477
+ "encoder.block.10.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00004.bin",
478
+ "encoder.block.10.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00004.bin",
479
+ "encoder.block.10.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00004.bin",
480
+ "encoder.block.10.layer.0.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
481
+ "encoder.block.10.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00004.bin",
482
+ "encoder.block.10.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00004.bin",
483
+ "encoder.block.10.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00004.bin",
484
+ "encoder.block.10.layer.1.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
485
+ "encoder.block.11.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00004.bin",
486
+ "encoder.block.11.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00004.bin",
487
+ "encoder.block.11.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00004.bin",
488
+ "encoder.block.11.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00004.bin",
489
+ "encoder.block.11.layer.0.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
490
+ "encoder.block.11.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00004.bin",
491
+ "encoder.block.11.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00004.bin",
492
+ "encoder.block.11.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00004.bin",
493
+ "encoder.block.11.layer.1.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
494
+ "encoder.block.12.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00004.bin",
495
+ "encoder.block.12.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00004.bin",
496
+ "encoder.block.12.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00004.bin",
497
+ "encoder.block.12.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00004.bin",
498
+ "encoder.block.12.layer.0.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
499
+ "encoder.block.12.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00004.bin",
500
+ "encoder.block.12.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00004.bin",
501
+ "encoder.block.12.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00004.bin",
502
+ "encoder.block.12.layer.1.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
503
+ "encoder.block.13.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00004.bin",
504
+ "encoder.block.13.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00004.bin",
505
+ "encoder.block.13.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00004.bin",
506
+ "encoder.block.13.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00004.bin",
507
+ "encoder.block.13.layer.0.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
508
+ "encoder.block.13.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00004.bin",
509
+ "encoder.block.13.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00004.bin",
510
+ "encoder.block.13.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00004.bin",
511
+ "encoder.block.13.layer.1.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
512
+ "encoder.block.14.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00004.bin",
513
+ "encoder.block.14.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00004.bin",
514
+ "encoder.block.14.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00004.bin",
515
+ "encoder.block.14.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00004.bin",
516
+ "encoder.block.14.layer.0.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
517
+ "encoder.block.14.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00004.bin",
518
+ "encoder.block.14.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00004.bin",
519
+ "encoder.block.14.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00004.bin",
520
+ "encoder.block.14.layer.1.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
521
+ "encoder.block.15.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00004.bin",
522
+ "encoder.block.15.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00004.bin",
523
+ "encoder.block.15.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00004.bin",
524
+ "encoder.block.15.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00004.bin",
525
+ "encoder.block.15.layer.0.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
526
+ "encoder.block.15.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00004.bin",
527
+ "encoder.block.15.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00004.bin",
528
+ "encoder.block.15.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00004.bin",
529
+ "encoder.block.15.layer.1.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
530
+ "encoder.block.16.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00004.bin",
531
+ "encoder.block.16.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00004.bin",
532
+ "encoder.block.16.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00004.bin",
533
+ "encoder.block.16.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00004.bin",
534
+ "encoder.block.16.layer.0.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
535
+ "encoder.block.16.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00004.bin",
536
+ "encoder.block.16.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00004.bin",
537
+ "encoder.block.16.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00004.bin",
538
+ "encoder.block.16.layer.1.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
539
+ "encoder.block.17.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00004.bin",
540
+ "encoder.block.17.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00004.bin",
541
+ "encoder.block.17.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00004.bin",
542
+ "encoder.block.17.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00004.bin",
543
+ "encoder.block.17.layer.0.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
544
+ "encoder.block.17.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00004.bin",
545
+ "encoder.block.17.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00004.bin",
546
+ "encoder.block.17.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00004.bin",
547
+ "encoder.block.17.layer.1.layer_norm.weight": "pytorch_model-00002-of-00004.bin",
548
+ "encoder.block.18.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00004.bin",
549
+ "encoder.block.18.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00004.bin",
550
+ "encoder.block.18.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00004.bin",
551
+ "encoder.block.18.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00004.bin",
552
+ "encoder.block.18.layer.0.layer_norm.weight": "pytorch_model-00002-of-00004.bin",
553
+ "encoder.block.18.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00004.bin",
554
+ "encoder.block.18.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00004.bin",
555
+ "encoder.block.18.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00004.bin",
556
+ "encoder.block.18.layer.1.layer_norm.weight": "pytorch_model-00002-of-00004.bin",
557
+ "encoder.block.19.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00004.bin",
558
+ "encoder.block.19.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00004.bin",
559
+ "encoder.block.19.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00004.bin",
560
+ "encoder.block.19.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00004.bin",
561
+ "encoder.block.19.layer.0.layer_norm.weight": "pytorch_model-00002-of-00004.bin",
562
+ "encoder.block.19.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00004.bin",
563
+ "encoder.block.19.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00004.bin",
564
+ "encoder.block.19.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00004.bin",
565
+ "encoder.block.19.layer.1.layer_norm.weight": "pytorch_model-00002-of-00004.bin",
566
+ "encoder.block.2.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00004.bin",
567
+ "encoder.block.2.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00004.bin",
568
+ "encoder.block.2.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00004.bin",
569
+ "encoder.block.2.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00004.bin",
570
+ "encoder.block.2.layer.0.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
571
+ "encoder.block.2.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00004.bin",
572
+ "encoder.block.2.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00004.bin",
573
+ "encoder.block.2.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00004.bin",
574
+ "encoder.block.2.layer.1.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
575
+ "encoder.block.20.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00004.bin",
576
+ "encoder.block.20.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00004.bin",
577
+ "encoder.block.20.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00004.bin",
578
+ "encoder.block.20.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00004.bin",
579
+ "encoder.block.20.layer.0.layer_norm.weight": "pytorch_model-00002-of-00004.bin",
580
+ "encoder.block.20.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00004.bin",
581
+ "encoder.block.20.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00004.bin",
582
+ "encoder.block.20.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00004.bin",
583
+ "encoder.block.20.layer.1.layer_norm.weight": "pytorch_model-00002-of-00004.bin",
584
+ "encoder.block.21.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00004.bin",
585
+ "encoder.block.21.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00004.bin",
586
+ "encoder.block.21.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00004.bin",
587
+ "encoder.block.21.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00004.bin",
588
+ "encoder.block.21.layer.0.layer_norm.weight": "pytorch_model-00002-of-00004.bin",
589
+ "encoder.block.21.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00004.bin",
590
+ "encoder.block.21.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00004.bin",
591
+ "encoder.block.21.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00004.bin",
592
+ "encoder.block.21.layer.1.layer_norm.weight": "pytorch_model-00002-of-00004.bin",
593
+ "encoder.block.22.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00004.bin",
594
+ "encoder.block.22.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00004.bin",
595
+ "encoder.block.22.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00004.bin",
596
+ "encoder.block.22.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00004.bin",
597
+ "encoder.block.22.layer.0.layer_norm.weight": "pytorch_model-00002-of-00004.bin",
598
+ "encoder.block.22.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00004.bin",
599
+ "encoder.block.22.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00004.bin",
600
+ "encoder.block.22.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00004.bin",
601
+ "encoder.block.22.layer.1.layer_norm.weight": "pytorch_model-00002-of-00004.bin",
602
+ "encoder.block.23.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00004.bin",
603
+ "encoder.block.23.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00004.bin",
604
+ "encoder.block.23.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00004.bin",
605
+ "encoder.block.23.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00004.bin",
606
+ "encoder.block.23.layer.0.layer_norm.weight": "pytorch_model-00002-of-00004.bin",
607
+ "encoder.block.23.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00004.bin",
608
+ "encoder.block.23.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00004.bin",
609
+ "encoder.block.23.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00004.bin",
610
+ "encoder.block.23.layer.1.layer_norm.weight": "pytorch_model-00002-of-00004.bin",
611
+ "encoder.block.24.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00004.bin",
612
+ "encoder.block.24.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00004.bin",
613
+ "encoder.block.24.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00004.bin",
614
+ "encoder.block.24.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00004.bin",
615
+ "encoder.block.24.layer.0.layer_norm.weight": "pytorch_model-00002-of-00004.bin",
616
+ "encoder.block.24.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00004.bin",
617
+ "encoder.block.24.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00004.bin",
618
+ "encoder.block.24.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00004.bin",
619
+ "encoder.block.24.layer.1.layer_norm.weight": "pytorch_model-00002-of-00004.bin",
620
+ "encoder.block.25.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00004.bin",
621
+ "encoder.block.25.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00004.bin",
622
+ "encoder.block.25.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00004.bin",
623
+ "encoder.block.25.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00004.bin",
624
+ "encoder.block.25.layer.0.layer_norm.weight": "pytorch_model-00002-of-00004.bin",
625
+ "encoder.block.25.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00004.bin",
626
+ "encoder.block.25.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00004.bin",
627
+ "encoder.block.25.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00004.bin",
628
+ "encoder.block.25.layer.1.layer_norm.weight": "pytorch_model-00002-of-00004.bin",
629
+ "encoder.block.26.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00004.bin",
630
+ "encoder.block.26.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00004.bin",
631
+ "encoder.block.26.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00004.bin",
632
+ "encoder.block.26.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00004.bin",
633
+ "encoder.block.26.layer.0.layer_norm.weight": "pytorch_model-00002-of-00004.bin",
634
+ "encoder.block.26.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00004.bin",
635
+ "encoder.block.26.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00004.bin",
636
+ "encoder.block.26.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00004.bin",
637
+ "encoder.block.26.layer.1.layer_norm.weight": "pytorch_model-00002-of-00004.bin",
638
+ "encoder.block.27.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00004.bin",
639
+ "encoder.block.27.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00004.bin",
640
+ "encoder.block.27.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00004.bin",
641
+ "encoder.block.27.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00004.bin",
642
+ "encoder.block.27.layer.0.layer_norm.weight": "pytorch_model-00002-of-00004.bin",
643
+ "encoder.block.27.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00004.bin",
644
+ "encoder.block.27.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00004.bin",
645
+ "encoder.block.27.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00004.bin",
646
+ "encoder.block.27.layer.1.layer_norm.weight": "pytorch_model-00002-of-00004.bin",
647
+ "encoder.block.28.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00004.bin",
648
+ "encoder.block.28.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00004.bin",
649
+ "encoder.block.28.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00004.bin",
650
+ "encoder.block.28.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00004.bin",
651
+ "encoder.block.28.layer.0.layer_norm.weight": "pytorch_model-00002-of-00004.bin",
652
+ "encoder.block.28.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00004.bin",
653
+ "encoder.block.28.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00004.bin",
654
+ "encoder.block.28.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00004.bin",
655
+ "encoder.block.28.layer.1.layer_norm.weight": "pytorch_model-00002-of-00004.bin",
656
+ "encoder.block.29.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00004.bin",
657
+ "encoder.block.29.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00004.bin",
658
+ "encoder.block.29.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00004.bin",
659
+ "encoder.block.29.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00004.bin",
660
+ "encoder.block.29.layer.0.layer_norm.weight": "pytorch_model-00002-of-00004.bin",
661
+ "encoder.block.29.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00004.bin",
662
+ "encoder.block.29.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00004.bin",
663
+ "encoder.block.29.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00004.bin",
664
+ "encoder.block.29.layer.1.layer_norm.weight": "pytorch_model-00002-of-00004.bin",
665
+ "encoder.block.3.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00004.bin",
666
+ "encoder.block.3.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00004.bin",
667
+ "encoder.block.3.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00004.bin",
668
+ "encoder.block.3.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00004.bin",
669
+ "encoder.block.3.layer.0.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
670
+ "encoder.block.3.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00004.bin",
671
+ "encoder.block.3.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00004.bin",
672
+ "encoder.block.3.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00004.bin",
673
+ "encoder.block.3.layer.1.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
674
+ "encoder.block.30.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00004.bin",
675
+ "encoder.block.30.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00004.bin",
676
+ "encoder.block.30.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00004.bin",
677
+ "encoder.block.30.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00004.bin",
678
+ "encoder.block.30.layer.0.layer_norm.weight": "pytorch_model-00002-of-00004.bin",
679
+ "encoder.block.30.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00004.bin",
680
+ "encoder.block.30.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00004.bin",
681
+ "encoder.block.30.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00004.bin",
682
+ "encoder.block.30.layer.1.layer_norm.weight": "pytorch_model-00002-of-00004.bin",
683
+ "encoder.block.31.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00004.bin",
684
+ "encoder.block.31.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00004.bin",
685
+ "encoder.block.31.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00004.bin",
686
+ "encoder.block.31.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00004.bin",
687
+ "encoder.block.31.layer.0.layer_norm.weight": "pytorch_model-00002-of-00004.bin",
688
+ "encoder.block.31.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00004.bin",
689
+ "encoder.block.31.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00004.bin",
690
+ "encoder.block.31.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00004.bin",
691
+ "encoder.block.31.layer.1.layer_norm.weight": "pytorch_model-00002-of-00004.bin",
692
+ "encoder.block.4.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00004.bin",
693
+ "encoder.block.4.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00004.bin",
694
+ "encoder.block.4.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00004.bin",
695
+ "encoder.block.4.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00004.bin",
696
+ "encoder.block.4.layer.0.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
697
+ "encoder.block.4.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00004.bin",
698
+ "encoder.block.4.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00004.bin",
699
+ "encoder.block.4.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00004.bin",
700
+ "encoder.block.4.layer.1.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
701
+ "encoder.block.5.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00004.bin",
702
+ "encoder.block.5.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00004.bin",
703
+ "encoder.block.5.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00004.bin",
704
+ "encoder.block.5.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00004.bin",
705
+ "encoder.block.5.layer.0.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
706
+ "encoder.block.5.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00004.bin",
707
+ "encoder.block.5.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00004.bin",
708
+ "encoder.block.5.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00004.bin",
709
+ "encoder.block.5.layer.1.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
710
+ "encoder.block.6.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00004.bin",
711
+ "encoder.block.6.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00004.bin",
712
+ "encoder.block.6.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00004.bin",
713
+ "encoder.block.6.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00004.bin",
714
+ "encoder.block.6.layer.0.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
715
+ "encoder.block.6.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00004.bin",
716
+ "encoder.block.6.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00004.bin",
717
+ "encoder.block.6.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00004.bin",
718
+ "encoder.block.6.layer.1.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
719
+ "encoder.block.7.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00004.bin",
720
+ "encoder.block.7.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00004.bin",
721
+ "encoder.block.7.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00004.bin",
722
+ "encoder.block.7.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00004.bin",
723
+ "encoder.block.7.layer.0.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
724
+ "encoder.block.7.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00004.bin",
725
+ "encoder.block.7.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00004.bin",
726
+ "encoder.block.7.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00004.bin",
727
+ "encoder.block.7.layer.1.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
728
+ "encoder.block.8.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00004.bin",
729
+ "encoder.block.8.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00004.bin",
730
+ "encoder.block.8.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00004.bin",
731
+ "encoder.block.8.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00004.bin",
732
+ "encoder.block.8.layer.0.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
733
+ "encoder.block.8.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00004.bin",
734
+ "encoder.block.8.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00004.bin",
735
+ "encoder.block.8.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00004.bin",
736
+ "encoder.block.8.layer.1.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
737
+ "encoder.block.9.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00004.bin",
738
+ "encoder.block.9.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00004.bin",
739
+ "encoder.block.9.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00004.bin",
740
+ "encoder.block.9.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00004.bin",
741
+ "encoder.block.9.layer.0.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
742
+ "encoder.block.9.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00004.bin",
743
+ "encoder.block.9.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00004.bin",
744
+ "encoder.block.9.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00004.bin",
745
+ "encoder.block.9.layer.1.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
746
+ "encoder.embed_tokens.weight": "pytorch_model-00001-of-00004.bin",
747
+ "encoder.final_layer_norm.weight": "pytorch_model-00002-of-00004.bin",
748
+ "lm_head.weight": "pytorch_model-00004-of-00004.bin",
749
+ "shared.weight": "pytorch_model-00001-of-00004.bin"
750
+ }
751
+ }
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "additional_special_tokens": ["<extra_id_0>", "<extra_id_1>", "<extra_id_2>", "<extra_id_3>", "<extra_id_4>", "<extra_id_5>", "<extra_id_6>", "<extra_id_7>", "<extra_id_8>", "<extra_id_9>", "<extra_id_10>", "<extra_id_11>", "<extra_id_12>", "<extra_id_13>", "<extra_id_14>", "<extra_id_15>", "<extra_id_16>", "<extra_id_17>", "<extra_id_18>", "<extra_id_19>", "<extra_id_20>", "<extra_id_21>", "<extra_id_22>", "<extra_id_23>", "<extra_id_24>", "<extra_id_25>", "<extra_id_26>", "<extra_id_27>", "<extra_id_28>", "<extra_id_29>", "<extra_id_30>", "<extra_id_31>", "<extra_id_32>", "<extra_id_33>", "<extra_id_34>", "<extra_id_35>", "<extra_id_36>", "<extra_id_37>", "<extra_id_38>", "<extra_id_39>", "<extra_id_40>", "<extra_id_41>", "<extra_id_42>", "<extra_id_43>", "<extra_id_44>", "<extra_id_45>", "<extra_id_46>", "<extra_id_47>", "<extra_id_48>", "<extra_id_49>", "<extra_id_50>", "<extra_id_51>", "<extra_id_52>", "<extra_id_53>", "<extra_id_54>", "<extra_id_55>", "<extra_id_56>", "<extra_id_57>", "<extra_id_58>", "<extra_id_59>", "<extra_id_60>", "<extra_id_61>", "<extra_id_62>", "<extra_id_63>", "<extra_id_64>", "<extra_id_65>", "<extra_id_66>", "<extra_id_67>", "<extra_id_68>", "<extra_id_69>", "<extra_id_70>", "<extra_id_71>", "<extra_id_72>", "<extra_id_73>", "<extra_id_74>", "<extra_id_75>", "<extra_id_76>", "<extra_id_77>", "<extra_id_78>", "<extra_id_79>", "<extra_id_80>", "<extra_id_81>", "<extra_id_82>", "<extra_id_83>", "<extra_id_84>", "<extra_id_85>", "<extra_id_86>", "<extra_id_87>", "<extra_id_88>", "<extra_id_89>", "<extra_id_90>", "<extra_id_91>", "<extra_id_92>", "<extra_id_93>", "<extra_id_94>", "<extra_id_95>", "<extra_id_96>", "<extra_id_97>", "<extra_id_98>", "<extra_id_99>"]}
spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
3
+ size 791656
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "extra_ids": 100, "additional_special_tokens": ["<extra_id_0>", "<extra_id_1>", "<extra_id_2>", "<extra_id_3>", "<extra_id_4>", "<extra_id_5>", "<extra_id_6>", "<extra_id_7>", "<extra_id_8>", "<extra_id_9>", "<extra_id_10>", "<extra_id_11>", "<extra_id_12>", "<extra_id_13>", "<extra_id_14>", "<extra_id_15>", "<extra_id_16>", "<extra_id_17>", "<extra_id_18>", "<extra_id_19>", "<extra_id_20>", "<extra_id_21>", "<extra_id_22>", "<extra_id_23>", "<extra_id_24>", "<extra_id_25>", "<extra_id_26>", "<extra_id_27>", "<extra_id_28>", "<extra_id_29>", "<extra_id_30>", "<extra_id_31>", "<extra_id_32>", "<extra_id_33>", "<extra_id_34>", "<extra_id_35>", "<extra_id_36>", "<extra_id_37>", "<extra_id_38>", "<extra_id_39>", "<extra_id_40>", "<extra_id_41>", "<extra_id_42>", "<extra_id_43>", "<extra_id_44>", "<extra_id_45>", "<extra_id_46>", "<extra_id_47>", "<extra_id_48>", "<extra_id_49>", "<extra_id_50>", "<extra_id_51>", "<extra_id_52>", "<extra_id_53>", "<extra_id_54>", "<extra_id_55>", "<extra_id_56>", "<extra_id_57>", "<extra_id_58>", "<extra_id_59>", "<extra_id_60>", "<extra_id_61>", "<extra_id_62>", "<extra_id_63>", "<extra_id_64>", "<extra_id_65>", "<extra_id_66>", "<extra_id_67>", "<extra_id_68>", "<extra_id_69>", "<extra_id_70>", "<extra_id_71>", "<extra_id_72>", "<extra_id_73>", "<extra_id_74>", "<extra_id_75>", "<extra_id_76>", "<extra_id_77>", "<extra_id_78>", "<extra_id_79>", "<extra_id_80>", "<extra_id_81>", "<extra_id_82>", "<extra_id_83>", "<extra_id_84>", "<extra_id_85>", "<extra_id_86>", "<extra_id_87>", "<extra_id_88>", "<extra_id_89>", "<extra_id_90>", "<extra_id_91>", "<extra_id_92>", "<extra_id_93>", "<extra_id_94>", "<extra_id_95>", "<extra_id_96>", "<extra_id_97>", "<extra_id_98>", "<extra_id_99>"], "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "t5-3b", "tokenizer_class": "T5Tokenizer"}