Hugging Face's logo

LLM360
/
K2-V2-Instruct

PyTorch
English
llama
Model card Files
xet
Community
10
richardmfan commited on
Commit
3cec807
·
verified ·
1 Parent(s): 9156799

Upload stage_1_0065000

Browse files
Files changed (14) hide show
  1. .gitattributes +1 -0
  2. config.json +30 -0
  3. done.txt +1 -0
  4. generation_config.json +6 -0
  5. pytorch_model-00001-of-00006.bin +1 -1
  6. pytorch_model-00002-of-00006.bin +1 -1
  7. pytorch_model-00003-of-00006.bin +1 -1
  8. pytorch_model-00004-of-00006.bin +1 -1
  9. pytorch_model-00005-of-00006.bin +1 -1
  10. pytorch_model-00006-of-00006.bin +1 -1
  11. pytorch_model.bin.index.json +731 -0
  12. special_tokens_map.json +16 -0
  13. tokenizer.json +3 -0
  14. tokenizer_config.json +926 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlamaForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 0,
8
+ "eos_token_id": 1,
9
+ "head_dim": 128,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 8192,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 28672,
14
+ "max_position_embeddings": 32768,
15
+ "mlp_bias": false,
16
+ "model_type": "llama",
17
+ "num_attention_heads": 64,
18
+ "num_hidden_layers": 80,
19
+ "num_key_value_heads": 8,
20
+ "num_local_experts": null,
21
+ "pretraining_tp": 1,
22
+ "rms_norm_eps": 1e-05,
23
+ "rope_scaling": null,
24
+ "rope_theta": 500000,
25
+ "tie_word_embeddings": false,
26
+ "torch_dtype": "float32",
27
+ "transformers_version": "4.53.2",
28
+ "use_cache": true,
29
+ "vocab_size": 250112
30
+ }
done.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ saving done
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "eos_token_id": 1,
5
+ "transformers_version": "4.53.2"
6
+ }
pytorch_model-00001-of-00006.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:909b8615f928423d2074ea7bf4ea31003cad7181a2800909239b4b9d5c157f14
3
  size 49871101268
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b7f90d890ca1d716955a64fe8d041e9e403cb15b047f7f1ed1f019fdb83850d
3
  size 49871101268
pytorch_model-00002-of-00006.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:60bae6b0ced8f2cfa83b1f0d5b56511adce096d46e20d5ce4c33f68770ab1ef6
3
  size 49795740133
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:13741a36e22ea360965f8da5e5f8e923259fe456d500aea4ffef0db03d887262
3
  size 49795740133
pytorch_model-00003-of-00006.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0d54ce154d56d1114bea3d8e5784f3b523f619e08bce8d28fe62a75e4f7adf3a
3
  size 49460263104
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27d0c7c25fb38c143612935b635df7bbab7940980fef64813a0e6047f66e7799
3
  size 49460263104
pytorch_model-00004-of-00006.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:29faf1fe1f7247a9067b263f58c6c3bbb83cff62064703f6e4d1ce1955adf822
3
  size 49795740133
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4e25f1a5a2b7740ca523adcc835e86bcf58dfdbb42f71ad38c618cdb654db5b
3
  size 49795740133
pytorch_model-00005-of-00006.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1cf75748f7cc7116c8872f1e447531b7741a3fd90ff0e8d2e6b7d6ba5d96eaa9
3
  size 49460263104
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:505b10b6834e3ec82ee5f1ba623e5924679c93048cb83327e851fbef0867bb73
3
  size 49460263104
pytorch_model-00006-of-00006.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5b61cc9e8a11fdd665f4d941509d3b947fed05523ffbac79479570b90a4d7138
3
  size 41817930473
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:88e9abf5703a245c4ed16bec91f3ba1f90ecc9cd3b7a4339eda8c906c6c53a6a
3
  size 41817930473
pytorch_model.bin.index.json ADDED
@@ -0,0 +1,731 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_parameters": 72550195200,
4
+ "total_size": 290200780800
5
+ },
6
+ "weight_map": {
7
+ "lm_head.weight": "pytorch_model-00006-of-00006.bin",
8
+ "model.embed_tokens.weight": "pytorch_model-00001-of-00006.bin",
9
+ "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
10
+ "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
11
+ "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
12
+ "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
13
+ "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
14
+ "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
15
+ "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
16
+ "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
17
+ "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
18
+ "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
19
+ "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
20
+ "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
21
+ "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
22
+ "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
23
+ "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
24
+ "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
25
+ "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
26
+ "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
27
+ "model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
28
+ "model.layers.10.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
29
+ "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
30
+ "model.layers.10.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
31
+ "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
32
+ "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
33
+ "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
34
+ "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
35
+ "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
36
+ "model.layers.11.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
37
+ "model.layers.11.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
38
+ "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
39
+ "model.layers.11.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
40
+ "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
41
+ "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
42
+ "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
43
+ "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
44
+ "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
45
+ "model.layers.12.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
46
+ "model.layers.12.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
47
+ "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
48
+ "model.layers.12.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
49
+ "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
50
+ "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
51
+ "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
52
+ "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
53
+ "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
54
+ "model.layers.13.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
55
+ "model.layers.13.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
56
+ "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
57
+ "model.layers.13.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
58
+ "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
59
+ "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
60
+ "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
61
+ "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
62
+ "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
63
+ "model.layers.14.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
64
+ "model.layers.14.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
65
+ "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
66
+ "model.layers.14.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
67
+ "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
68
+ "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
69
+ "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
70
+ "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
71
+ "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
72
+ "model.layers.15.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
73
+ "model.layers.15.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
74
+ "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
75
+ "model.layers.15.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
76
+ "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
77
+ "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
78
+ "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
79
+ "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
80
+ "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
81
+ "model.layers.16.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
82
+ "model.layers.16.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
83
+ "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
84
+ "model.layers.16.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
85
+ "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
86
+ "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
87
+ "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
88
+ "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
89
+ "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
90
+ "model.layers.17.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
91
+ "model.layers.17.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
92
+ "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
93
+ "model.layers.17.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
94
+ "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
95
+ "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
96
+ "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
97
+ "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
98
+ "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
99
+ "model.layers.18.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
100
+ "model.layers.18.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
101
+ "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
102
+ "model.layers.18.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
103
+ "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
104
+ "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
105
+ "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
106
+ "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
107
+ "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
108
+ "model.layers.19.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
109
+ "model.layers.19.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
110
+ "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
111
+ "model.layers.19.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
112
+ "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
113
+ "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
114
+ "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
115
+ "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
116
+ "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
117
+ "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
118
+ "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
119
+ "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
120
+ "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
121
+ "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
122
+ "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
123
+ "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
124
+ "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
125
+ "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
126
+ "model.layers.20.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
127
+ "model.layers.20.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
128
+ "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
129
+ "model.layers.20.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
130
+ "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
131
+ "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
132
+ "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
133
+ "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
134
+ "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
135
+ "model.layers.21.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
136
+ "model.layers.21.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
137
+ "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
138
+ "model.layers.21.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
139
+ "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
140
+ "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
141
+ "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
142
+ "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
143
+ "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
144
+ "model.layers.22.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
145
+ "model.layers.22.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
146
+ "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
147
+ "model.layers.22.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
148
+ "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
149
+ "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
150
+ "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
151
+ "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
152
+ "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
153
+ "model.layers.23.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
154
+ "model.layers.23.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
155
+ "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
156
+ "model.layers.23.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
157
+ "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
158
+ "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
159
+ "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
160
+ "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
161
+ "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
162
+ "model.layers.24.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
163
+ "model.layers.24.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
164
+ "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
165
+ "model.layers.24.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
166
+ "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
167
+ "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
168
+ "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
169
+ "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
170
+ "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
171
+ "model.layers.25.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
172
+ "model.layers.25.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
173
+ "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
174
+ "model.layers.25.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
175
+ "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
176
+ "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
177
+ "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
178
+ "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
179
+ "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
180
+ "model.layers.26.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
181
+ "model.layers.26.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
182
+ "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
183
+ "model.layers.26.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
184
+ "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
185
+ "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
186
+ "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
187
+ "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
188
+ "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
189
+ "model.layers.27.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
190
+ "model.layers.27.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
191
+ "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
192
+ "model.layers.27.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
193
+ "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
194
+ "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
195
+ "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
196
+ "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
197
+ "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
198
+ "model.layers.28.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
199
+ "model.layers.28.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
200
+ "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
201
+ "model.layers.28.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
202
+ "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
203
+ "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
204
+ "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
205
+ "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
206
+ "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
207
+ "model.layers.29.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
208
+ "model.layers.29.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
209
+ "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
210
+ "model.layers.29.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
211
+ "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
212
+ "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
213
+ "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
214
+ "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
215
+ "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
216
+ "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
217
+ "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
218
+ "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
219
+ "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
220
+ "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
221
+ "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
222
+ "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
223
+ "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
224
+ "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
225
+ "model.layers.30.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
226
+ "model.layers.30.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
227
+ "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
228
+ "model.layers.30.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
229
+ "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
230
+ "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
231
+ "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
232
+ "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
233
+ "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
234
+ "model.layers.31.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
235
+ "model.layers.31.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
236
+ "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
237
+ "model.layers.31.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
238
+ "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
239
+ "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
240
+ "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
241
+ "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
242
+ "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
243
+ "model.layers.32.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
244
+ "model.layers.32.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
245
+ "model.layers.32.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
246
+ "model.layers.32.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
247
+ "model.layers.32.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
248
+ "model.layers.32.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
249
+ "model.layers.32.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
250
+ "model.layers.32.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
251
+ "model.layers.32.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
252
+ "model.layers.33.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
253
+ "model.layers.33.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
254
+ "model.layers.33.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
255
+ "model.layers.33.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
256
+ "model.layers.33.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
257
+ "model.layers.33.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
258
+ "model.layers.33.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
259
+ "model.layers.33.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
260
+ "model.layers.33.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
261
+ "model.layers.34.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
262
+ "model.layers.34.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
263
+ "model.layers.34.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
264
+ "model.layers.34.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
265
+ "model.layers.34.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
266
+ "model.layers.34.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
267
+ "model.layers.34.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
268
+ "model.layers.34.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
269
+ "model.layers.34.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
270
+ "model.layers.35.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
271
+ "model.layers.35.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
272
+ "model.layers.35.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
273
+ "model.layers.35.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
274
+ "model.layers.35.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
275
+ "model.layers.35.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
276
+ "model.layers.35.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
277
+ "model.layers.35.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
278
+ "model.layers.35.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
279
+ "model.layers.36.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
280
+ "model.layers.36.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
281
+ "model.layers.36.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
282
+ "model.layers.36.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
283
+ "model.layers.36.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
284
+ "model.layers.36.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
285
+ "model.layers.36.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
286
+ "model.layers.36.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
287
+ "model.layers.36.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
288
+ "model.layers.37.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
289
+ "model.layers.37.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
290
+ "model.layers.37.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
291
+ "model.layers.37.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
292
+ "model.layers.37.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
293
+ "model.layers.37.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
294
+ "model.layers.37.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
295
+ "model.layers.37.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
296
+ "model.layers.37.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
297
+ "model.layers.38.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
298
+ "model.layers.38.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
299
+ "model.layers.38.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
300
+ "model.layers.38.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
301
+ "model.layers.38.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
302
+ "model.layers.38.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
303
+ "model.layers.38.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
304
+ "model.layers.38.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
305
+ "model.layers.38.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
306
+ "model.layers.39.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
307
+ "model.layers.39.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
308
+ "model.layers.39.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
309
+ "model.layers.39.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
310
+ "model.layers.39.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
311
+ "model.layers.39.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
312
+ "model.layers.39.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
313
+ "model.layers.39.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
314
+ "model.layers.39.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
315
+ "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
316
+ "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
317
+ "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
318
+ "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
319
+ "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
320
+ "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
321
+ "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
322
+ "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
323
+ "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
324
+ "model.layers.40.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
325
+ "model.layers.40.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
326
+ "model.layers.40.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
327
+ "model.layers.40.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
328
+ "model.layers.40.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
329
+ "model.layers.40.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
330
+ "model.layers.40.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
331
+ "model.layers.40.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
332
+ "model.layers.40.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
333
+ "model.layers.41.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
334
+ "model.layers.41.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
335
+ "model.layers.41.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
336
+ "model.layers.41.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
337
+ "model.layers.41.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
338
+ "model.layers.41.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
339
+ "model.layers.41.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
340
+ "model.layers.41.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
341
+ "model.layers.41.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
342
+ "model.layers.42.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
343
+ "model.layers.42.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
344
+ "model.layers.42.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
345
+ "model.layers.42.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
346
+ "model.layers.42.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
347
+ "model.layers.42.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
348
+ "model.layers.42.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
349
+ "model.layers.42.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
350
+ "model.layers.42.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
351
+ "model.layers.43.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
352
+ "model.layers.43.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
353
+ "model.layers.43.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
354
+ "model.layers.43.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
355
+ "model.layers.43.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
356
+ "model.layers.43.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
357
+ "model.layers.43.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
358
+ "model.layers.43.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
359
+ "model.layers.43.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
360
+ "model.layers.44.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
361
+ "model.layers.44.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
362
+ "model.layers.44.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
363
+ "model.layers.44.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
364
+ "model.layers.44.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
365
+ "model.layers.44.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
366
+ "model.layers.44.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
367
+ "model.layers.44.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
368
+ "model.layers.44.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
369
+ "model.layers.45.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
370
+ "model.layers.45.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
371
+ "model.layers.45.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
372
+ "model.layers.45.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
373
+ "model.layers.45.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
374
+ "model.layers.45.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
375
+ "model.layers.45.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
376
+ "model.layers.45.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
377
+ "model.layers.45.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
378
+ "model.layers.46.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
379
+ "model.layers.46.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
380
+ "model.layers.46.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
381
+ "model.layers.46.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
382
+ "model.layers.46.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
383
+ "model.layers.46.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
384
+ "model.layers.46.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
385
+ "model.layers.46.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
386
+ "model.layers.46.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
387
+ "model.layers.47.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
388
+ "model.layers.47.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
389
+ "model.layers.47.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
390
+ "model.layers.47.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
391
+ "model.layers.47.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
392
+ "model.layers.47.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
393
+ "model.layers.47.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
394
+ "model.layers.47.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
395
+ "model.layers.47.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
396
+ "model.layers.48.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
397
+ "model.layers.48.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
398
+ "model.layers.48.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
399
+ "model.layers.48.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
400
+ "model.layers.48.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
401
+ "model.layers.48.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
402
+ "model.layers.48.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
403
+ "model.layers.48.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
404
+ "model.layers.48.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
405
+ "model.layers.49.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
406
+ "model.layers.49.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
407
+ "model.layers.49.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
408
+ "model.layers.49.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
409
+ "model.layers.49.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
410
+ "model.layers.49.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
411
+ "model.layers.49.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
412
+ "model.layers.49.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
413
+ "model.layers.49.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
414
+ "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
415
+ "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
416
+ "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
417
+ "model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
418
+ "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
419
+ "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
420
+ "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
421
+ "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
422
+ "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
423
+ "model.layers.50.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
424
+ "model.layers.50.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
425
+ "model.layers.50.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
426
+ "model.layers.50.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
427
+ "model.layers.50.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
428
+ "model.layers.50.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
429
+ "model.layers.50.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
430
+ "model.layers.50.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
431
+ "model.layers.50.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
432
+ "model.layers.51.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
433
+ "model.layers.51.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
434
+ "model.layers.51.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
435
+ "model.layers.51.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
436
+ "model.layers.51.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
437
+ "model.layers.51.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
438
+ "model.layers.51.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
439
+ "model.layers.51.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
440
+ "model.layers.51.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
441
+ "model.layers.52.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
442
+ "model.layers.52.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
443
+ "model.layers.52.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
444
+ "model.layers.52.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
445
+ "model.layers.52.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
446
+ "model.layers.52.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
447
+ "model.layers.52.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
448
+ "model.layers.52.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
449
+ "model.layers.52.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
450
+ "model.layers.53.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
451
+ "model.layers.53.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
452
+ "model.layers.53.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
453
+ "model.layers.53.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
454
+ "model.layers.53.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
455
+ "model.layers.53.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
456
+ "model.layers.53.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
457
+ "model.layers.53.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
458
+ "model.layers.53.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
459
+ "model.layers.54.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
460
+ "model.layers.54.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
461
+ "model.layers.54.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
462
+ "model.layers.54.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
463
+ "model.layers.54.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
464
+ "model.layers.54.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
465
+ "model.layers.54.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
466
+ "model.layers.54.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
467
+ "model.layers.54.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
468
+ "model.layers.55.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
469
+ "model.layers.55.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
470
+ "model.layers.55.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
471
+ "model.layers.55.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
472
+ "model.layers.55.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
473
+ "model.layers.55.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
474
+ "model.layers.55.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
475
+ "model.layers.55.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
476
+ "model.layers.55.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
477
+ "model.layers.56.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
478
+ "model.layers.56.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
479
+ "model.layers.56.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
480
+ "model.layers.56.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
481
+ "model.layers.56.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
482
+ "model.layers.56.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
483
+ "model.layers.56.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
484
+ "model.layers.56.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
485
+ "model.layers.56.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
486
+ "model.layers.57.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
487
+ "model.layers.57.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
488
+ "model.layers.57.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
489
+ "model.layers.57.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
490
+ "model.layers.57.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
491
+ "model.layers.57.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
492
+ "model.layers.57.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
493
+ "model.layers.57.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
494
+ "model.layers.57.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
495
+ "model.layers.58.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
496
+ "model.layers.58.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
497
+ "model.layers.58.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
498
+ "model.layers.58.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
499
+ "model.layers.58.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
500
+ "model.layers.58.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
501
+ "model.layers.58.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
502
+ "model.layers.58.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
503
+ "model.layers.58.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
504
+ "model.layers.59.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
505
+ "model.layers.59.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
506
+ "model.layers.59.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
507
+ "model.layers.59.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
508
+ "model.layers.59.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
509
+ "model.layers.59.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
510
+ "model.layers.59.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
511
+ "model.layers.59.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
512
+ "model.layers.59.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
513
+ "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
514
+ "model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
515
+ "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
516
+ "model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
517
+ "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
518
+ "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
519
+ "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
520
+ "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
521
+ "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
522
+ "model.layers.60.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
523
+ "model.layers.60.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
524
+ "model.layers.60.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
525
+ "model.layers.60.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
526
+ "model.layers.60.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
527
+ "model.layers.60.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
528
+ "model.layers.60.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
529
+ "model.layers.60.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
530
+ "model.layers.60.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
531
+ "model.layers.61.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
532
+ "model.layers.61.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
533
+ "model.layers.61.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
534
+ "model.layers.61.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
535
+ "model.layers.61.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
536
+ "model.layers.61.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
537
+ "model.layers.61.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
538
+ "model.layers.61.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
539
+ "model.layers.61.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
540
+ "model.layers.62.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
541
+ "model.layers.62.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
542
+ "model.layers.62.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
543
+ "model.layers.62.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
544
+ "model.layers.62.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
545
+ "model.layers.62.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
546
+ "model.layers.62.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
547
+ "model.layers.62.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
548
+ "model.layers.62.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
549
+ "model.layers.63.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
550
+ "model.layers.63.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
551
+ "model.layers.63.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
552
+ "model.layers.63.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
553
+ "model.layers.63.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
554
+ "model.layers.63.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
555
+ "model.layers.63.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
556
+ "model.layers.63.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
557
+ "model.layers.63.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
558
+ "model.layers.64.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
559
+ "model.layers.64.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
560
+ "model.layers.64.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
561
+ "model.layers.64.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
562
+ "model.layers.64.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
563
+ "model.layers.64.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
564
+ "model.layers.64.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
565
+ "model.layers.64.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
566
+ "model.layers.64.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
567
+ "model.layers.65.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
568
+ "model.layers.65.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
569
+ "model.layers.65.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
570
+ "model.layers.65.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
571
+ "model.layers.65.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
572
+ "model.layers.65.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
573
+ "model.layers.65.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
574
+ "model.layers.65.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
575
+ "model.layers.65.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
576
+ "model.layers.66.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
577
+ "model.layers.66.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
578
+ "model.layers.66.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
579
+ "model.layers.66.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
580
+ "model.layers.66.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
581
+ "model.layers.66.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
582
+ "model.layers.66.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
583
+ "model.layers.66.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
584
+ "model.layers.66.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
585
+ "model.layers.67.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
586
+ "model.layers.67.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
587
+ "model.layers.67.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
588
+ "model.layers.67.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
589
+ "model.layers.67.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
590
+ "model.layers.67.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
591
+ "model.layers.67.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
592
+ "model.layers.67.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
593
+ "model.layers.67.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
594
+ "model.layers.68.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
595
+ "model.layers.68.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
596
+ "model.layers.68.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
597
+ "model.layers.68.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
598
+ "model.layers.68.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
599
+ "model.layers.68.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
600
+ "model.layers.68.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
601
+ "model.layers.68.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
602
+ "model.layers.68.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
603
+ "model.layers.69.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
604
+ "model.layers.69.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
605
+ "model.layers.69.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
606
+ "model.layers.69.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
607
+ "model.layers.69.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
608
+ "model.layers.69.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
609
+ "model.layers.69.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
610
+ "model.layers.69.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
611
+ "model.layers.69.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
612
+ "model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
613
+ "model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
614
+ "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
615
+ "model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
616
+ "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
617
+ "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
618
+ "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
619
+ "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
620
+ "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
621
+ "model.layers.70.input_layernorm.weight": "pytorch_model-00006-of-00006.bin",
622
+ "model.layers.70.mlp.down_proj.weight": "pytorch_model-00006-of-00006.bin",
623
+ "model.layers.70.mlp.gate_proj.weight": "pytorch_model-00006-of-00006.bin",
624
+ "model.layers.70.mlp.up_proj.weight": "pytorch_model-00006-of-00006.bin",
625
+ "model.layers.70.post_attention_layernorm.weight": "pytorch_model-00006-of-00006.bin",
626
+ "model.layers.70.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
627
+ "model.layers.70.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
628
+ "model.layers.70.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
629
+ "model.layers.70.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
630
+ "model.layers.71.input_layernorm.weight": "pytorch_model-00006-of-00006.bin",
631
+ "model.layers.71.mlp.down_proj.weight": "pytorch_model-00006-of-00006.bin",
632
+ "model.layers.71.mlp.gate_proj.weight": "pytorch_model-00006-of-00006.bin",
633
+ "model.layers.71.mlp.up_proj.weight": "pytorch_model-00006-of-00006.bin",
634
+ "model.layers.71.post_attention_layernorm.weight": "pytorch_model-00006-of-00006.bin",
635
+ "model.layers.71.self_attn.k_proj.weight": "pytorch_model-00006-of-00006.bin",
636
+ "model.layers.71.self_attn.o_proj.weight": "pytorch_model-00006-of-00006.bin",
637
+ "model.layers.71.self_attn.q_proj.weight": "pytorch_model-00006-of-00006.bin",
638
+ "model.layers.71.self_attn.v_proj.weight": "pytorch_model-00006-of-00006.bin",
639
+ "model.layers.72.input_layernorm.weight": "pytorch_model-00006-of-00006.bin",
640
+ "model.layers.72.mlp.down_proj.weight": "pytorch_model-00006-of-00006.bin",
641
+ "model.layers.72.mlp.gate_proj.weight": "pytorch_model-00006-of-00006.bin",
642
+ "model.layers.72.mlp.up_proj.weight": "pytorch_model-00006-of-00006.bin",
643
+ "model.layers.72.post_attention_layernorm.weight": "pytorch_model-00006-of-00006.bin",
644
+ "model.layers.72.self_attn.k_proj.weight": "pytorch_model-00006-of-00006.bin",
645
+ "model.layers.72.self_attn.o_proj.weight": "pytorch_model-00006-of-00006.bin",
646
+ "model.layers.72.self_attn.q_proj.weight": "pytorch_model-00006-of-00006.bin",
647
+ "model.layers.72.self_attn.v_proj.weight": "pytorch_model-00006-of-00006.bin",
648
+ "model.layers.73.input_layernorm.weight": "pytorch_model-00006-of-00006.bin",
649
+ "model.layers.73.mlp.down_proj.weight": "pytorch_model-00006-of-00006.bin",
650
+ "model.layers.73.mlp.gate_proj.weight": "pytorch_model-00006-of-00006.bin",
651
+ "model.layers.73.mlp.up_proj.weight": "pytorch_model-00006-of-00006.bin",
652
+ "model.layers.73.post_attention_layernorm.weight": "pytorch_model-00006-of-00006.bin",
653
+ "model.layers.73.self_attn.k_proj.weight": "pytorch_model-00006-of-00006.bin",
654
+ "model.layers.73.self_attn.o_proj.weight": "pytorch_model-00006-of-00006.bin",
655
+ "model.layers.73.self_attn.q_proj.weight": "pytorch_model-00006-of-00006.bin",
656
+ "model.layers.73.self_attn.v_proj.weight": "pytorch_model-00006-of-00006.bin",
657
+ "model.layers.74.input_layernorm.weight": "pytorch_model-00006-of-00006.bin",
658
+ "model.layers.74.mlp.down_proj.weight": "pytorch_model-00006-of-00006.bin",
659
+ "model.layers.74.mlp.gate_proj.weight": "pytorch_model-00006-of-00006.bin",
660
+ "model.layers.74.mlp.up_proj.weight": "pytorch_model-00006-of-00006.bin",
661
+ "model.layers.74.post_attention_layernorm.weight": "pytorch_model-00006-of-00006.bin",
662
+ "model.layers.74.self_attn.k_proj.weight": "pytorch_model-00006-of-00006.bin",
663
+ "model.layers.74.self_attn.o_proj.weight": "pytorch_model-00006-of-00006.bin",
664
+ "model.layers.74.self_attn.q_proj.weight": "pytorch_model-00006-of-00006.bin",
665
+ "model.layers.74.self_attn.v_proj.weight": "pytorch_model-00006-of-00006.bin",
666
+ "model.layers.75.input_layernorm.weight": "pytorch_model-00006-of-00006.bin",
667
+ "model.layers.75.mlp.down_proj.weight": "pytorch_model-00006-of-00006.bin",
668
+ "model.layers.75.mlp.gate_proj.weight": "pytorch_model-00006-of-00006.bin",
669
+ "model.layers.75.mlp.up_proj.weight": "pytorch_model-00006-of-00006.bin",
670
+ "model.layers.75.post_attention_layernorm.weight": "pytorch_model-00006-of-00006.bin",
671
+ "model.layers.75.self_attn.k_proj.weight": "pytorch_model-00006-of-00006.bin",
672
+ "model.layers.75.self_attn.o_proj.weight": "pytorch_model-00006-of-00006.bin",
673
+ "model.layers.75.self_attn.q_proj.weight": "pytorch_model-00006-of-00006.bin",
674
+ "model.layers.75.self_attn.v_proj.weight": "pytorch_model-00006-of-00006.bin",
675
+ "model.layers.76.input_layernorm.weight": "pytorch_model-00006-of-00006.bin",
676
+ "model.layers.76.mlp.down_proj.weight": "pytorch_model-00006-of-00006.bin",
677
+ "model.layers.76.mlp.gate_proj.weight": "pytorch_model-00006-of-00006.bin",
678
+ "model.layers.76.mlp.up_proj.weight": "pytorch_model-00006-of-00006.bin",
679
+ "model.layers.76.post_attention_layernorm.weight": "pytorch_model-00006-of-00006.bin",
680
+ "model.layers.76.self_attn.k_proj.weight": "pytorch_model-00006-of-00006.bin",
681
+ "model.layers.76.self_attn.o_proj.weight": "pytorch_model-00006-of-00006.bin",
682
+ "model.layers.76.self_attn.q_proj.weight": "pytorch_model-00006-of-00006.bin",
683
+ "model.layers.76.self_attn.v_proj.weight": "pytorch_model-00006-of-00006.bin",
684
+ "model.layers.77.input_layernorm.weight": "pytorch_model-00006-of-00006.bin",
685
+ "model.layers.77.mlp.down_proj.weight": "pytorch_model-00006-of-00006.bin",
686
+ "model.layers.77.mlp.gate_proj.weight": "pytorch_model-00006-of-00006.bin",
687
+ "model.layers.77.mlp.up_proj.weight": "pytorch_model-00006-of-00006.bin",
688
+ "model.layers.77.post_attention_layernorm.weight": "pytorch_model-00006-of-00006.bin",
689
+ "model.layers.77.self_attn.k_proj.weight": "pytorch_model-00006-of-00006.bin",
690
+ "model.layers.77.self_attn.o_proj.weight": "pytorch_model-00006-of-00006.bin",
691
+ "model.layers.77.self_attn.q_proj.weight": "pytorch_model-00006-of-00006.bin",
692
+ "model.layers.77.self_attn.v_proj.weight": "pytorch_model-00006-of-00006.bin",
693
+ "model.layers.78.input_layernorm.weight": "pytorch_model-00006-of-00006.bin",
694
+ "model.layers.78.mlp.down_proj.weight": "pytorch_model-00006-of-00006.bin",
695
+ "model.layers.78.mlp.gate_proj.weight": "pytorch_model-00006-of-00006.bin",
696
+ "model.layers.78.mlp.up_proj.weight": "pytorch_model-00006-of-00006.bin",
697
+ "model.layers.78.post_attention_layernorm.weight": "pytorch_model-00006-of-00006.bin",
698
+ "model.layers.78.self_attn.k_proj.weight": "pytorch_model-00006-of-00006.bin",
699
+ "model.layers.78.self_attn.o_proj.weight": "pytorch_model-00006-of-00006.bin",
700
+ "model.layers.78.self_attn.q_proj.weight": "pytorch_model-00006-of-00006.bin",
701
+ "model.layers.78.self_attn.v_proj.weight": "pytorch_model-00006-of-00006.bin",
702
+ "model.layers.79.input_layernorm.weight": "pytorch_model-00006-of-00006.bin",
703
+ "model.layers.79.mlp.down_proj.weight": "pytorch_model-00006-of-00006.bin",
704
+ "model.layers.79.mlp.gate_proj.weight": "pytorch_model-00006-of-00006.bin",
705
+ "model.layers.79.mlp.up_proj.weight": "pytorch_model-00006-of-00006.bin",
706
+ "model.layers.79.post_attention_layernorm.weight": "pytorch_model-00006-of-00006.bin",
707
+ "model.layers.79.self_attn.k_proj.weight": "pytorch_model-00006-of-00006.bin",
708
+ "model.layers.79.self_attn.o_proj.weight": "pytorch_model-00006-of-00006.bin",
709
+ "model.layers.79.self_attn.q_proj.weight": "pytorch_model-00006-of-00006.bin",
710
+ "model.layers.79.self_attn.v_proj.weight": "pytorch_model-00006-of-00006.bin",
711
+ "model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
712
+ "model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
713
+ "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
714
+ "model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
715
+ "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
716
+ "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
717
+ "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
718
+ "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
719
+ "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
720
+ "model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
721
+ "model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
722
+ "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
723
+ "model.layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
724
+ "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
725
+ "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
726
+ "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
727
+ "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
728
+ "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
729
+ "model.norm.weight": "pytorch_model-00006-of-00006.bin"
730
+ }
731
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|begin_of_text|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|end_of_text|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ }
16
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4a4ca9d0a58168cb02f13950d12275d1cb3bccb470a907328f2d2e495116c73
3
+ size 20680501
tokenizer_config.json ADDED
@@ -0,0 +1,926 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<|begin_of_text|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<|end_of_text|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "250000": {
20
+ "content": "<|fim_prefix|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "250001": {
28
+ "content": "<|fim_middle|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "250002": {
36
+ "content": "<|fim_suffix|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "250003": {
44
+ "content": "<|fim_pad|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "250004": {
52
+ "content": "<|filename|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "250005": {
60
+ "content": "<|gh_stars|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "250006": {
68
+ "content": "<|issue_start|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "250007": {
76
+ "content": "<|issue_comment|>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "250008": {
84
+ "content": "<|issue_closed|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "250009": {
92
+ "content": "<|jupyter_start|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "250010": {
100
+ "content": "<|jupyter_text|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "250011": {
108
+ "content": "<|jupyter_code|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "250012": {
116
+ "content": "<|jupyter_output|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "250013": {
124
+ "content": "<|empty_output|>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "250014": {
132
+ "content": "<|commit_before|>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "250015": {
140
+ "content": "<|commit_msg|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "250016": {
148
+ "content": "<|commit_after|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "250017": {
156
+ "content": "<|reponame|>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "250018": {
164
+ "content": "<|im_start|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "250019": {
172
+ "content": "<|im_end|>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "250020": {
180
+ "content": "<|sys_start|>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "250021": {
188
+ "content": "<|sys_end|>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "250022": {
196
+ "content": "reserved_special_token_0",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "250023": {
204
+ "content": "reserved_special_token_1",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "250024": {
212
+ "content": "reserved_special_token_2",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "250025": {
220
+ "content": "reserved_special_token_3",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "250026": {
228
+ "content": "reserved_special_token_4",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "250027": {
236
+ "content": "reserved_special_token_5",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "250028": {
244
+ "content": "reserved_special_token_6",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "250029": {
252
+ "content": "reserved_special_token_7",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "250030": {
260
+ "content": "reserved_special_token_8",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "250031": {
268
+ "content": "reserved_special_token_9",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "250032": {
276
+ "content": "reserved_special_token_10",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "250033": {
284
+ "content": "reserved_special_token_11",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "250034": {
292
+ "content": "reserved_special_token_12",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "250035": {
300
+ "content": "reserved_special_token_13",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "250036": {
308
+ "content": "reserved_special_token_14",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "250037": {
316
+ "content": "reserved_special_token_15",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "250038": {
324
+ "content": "reserved_special_token_16",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "250039": {
332
+ "content": "reserved_special_token_17",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "250040": {
340
+ "content": "reserved_special_token_18",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "250041": {
348
+ "content": "reserved_special_token_19",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "250042": {
356
+ "content": "reserved_special_token_20",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "250043": {
364
+ "content": "reserved_special_token_21",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "250044": {
372
+ "content": "reserved_special_token_22",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "250045": {
380
+ "content": "reserved_special_token_23",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "250046": {
388
+ "content": "reserved_special_token_24",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "250047": {
396
+ "content": "reserved_special_token_25",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "250048": {
404
+ "content": "reserved_special_token_26",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "250049": {
412
+ "content": "reserved_special_token_27",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "250050": {
420
+ "content": "reserved_special_token_28",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "250051": {
428
+ "content": "reserved_special_token_29",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "250052": {
436
+ "content": "reserved_special_token_30",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "250053": {
444
+ "content": "reserved_special_token_31",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "250054": {
452
+ "content": "reserved_special_token_32",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "250055": {
460
+ "content": "reserved_special_token_33",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "250056": {
468
+ "content": "reserved_special_token_34",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "250057": {
476
+ "content": "reserved_special_token_35",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "250058": {
484
+ "content": "reserved_special_token_36",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "250059": {
492
+ "content": "reserved_special_token_37",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "250060": {
500
+ "content": "reserved_special_token_38",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "250061": {
508
+ "content": "reserved_special_token_39",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "250062": {
516
+ "content": "reserved_special_token_40",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "250063": {
524
+ "content": "reserved_special_token_41",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "250064": {
532
+ "content": "reserved_special_token_42",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "250065": {
540
+ "content": "reserved_special_token_43",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "250066": {
548
+ "content": "reserved_special_token_44",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "250067": {
556
+ "content": "reserved_special_token_45",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "250068": {
564
+ "content": "reserved_special_token_46",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "250069": {
572
+ "content": "reserved_special_token_47",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "250070": {
580
+ "content": "reserved_special_token_48",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "250071": {
588
+ "content": "reserved_special_token_49",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "250072": {
596
+ "content": "reserved_special_token_50",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "250073": {
604
+ "content": "reserved_special_token_51",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "250074": {
612
+ "content": "reserved_special_token_52",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "250075": {
620
+ "content": "reserved_special_token_53",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "250076": {
628
+ "content": "reserved_special_token_54",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "250077": {
636
+ "content": "reserved_special_token_55",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "250078": {
644
+ "content": "reserved_special_token_56",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "250079": {
652
+ "content": "reserved_special_token_57",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "250080": {
660
+ "content": "reserved_special_token_58",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "250081": {
668
+ "content": "reserved_special_token_59",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "250082": {
676
+ "content": "reserved_special_token_60",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "250083": {
684
+ "content": "reserved_special_token_61",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "250084": {
692
+ "content": "reserved_special_token_62",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "250085": {
700
+ "content": "reserved_special_token_63",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "250086": {
708
+ "content": "reserved_special_token_64",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "250087": {
716
+ "content": "reserved_special_token_65",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "250088": {
724
+ "content": "reserved_special_token_66",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "250089": {
732
+ "content": "reserved_special_token_67",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "250090": {
740
+ "content": "reserved_special_token_68",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "250091": {
748
+ "content": "reserved_special_token_69",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "250092": {
756
+ "content": "reserved_special_token_70",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "250093": {
764
+ "content": "reserved_special_token_71",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "250094": {
772
+ "content": "reserved_special_token_72",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "250095": {
780
+ "content": "reserved_special_token_73",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "250096": {
788
+ "content": "reserved_special_token_74",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "250097": {
796
+ "content": "reserved_special_token_75",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "250098": {
804
+ "content": "reserved_special_token_76",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "250099": {
812
+ "content": "reserved_special_token_77",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "250100": {
820
+ "content": "reserved_special_token_78",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "250101": {
828
+ "content": "reserved_special_token_79",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ },
835
+ "250102": {
836
+ "content": "reserved_special_token_80",
837
+ "lstrip": false,
838
+ "normalized": false,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": true
842
+ },
843
+ "250103": {
844
+ "content": "reserved_special_token_81",
845
+ "lstrip": false,
846
+ "normalized": false,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": true
850
+ },
851
+ "250104": {
852
+ "content": "reserved_special_token_82",
853
+ "lstrip": false,
854
+ "normalized": false,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": true
858
+ },
859
+ "250105": {
860
+ "content": "reserved_special_token_83",
861
+ "lstrip": false,
862
+ "normalized": false,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": true
866
+ },
867
+ "250106": {
868
+ "content": "reserved_special_token_84",
869
+ "lstrip": false,
870
+ "normalized": false,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": true
874
+ },
875
+ "250107": {
876
+ "content": "reserved_special_token_85",
877
+ "lstrip": false,
878
+ "normalized": false,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": true
882
+ },
883
+ "250108": {
884
+ "content": "reserved_special_token_86",
885
+ "lstrip": false,
886
+ "normalized": false,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": true
890
+ },
891
+ "250109": {
892
+ "content": "reserved_special_token_87",
893
+ "lstrip": false,
894
+ "normalized": false,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": true
898
+ },
899
+ "250110": {
900
+ "content": "reserved_special_token_88",
901
+ "lstrip": false,
902
+ "normalized": false,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": true
906
+ },
907
+ "250111": {
908
+ "content": "reserved_special_token_89",
909
+ "lstrip": false,
910
+ "normalized": false,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": true
914
+ }
915
+ },
916
+ "bos_token": "<|begin_of_text|>",
917
+ "clean_up_tokenization_spaces": true,
918
+ "eos_token": "<|end_of_text|>",
919
+ "extra_special_tokens": {},
920
+ "model_input_names": [
921
+ "input_ids",
922
+ "attention_mask"
923
+ ],
924
+ "model_max_length": 1000000000000000019884624838656,
925
+ "tokenizer_class": "PreTrainedTokenizerFast"
926
+ }